AI agents that help you write, fix, and review code
416 AI agents and agent tools that help you write, fix, and review code. Ranked by momentum this week, with setup difficulty for each.
Ranks for week 44 (Oct 26 to Nov 1, 2026). Data as of Nov 2, 2026.
In short
- Gaining the most momentum this week: elephant-goldfish-model, ThinkRail, and tstack.
- Easiest to start with (nothing to install, or adds to an AI app you already use): elephant-goldfish-model, Floorplan, and Impeccable.
- #1
elephant-goldfish-model
Elephant-goldfish-model is a skill that helps teams plan software features with AI agents and stress-test the design before coding.
- #2
ThinkRail
ThinkRail is an agentic IDE that runs the pi coding agent in isolated workspaces for developers who vibe code.
- #3
tstack
tstack is a set of agent skills that take a pull request from change to merge for developers using Claude Code or Codex.
- #4
bla
BLA is a defensive tool that makes software harder for AI reverse-engineering agents to analyze, for people protecting their own apps and builds.
- #5
Floorplan
Floorplan is a skill that draws an interactive, plain-English map of your app's code for people who built it with AI help and need to understand it.
- #6
bama
BAMA is a set of agent skills that helps build a native Mac app from an existing app you like, for people who can describe what they want.
- #7
REA
REA is an MCP server that lets AI agents reverse engineer apps and native binaries to explain how a feature works.
- #8
Impeccable
Impeccable is a set of design commands for coding agents that steers, reviews, and polishes interfaces to avoid generic AI-looking design.
- #9
magpie
magpie is a local gateway app that lets you switch the AI model behind each coding agent from one menu bar for users with several agents or providers.
- #10
security-audit-skill
security-audit-skill is a skill that makes a coding agent run multi-phase security audits of a codebase and write verified findings for developers reviewing their own code.
- #11
agent-purge
agent-purge is a local tool that applies one persona prompt across several coding agents from a single web console or command line for developers.
- #12
Claude Code Game Studios
Claude Code Game Studios is a set of 49 AI agents and 74 workflow skills that gives a solo game developer studio-style structure for building games with Claude Code.
- #13
claude-mem
claude-mem is a plugin that gives AI coding agents like Claude Code a memory of past sessions for developers and vibe coders.
- #14
mcode-stack
mcode-stack is a set of skills and checklists for developers who build with AI coding agents, covering planning, review, context use, and long commands.
- #15
Nasiko
Nasiko is an agent runtime that shows what coding agents cost and lets you choose which model they use, for teams running multiple coding agents.
- #16
Codync
Codync is a self-hosted app that lets you message your coding agents as bots from your phone or computer, for people who already pay for Claude, Codex or similar tools.
- #17
Capri
Capri is a Windows desktop agent that carries out file, project, and computer tasks from plain-language requests using Claude Code, Codex, or Antigravity.
- #18
Expo Skills
Expo Skills is a skill that helps AI coding agents build, deploy, upgrade, and debug Expo apps for developers.
- #19
ste-zh
ste-zh is a skill that makes AI agents report task results in short, controlled Chinese for people who need clear status and evidence.
- #20
XERJ
XERJ is a local search engine and MCP server that lets AI agents search code, docs and logs without reading files one by one, for developers and coding-agent users.
- #21
Squadra
Squadra is a local coordination tool that keeps several Claude, Codex and Cursor coding windows on one shared task list with proof and independent review for developers.
- #22
BeautifulRust
BeautifulRust is a set of skills that teach coding agents to write, review, and port idiomatic Rust code for developers.
- #23
Orca
Orca is a desktop app that runs and tracks several coding agents at once, each in its own worktree, for developers and vibe coders.
- #24
HyperFrames
HyperFrames is a skill set that lets AI coding agents write HTML and render it into MP4 videos for creators and developers.
- #25
devbox
DevBox is an open source agent that takes a coding ticket, writes the change, runs tests and opens a draft pull request for engineering teams.
- #26
Ponytail
Ponytail is a skill that makes an AI coding agent write less code and reuse what already exists, for developers using Claude Code or Codex.
- #27
ECC
ECC is a plugin and toolkit that adds planning, testing, review, and memory routines to coding agents like Claude Code for developers building software.
- #28
graphify
Graphify is a skill that turns a project's code, docs, and PDFs into a queryable map for AI coding assistants, so they can answer questions without rereading every file.
- #29
Locally Uncensored
Locally Uncensored is a desktop app that runs chat, image, video and a coding agent on your own computer for people who want private AI without the cloud.
- #30
Deva
Deva is a desktop AI agent app that handles files, code, and scheduled tasks in one chat window for chat-first users.
- #31
Mavericks OS
Mavericks OS is a set of files and rules that keeps Claude Code projects on track across sessions and repositories for operators and small teams.
- #32
omnirush-gui
omnirush-gui is a desktop coding agent that works on your own projects for people who build software with AI.
- #33
oh-my-hermes
oh-my-hermes is an add-on for Hermes Agent that routes coding work to the right model and runs task graphs in parallel for developers.
- #34
Superpowers
Superpowers is a set of skills that makes coding agents plan, test, and review software work before writing code, for people building software with AI.
- #35
skills
Skills is a set of small agent instruction files that help coding agents like Claude Code and Codex build real software without losing the developer's control.
- #36
DS Remote
DS Remote is a plugin that lets you reach your local DeepSeek workspaces from a phone or browser when you are away from your computer.
- #37
skills
Skills is a set of instruction files that teach AI coding agents to create images, video, audio, and 3D assets through the Scenario MCP server for games and creative work.
- #38
Archify
Archify is a skill that turns an idea, plan, or codebase into an interactive diagram for people who need to understand or share a system.
- #39
herdr-gpui
herdr-gpui is a native desktop app that shows your Herdr terminal sessions, worktrees, and agent activity in one window for developers running Herdr.
- #40
pstack
pstack is a set of Agent Skills that makes AI coding agents write less, higher quality code for developers and engineering teams.
- #41
Free Claude Code
Free Claude Code is an agent app that lets you run Claude Code, Codex, and other coding agents on many free or low-cost models for developers and vibe coders.
- #42
Pullboard
Pullboard is a coordination queue that lets many AI coding agents build a software project from an approved spec, with a second agent checking each change.
- #43
Hyperfide
Hyperfide is a command-line agent workflow tool that keeps track of a codebase, its task plan, and its decisions for developers working with AI agents.
- #44
layerfs
LayerFS is a filesystem layer that gives each AI agent its own writable workspace over shared history for developers running parallel agents.
- #45
anti-slop
Anti Slop is a set of rules that stops an AI coding agent from producing generic UI, text, and code for people building websites and apps.
- #46
Dsh-TUI
Dsh-TUI is a terminal interface that adds live status, streaming output, and easy navigation to DeepSeek use for people who work in the terminal.
- #47
OmniRoute
OmniRoute is a self-hosted AI gateway that routes coding requests across many AI providers for developers who want to keep working when one provider runs out of quota.
- #48
failproofai
failproofai is an agent app that records what AI coding agents do and blocks dangerous actions for developers and teams running agents.
- #49
herdr
herdr is a terminal app that keeps your coding agents running in the background and shows which ones need your answer for developers running several coding agents.
- #50
OpenQodex
OpenQodex is an open source code review add-on that checks changes your coding agent writes before you push them.
-
opencode
opencode is an open source coding agent that writes and changes code in your project for developers.
-
n8n
n8n is a platform that builds and runs AI agents and automated workflows that connect your apps, for teams that want visual building with optional code.
-
Claw Code
Claw Code is a command-line coding agent that runs prompts and code tasks from a terminal for developers.
-
Open WebUI
Open WebUI is a self-hosted AI interface that runs local and cloud models, with tools and agent features, for people who want their own chat setup.
-
Claude Code
Claude Code is an agent app that handles routine coding work in your terminal for developers and vibe coders.
-
CC Switch
CC Switch is a desktop app that switches AI coding agents' API providers and manages their settings for developers.
-
gstack
gstack is a set of 23 slash-command skills that turn Claude Code into a virtual engineering team for solo founders and tech leads.
-
Codex
Codex is a coding agent that runs in your terminal and writes or fixes code on your computer for developers.
-
pi
Pi is a minimal, extensible coding agent CLI that runs in your terminal for developers who want to customize their own agent setup.
-
caveman
Caveman is a skill and proxy that cuts token use by making coding agents answer tersely and shrink the text they read, for developers and heavy AI users.
-
Agent Skills
Agent Skills is a set of skill files that make AI coding agents follow senior engineering workflows for building software.
-
Gemini CLI
Gemini CLI is an open-source terminal agent that helps developers query, edit, and debug code from the command line.
-
Understand-Anything
Understand-Anything is a plugin that turns a codebase, knowledge base, or docs into an interactive graph you can explore and ask questions about, for people new to a project.
-
rtk
rtk is a command-line proxy that shrinks the output of developer commands before an AI coding agent reads it, to cut token costs.
-
DeerFlow
DeerFlow is an open-source super agent that researches topics, writes code, and creates content over tasks that take minutes to hours, for people who need multi-step work done.
-
Ruflo
Ruflo is a coordination layer that runs teams of AI agents alongside Claude Code and Codex for developers who need multi-agent work done.
-
CodeGraph
CodeGraph is a code knowledge graph that gives AI coding agents the relevant source code in fewer steps, running locally on your machine for developers.
-
Cline
Cline is an open source coding agent that writes, edits, and runs code in your editor, terminal, or desktop app for developers.
-
OmO
OmO is a coding agent app that turns a single prompt into finished software work for developers and builders who want agents to handle multi-step jobs.
-
Open Interpreter
Open Interpreter is a coding agent that runs in your terminal and is built for low-cost AI models.
-
Warp
Warp is an agentic development environment that runs a built-in coding agent or your own CLI agent inside a terminal for developers.
-
Context7
Context7 is an MCP server that gives AI coding agents up-to-date library documentation for developers.
-
i-have-adhd
i-have-adhd is a skill that makes a coding assistant lead with the next action and skip filler text, for developers who find long answers hard to follow.
-
CLI-Anything
CLI-Anything is a toolkit that builds command-line interfaces so AI agents can control existing software for developers and power users.
-
CLIProxyAPI
CLIProxyAPI is a proxy server that lets apps use AI coding accounts from Claude Code, Codex, and other tools through one standard API for developers.
-
goose
goose is an agent app that runs on your computer and handles coding, research, writing, and automation tasks for developers and power users.
-
chrome-devtools-mcp
Chrome DevTools MCP is a connector that lets coding agents control and inspect a live Chrome browser for testing and debugging.
-
Multica
Multica is a workspace that lets teams assign issues to AI coding agents like teammates for developers and managers who run several agents.
-
Open Code Review
Open Code Review is a command-line tool that reviews code changes for defects and posts line-level comments for developers.
-
codebase-memory-mcp
codebase-memory-mcp is an MCP server that builds a local map of a code repository so AI coding agents can find and trace code faster.
-
LibreChat
LibreChat is a self-hosted chat app that runs AI agents, tools, and multiple AI models for teams that want their own ChatGPT-style interface.
-
claude-howto
claude-howto is a visual, example-driven guide that teaches developers to use Claude Code features with copy-paste templates.
-
claude-plugins-official
Claude Plugins Official is a curated directory of add-ons that extend Claude Code for developers and advanced users.
-
Sub2API
Sub2API is a self-hosted gateway that lets a team share Claude, OpenAI, Gemini and Grok subscriptions through one service.
-
agents
agents is a collection of plugins, agents, skills, and commands that adds specialist coding help to Claude Code, Codex, Cursor, and other coding tools for developers.
-
Codewhale
Codewhale is an agent app that reads a code repository, edits files, and runs commands in your terminal for developers using any AI model.
-
oh-my-claudecode
oh-my-claudecode is a plugin that runs several Claude Code agents in parallel on one task for developers who prefer not to learn Claude Code in depth.
-
Playwright MCP
Playwright MCP is an MCP server that lets AI apps control a web browser for you, for people who want their AI to click through websites and read pages.
-
AI Website Cloner Template
AI Website Cloner Template is a skill that recreates an existing website as a Next.js app for people who want a copy of a site's design and layout.
-
Claude Code Router
Claude Code Router is a local app that lets many AI coding agents share one set of model providers, with routing, fallbacks, and request logs for developers and power users.
-
skills
skills is a command-line tool that finds, installs, and manages instruction packs that teach coding agents specific tasks for developers.
-
oh-my-pi
Oh-my-pi is a coding agent that runs in the terminal and edits code with IDE-style tools for developers.
-
Reasonix
Reasonix is a coding agent that reads a project, edits files and runs tests for developers working in a terminal, desktop app, browser or editor.
-
codex-plugin-cc
Codex plugin for Claude Code that runs code reviews and hands off coding tasks to Codex from inside Claude Code, for developers who already use Claude Code.
-
OpenClaude
OpenClaude is a terminal coding agent that runs on many cloud and local model providers for developers who want one workflow.
-
GitHub MCP Server
GitHub MCP Server is a connector that lets AI tools read repositories, manage issues and pull requests, and check build runs on GitHub for developers.
-
agent-skills
Agent-skills is a collection of skill packs that teach AI coding agents to audit Vercel projects, review UI and writing, and deploy sites for developers.
-
context-mode
context-mode is an MCP server that keeps raw tool output out of an AI coding agent's context window for developers running long coding sessions.
-
Claude Code Templates
Claude Code Templates is a command-line tool that adds ready-made agents, commands, and settings to Claude Code for developers.
-
CodexPlusPlus
CodexPlusPlus is an agent app that manages Codex and other AI coding agents from one place for vibe coders and developers.
-
code-review-graph
code-review-graph is a local code map that lets AI coding tools read only the files a change touches, for developers reviewing code.
-
9Router
9Router is a self-hosted router that lets AI coding tools like Claude Code and Cursor use lower-cost or free models for developers and vibe coders hitting usage limits.
-
Serena
Serena is an MCP server that gives AI coding agents IDE-style code search, editing, and refactoring for developers working in large codebases.
-
TencentDB-Agent-Memory
TencentDB-Agent-Memory is a self-hosted memory hub that lets a team's AI agents share saved chats, skills, docs, and code context for developers.
-
claude-hud
Claude HUD is a plugin that shows context usage, active tools, and running agents in Claude Code while you work.
-
Crush
Crush is a terminal coding agent that works on your code with the AI model of your choice for developers who prefer the command line.
-
qwen-code
Qwen Code is an open-source AI coding agent that runs in your terminal and works on your project files for developers and vibe coders.
-
cmux
cmux is a macOS terminal app that alerts you when AI coding agents need input and organizes many parallel sessions for developers.
-
dbx
dbx is a lightweight database client that lets you browse, query, and manage 100+ databases, with a built-in AI SQL assistant, for developers and data users.
-
Vibe Kanban
Vibe Kanban is a kanban board that plans work and runs coding agents in isolated workspaces for developers and vibe coders.
-
beads
Beads is a command-line issue tracker that gives coding agents persistent memory of tasks and project facts.
-
planning-with-files
planning-with-files is a skill that keeps a written plan on disk so AI coding agents can resume long tasks after context loss for developers and power users.
-
AgenticSeek
AgenticSeek is a self-hosted agent app that browses the web, writes code, and plans tasks for people who want to keep their data on their own machine.
-
compound-engineering-plugin
Compound Engineering is a plugin of 36 skills that makes each coding task leave notes for the next one, for developers using AI coding agents.
-
Happy
Happy is an agent app that runs Claude, Codex, and Grok in one app for people who code with several AI models.
-
Claude Code Best V5 (CCB)
Claude Code Best V5 is an agent app that runs a Claude Code style coding agent in your terminal for developers who want to modify or debug it.
-
CodexBar
CodexBar is a menu bar app that shows how much of your AI coding limits you have left and when they reset, for developers using Codex and Claude Code.
-
Paseo
Paseo is an app that runs and coordinates several coding agents at once for developers working across desktop and phone.
-
khazix-skills
Khazix Skills is a collection of ready-made skills that teach AI agents like Claude Code and Codex to handle tasks such as disk cleanup, writing, and project notes.
-
skills
skills is a collection of agent skills that teaches AI coding agents how to work with Google products and Google Cloud.
-
jcode
jcode is a terminal coding agent that runs many agent sessions in parallel on one machine without using much memory.
-
OpenShell
OpenShell is a self-hosted runtime that lets autonomous AI agents run in isolated sandboxes with set limits on files, network, and credentials for developers and technical teams.
-
img2threejs
img2threejs is a skill that rebuilds an object from a reference image as Three.js code for 3D web scenes, without downloading models.
-
GitDiagram
GitDiagram is an MCP server and web tool that turns a GitHub repository into an architecture diagram or narrated video for people who need to understand a codebase.
-
Agent-Skills-for-Context-Engineering
A collection of skills that teach AI coding agents how to manage their context window for building and debugging agent systems.
-
opencodex
opencodex is a local gateway that lets Codex, Claude Code and similar coding tools use models from other providers such as Claude, Gemini, DeepSeek and Ollama for developers.
-
Coder
Coder is a self-hosted platform that gives developers cloud development environments and AI coding agents on their own infrastructure.
-
MCP Toolbox for Databases
MCP Toolbox for Databases is an open source MCP server that lets AI assistants and agents query and explore your databases for developers and data teams.
-
cc-connect
cc-connect is a bridge that lets you chat with local AI coding agents from messaging apps like Slack, Telegram, and Feishu for developers working away from their computer.
-
docker-android
docker-android is a Docker image that runs an Android emulator in a container for app testing, with a browser view and an MCP server for AI agents.
-
Paradev
Paradev is a desktop app that runs several coding agents in parallel, each on its own branch, for developers who already use coding agents in the terminal.
-
MCP for Unity
MCP for Unity is a connector that lets AI assistants control the Unity Editor to build game scenes and scripts for game developers.
-
codex-chatgpt-web
codex-chatgpt-web is a launcher that lets Codex use ChatGPT Web models from your own signed-in account, for people who want to avoid spending Codex quota.
-
Prompt Master
Prompt Master is a Claude skill that writes precise prompts for many AI tools, so users need fewer retries for ai-generated results.
-
cc-haha
cc-haha is a desktop app that puts Claude Code sessions, diffs, and agent teams in one local workspace for coders.
-
Skill Seekers
Skill Seekers is a tool that turns documentation sites, GitHub repos, and PDFs into Claude skills for developers and AI builders.
-
CloudCLI
CloudCLI is a web and mobile interface that lets you run and check Claude Code, Cursor CLI, and Codex sessions from any device.
-
AI-Research-SKILLs
AI-Research-SKILLs is a library of 98 skill files that teach Claude Code, Codex, or Gemini agents to carry out AI research tasks.
-
Orchestrator.inc
Orchestrator.inc is a desktop app that runs a fleet of coding agents on one project, each in its own branch, for developers who want parallel work merged without manual juggling.
-
MiMoCode
MiMoCode is a terminal-native AI coding assistant that reads, writes, and runs code for developers working in a command line.
-
ccstatusline
ccstatusline is a customizable status line for Claude Code that shows model, git, and token usage in the terminal for developers.
-
IDA Pro MCP
IDA Pro MCP is an MCP server that lets AI assistants like Claude read and work inside IDA Pro for reverse engineering binaries.
-
InsForge
InsForge is a backend platform that gives coding agents a database, auth, storage, and hosting for building full-stack apps.
-
HumanLayer
HumanLayer is a platform that runs coding agents on your machines so a team can steer them from one place for hard software problems.
-
OpenChamber
OpenChamber is an open-source workspace that runs AI coding agents on desktop, web, VS Code, and mobile, so developers can review and ship their work.
-
claude-skills
claude-skills is a skill that adds 67 specialized coding skills to Claude Code for full-stack developers.
-
GhidraMCP
GhidraMCP is an MCP server (a connector that lets AI apps like Claude use another tool) that lets AI models reverse engineer compiled programs in Ghidra.
-
CodeBurn
CodeBurn is a local tool that tracks what your AI coding tools cost, broken down by project, model and task, for developers.
-
Ekko Studio
Ekko Studio is a local-first workspace that runs multiple AI agents for chat, coding, and visual workflows for people who want to manage agents in one place.
-
Octop
Octop is a self-hosted AI assistant that runs multiple specialized agents for households and small teams.
-
Inspector
Inspector is a developer tool that tests and debugs MCP servers through a web UI, CLI, or terminal UI for developers building agent connectors.
-
Omnigent
Omnigent is an open-source agent app that runs Claude Code, Codex, Cursor, and custom agents together in one session for developers.
-
gsd-core
GSD Core is a set of instructions that adds a phased planning and verification workflow to AI coding agents for developers building software projects.
-
Trail-Code
Trail-Code is a context layer that gives coding agents like Claude Code and Cursor a map of your codebase and your team's past decisions for developers.
-
visual-explainer
Visual-explainer is a skill that turns terminal diagrams, diff reviews, and data tables into styled HTML pages for developers and technical readers.
-
drawio-skill
drawio-skill is an agent skill that turns text, code, and system sources into editable draw.io architecture diagrams for technical teams.
-
Desktop Commander
Desktop Commander is an MCP server that lets Claude and other AI apps search and edit files and run terminal commands on your computer for vibe coders and power users.
-
oh-my-opencode-slim
oh-my-opencode-slim is a plugin for OpenCode that splits coding jobs across a team of specialist AI agents for developers who use multiple models.
-
Plannotator
Plannotator is a local browser review surface that lets you mark up agent plans, documents, and code diffs and send feedback back to the agent for people who review AI coding work.
-
Worktrunk
Worktrunk is a command line tool that makes git worktrees easy to create, switch, and clean up for running several AI agents in parallel.
-
Claude Code Action
Claude Code Action is a GitHub action that answers questions and makes code changes on pull requests and issues for developer teams.
-
universal-modder
Universal-modder is a set of skills and tools that lets AI coding agents mod PC games you own, for people who want custom game changes without writing the code by hand.
-
Team-Architecture Factory for Claude Code
Team-Architecture Factory for Claude Code is a plugin that designs agent teams and their skills from a plain project description.
-
Munder Difflin
Munder Difflin is a desktop app that runs a team of terminal coding agents on your own computer for developers and power users who already pay for AI coding subscriptions.
-
mini-swe-agent
mini-swe-agent is a command line agent that fixes GitHub issues and runs terminal tasks for developers who want a simple, hackable tool.
-
Claude Squad
Claude Squad is a terminal app that runs several AI coding agents at once, each in its own workspace, for developers and vibe coders working on multiple tasks.
-
stitch-skills
Stitch-skills is a library of skill add-ons that teach coding agents to turn Google Stitch designs into code, design systems, and assets for designers and developers.
-
OpenRig
OpenRig is a command-line tool that runs a persistent team of Claude Code and Codex agents for developers working on shared projects.
-
SuperPlane
SuperPlane is a self-hosted or cloud system that turns routine backlog issues into reviewed pull requests for engineering teams.
-
superpowers-zh
superpowers-zh is a skill pack that gives AI coding tools a set of Chinese-language working methods for planning, testing, debugging and code review.
-
ZCode
ZCode is a coding agent workspace that runs as a desktop app, a web page, or a terminal agent for developers building software with AI.
-
Gentle-AI
Gentle-AI is a configuration layer that adds memory, a workflow, and review steps to AI coding agents for developers working on projects.
-
Repowise
Repowise is a codebase index that lets coding agents answer questions about code, callers, risk and tests without re-reading every file.
-
skills
Skills is a marketplace of security analysis plugins that teach Claude Code or Codex to audit code, test software, and review vulnerabilities.
-
fast-jev-compaction
fast-jev-compaction is a Claude Code plugin that shrinks long sessions by removing stale tool calls and results, without summarizing the conversation.
-
Engram
Engram is a persistent memory system that stops AI coding agents from forgetting your project between sessions.
-
Codex with ChatGPT
Codex with ChatGPT is a coding agent add-on that lets your ChatGPT web subscription plan and review code while Codex makes the edits, for developers and vibe coders.
-
PI-Desktop
PI-Desktop is a desktop app that runs a local AI coding agent and lets you manage projects, sessions, and plugins for it.
-
Waza
Waza is a set of eight skills that teach Claude Code, Codex, and Cursor engineering habits like planning, debugging, and reviewing code.
-
Backlog.md
Backlog.md is a markdown task manager that gives humans and AI coding agents a shared project board inside any Git repository.
-
Skills
Skills is a collection of agent skill folders that teaches Codex, Claude, and Cursor how to build landing pages, 3D scenes, and UI prompts for designers and builders.
-
Skills Manager
Skills Manager is a desktop app that organizes and syncs AI agent skills across many coding tools for people who use several agents.
-
agent-skills
Agent Skills is a skill registry that adds vetted instruction packs to AI coding agents for developers and vibe coders.
-
internet-court-skill
Internet Court skill is a catch-all agent skill that structures deals between AI agents, holds funds in escrow, and settles disputes for agent-to-agent commerce.
-
OpenPencil
OpenPencil is a vector design tool that turns text prompts into UI on a canvas, with AI agent teams working in parallel for designers and developers.
-
smolvm
smolvm is a tool that runs AI agents inside isolated virtual machines on your own computer or servers for developers and technical users.
-
Coucou
Coucou is an agent app that shows your AI coding agent sessions in the Mac notch and lets you approve their permission requests for developers using Claude Code and similar tools.
-
autoresearch
Autoresearch is a skill that makes Claude Code, OpenCode, or Codex repeatedly change, test, and keep or discard its work until a measurable goal is met, for people improving code or other numbers.
-
T3MP3ST
T3MP3ST is a self-hosted multi-agent framework that runs authorized red team tests on web apps, CTFs, and source code for security testers.
-
clawd-on-desk
Clawd on Desk is a desktop pet that shows what your AI coding agents are doing and asks you to approve their tool requests.
-
n8n-skills
n8n-skills is a set of Claude Code skills that helps build and deploy n8n automation workflows without guessing at syntax or setup.
-
LoopX
LoopX is a local-first control plane that keeps long-running agent work on goals, decisions and evidence across sessions and tools for engineers and researchers.
-
SwiftUI-Agent-Skill
SwiftUI-Agent-Skill is a skill that helps AI coding assistants write better SwiftUI code for iPhone and Mac apps for developers.
-
Kun
Kun is a desktop agent app that runs coding, writing, design, and research tasks on your own computer for developers and writers who want local control.
-
semble
Semble is a code search tool that lets coding agents pull only the relevant code snippets from a repo, for developers working with AI coding assistants.
-
21st MCP
21st MCP is an MCP server that lets Cursor, Claude Code, and Windsurf search, generate, and publish React and Tailwind UI components for developers building interfaces.
-
TUIOS
TUIOS is a terminal window manager that shows what your coding agents are doing and keeps sessions alive for developers running agents in a terminal.
-
agents-cli
agents-cli is a CLI and set of skills that teaches a coding assistant to build, test, and deploy AI agents on Google Cloud for developers.
-
emdash
Emdash is a desktop app that runs several AI coding agents in parallel for developers working on the same codebase.
-
ghidra-mcp
ghidra-mcp is an MCP server that lets AI tools analyze and document binaries in Ghidra for reverse engineers.
-
Lemonade
Lemonade is a local AI server that runs chat, coding, speech, and image models on your own PC for people who want free, private AI.
-
Maka
Maka is a desktop and terminal agent workspace that completes multi-step tasks and keeps a full local record of every action it took for developers and technical users.
-
anti-slop
Anti-slop is a set of opinionated Oxlint rules that flag low-evidence TypeScript and JavaScript patterns for developers who want stricter code review.
-
skills
skills is a set of skill plugins that teach AI coding agents .NET and C# development tasks for developers building .NET software.
-
aidlc-workflows
aidlc-workflows is a set of workflow rules that makes AI coding agents follow structured, approval-gated steps for building software.
-
gh-aw
gh-aw is a tool that lets developers write AI-powered repository automation in Markdown and run it through GitHub Actions.
-
mattpocock-skills-zh-CN
mattpocock-skills-zh-CN is a set of Simplified Chinese skills for coding agents that help plan changes, test code, and review codebase design for developers.
-
FrontierAgent
FrontierAgent is an agent app that runs research and file-based work in a terminal, with one agent or a team of parallel sub-agents, for people comfortable with the command line.
-
DevSpace
DevSpace is a self-hosted MCP server that lets ChatGPT and Claude read, edit, and run code in your local projects for developers who want that without uploading files to a third party.
-
tabularis
Tabularis is a desktop SQL workspace that lets you query databases and connect AI agents like Claude and Cursor to your schema for people who work with databases.
-
HAPI
HAPI is an agent app that lets you run and control Claude Code, Codex, and similar coding agents from your phone or browser, for developers and vibe coders.
-
DSH Go
DSH Go is an agent app that runs a coding agent on your Android phone and can also control your computer remotely.
-
agent-device
agent-device is a command-line tool and MCP server that lets AI coding agents control and check mobile, web, and desktop apps for developers.
-
Chat On Steroids
Chat On Steroids is a desktop app that lets ChatGPT edit your local files, run tests, and use your desktop for long coding tasks.
-
MonkeyCode
MonkeyCode is a self-hosted team AI workspace that lets staff hand office, coding, and design tasks to AI for small businesses and teams.
-
Agent Sprite Forge
Agent Sprite Forge is a skill that turns one approved character still into a full set of game-ready animated sprites for indie game makers.
-
DSH-better-sidebar
DSH-better-sidebar is a plugin that adds a richer sidebar with file, Git, terminal, and side chat pages for DSH users.
-
KiroCrew
KiroCrew is a self-hosted development workspace that keeps agent work running between sessions for developers who want long tasks done unattended.
-
ModLens
ModLens is a vision add-on that lets text-only coding agents read pasted images for users who need image understanding without a vision model.
-
Unity-MCP
Unity-MCP is an MCP server and plugin that lets AI apps like Claude, Cursor, and Copilot operate the Unity game engine for game developers.
-
design-extract
design-extract is a command-line tool that reads a website's design system and exports tokens and code for designers and developers building matching interfaces.
-
terminal-browser
terminal-browser is a browser that runs inside your terminal so you and a coding agent can view and use websites from the same tab.
-
scroll-craft
scroll-craft is an agent skill that helps a coding agent build premium scroll-driven websites with a real design standard, for people who want immersive landing pages.
-
CodeGraphContext
CodeGraphContext is an MCP server and command-line tool that maps a local code project into a graph so AI assistants can understand how its parts connect.
-
Claude Octopus
Claude Octopus is a plugin for Claude Code that runs several AI models on the same task to flag disagreements before you ship.
-
codeg
Codeg is a workspace that runs many AI coding agents in one place so developers can compare, resume, and combine their work.
-
unlazy
unlazy is a skill that makes AI agents finish substantial work by writing checkable acceptance gates and verifying results before reporting done, for people who give agents larger multi-step jobs.
-
Folkbench
Folkbench is a desktop tool that switches API providers for Claude Code and Codex and ranks relay services by uptime, latency, and price for developers.
-
VibeWise
VibeWise is a plugin that teaches you to build software while an AI writes the code, asking for your design choices first, for people who want to learn as they build.
-
Tutti
Tutti is a desktop workspace that lets people and several AI agents share context, files, and tasks so they stop needing copy-paste handoffs.
-
VulnClaw
VulnClaw is an agent app that runs penetration tests from plain-language requests for security testers working on authorized targets.
-
skills
skills is a catalog of instruction sets that teach Claude Code, Codex, and other coding agents to use NVIDIA software for robotics, simulation, CUDA, and RAG work.
-
SwiftUI-Agent-Skill
SwiftUI Expert Skill is a skill that adds SwiftUI best-practice guidance to AI coding tools for developers building iPhone and Mac apps.
-
DBHub
DBHub is an MCP server that lets AI apps query and explore your databases for developers and analysts, with read-only and row-limit guardrails.
-
Mercury
Mercury is an agent app that runs on your own machine and keeps working in the background, for people who want a personal assistant that remembers them and asks before acting.
-
cc-skills-golang
cc-skills-golang is a collection of Go skills that teach AI coding assistants production-ready Go practices for developers writing Go projects.
-
pstack-claude
pstack-claude is a set of skill plugins that adds rigorous, verified agent workflows to coding agents like Claude Code and Codex for developers.
-
fx
fx is a terminal coding agent that edits files and runs commands for developers working in a project folder.
-
SoL-Pi
SoL-Pi is an extension for the Pi coding agent that cuts token use and repeated model turns for developers running long coding tasks.
-
ctf-skills
ctf-skills is a set of agent skills that helps AI coding agents solve capture-the-flag security challenges for security students and hobbyists.
-
Monocode
Monocode is a desktop app that gives you one window to run and manage several coding agents for software projects.
-
Atomic Agent
Atomic Agent is a local-first agent app that runs on your own machine to browse the web, edit files, and run approved commands for people who want to keep their data local.
-
Stop That Shit
Stop That Shit is a skill and guard that keeps AI coding agents from adding unrequested hashes, checksums, and extra scope to a task.
-
Open Terminal
Open Terminal is a self-hosted remote shell that gives AI agents a place to run commands, manage files, and execute code for developers and tinkerers.
-
Zeron
Zeron is a desktop app that lets developers run and monitor several coding agents from one place, with local-first sessions.
-
workbuddy2api-hub
workbuddy2api-hub is a self-hosted gateway that lets tools like Codex and Claude Code use WorkBuddy and CodeBuddy accounts through standard OpenAI-style connections.
-
Agent Toolkit for AWS
Agent Toolkit for AWS is a set of MCP servers, skills, and plugins that help AI coding agents build, deploy, and manage applications on AWS for developers using AWS.
-
Godot AI
Godot AI is an MCP server that lets Claude Code, Codex, Cursor and other AI apps build and edit scenes in the Godot game engine.
-
Omnara
Omnara is a managed agent platform that runs AI agents with tools, memory, and machines for developers and teams who want to self-host.
-
Comet
Comet is a workflow platform that turns an idea into a resumable, tested coding task for AI agents, for developers and vibe coders.
-
RedAmon
RedAmon is an agent app that runs autonomous penetration tests and opens pull requests to fix the bugs it finds, for security testers and developers who own the systems they test.
-
vue-skills
vue-skills is a set of skills that teaches AI coding agents Vue 3 patterns for developers building Vue apps.
-
agent-rules-books
agent-rules-books is a set of instruction files that teach AI coding agents clean code and design habits from classic programming books.
-
jevgrep
jevgrep is a command-line tool that finds relevant code by answering plain questions about what a codebase does, for developers working with coding agents.
-
Argent
Argent is a toolkit that lets an AI assistant control, debug, and profile iOS and Android apps for developers testing mobile apps.
-
KiCAD-MCP-Server
KiCAD-MCP-Server is an MCP server that lets AI assistants like Claude control KiCad to design printed circuit boards.
-
PenguinHarness
PenguinHarness is an agent app that improves other AI agents automatically by evolving their prompts, skills, and tools for people building agent apps.
-
qwen-audio-agent
qwen-audio-agent is a realtime voice runtime that lets you talk to an AI agent while it keeps working on background tasks for you.
-
UX/UI Agent Skills
UX/UI Agent Skills is a skill that helps coding agents design interfaces to a professional standard and checks the result with 52 gates for developers.
-
Codenotch
Codenotch is a macOS app that shows how much usage limit your AI coding assistants have left, pinned to a screen edge, for developers and vibe coders who use several tools.
-
agent-skills
agent-skills is a skill that helps AI coding agents work accurately with Supabase for developers.
-
DSHA
DSHA is an Android app that runs a DeepSeek coding agent on your phone without root or Termux.
-
Pinvou Agent
Pinvou Agent is a desktop AI agent workspace that turns work, design, and coding requests into finished files for people who want results, not just chat replies.
-
x64dbg-mcp-server
x64dbg-mcp-server is an MCP server that lets AI assistants control the x64dbg debugger for reverse engineering programs and malware.
-
motion-design-skill
Motion-design-skill is a skill that teaches AI agents to choose timing, easing, and choreography for UI animations.
-
Skill Scanner
Skill Scanner is a security scanner that checks AI agent skills for prompt injection, data theft, and malicious code before you install them.
-
dsh-agent-teams
dsh-agent-teams is a plugin that lets one DeepSeek session coordinate a team of sub-agents on a complex task for people building multi-step AI work.
-
skills
Skills is a skill that gives Claude Code and Codex business, marketing, and UX frameworks drawn from bestselling books.
-
delegate-skills
delegate-skills is a set of skills that hands coding tasks to separate coding agent CLIs and keeps review and commits with you for developers using multiple AI coding tools.
-
Magic Context
Magic Context is a memory plugin that keeps coding agents from forgetting project details across long sessions for developers and vibe coders.
-
agent-teams-ai
Agent Teams is a free desktop app that runs a team of AI agents on coding and project work, shown on a kanban board for developers and project leads.
-
EAC-Desktop
EAC-Desktop is a desktop app that lets you run a DeepSeek AI agent on your computer for chats, project files, and plugin tools.
-
PR Lens
PR Lens is a skill and GitHub App that draws pull requests as animated diagrams so developers can understand code changes before reading the code.
-
MLX-Serve
MLX-Serve is a local model server and Mac app that runs AI models offline for chat, coding agents, and media for Mac users.
-
Solana MCP by Vybe
Solana MCP by Vybe is an MCP server (a connector that lets AI apps like Claude use another tool) that gives AI apps live Solana wallet, token, and trade data.
-
Vibe Coding Toolkit
Vibe Coding Toolkit is a set of instructions and prompts that sets up AI coding agents and project foundations for developers building with AI.
-
Nexting
Nexting is a remote control that lets you view and direct your AI coding agents on your computer from your phone or a wearable.
-
Happier
Happier is a multi-device control room that runs and orchestrates coding agents like Claude Code and Codex from your phone, desktop, or browser for developers managing parallel coding sessions.
-
zeroshot
zeroshot is an open-source tool that runs coding agents through a review workflow you define, for developers who want QA enforced by code.
-
Nimbalyst
Nimbalyst is a desktop app that lets you run and visually review several coding agents at once for building software.
-
shrt
shrt is a regression test tool that replays saved API call chains against a backend after each release for developers and vibe coders, and names the step and field that changed.
-
Gortex
Gortex is a code-intelligence engine that lets AI coding agents find code without reading whole files, cutting token use for developers working across repositories.
-
Loushang
Loushang is a terminal coding agent that keeps long software work resumable and traceable for developers using multiple AI models.
-
claude-reflect
claude-reflect is a plugin that remembers your corrections and preferences for Claude Code so you stop repeating yourself across sessions.
-
CC Safety Net
CC Safety Net is a guard that blocks destructive commands and access to secret files before AI coding agents run them, for developers and vibe coders.
-
Insomnia
Insomnia is a macOS menu bar app that keeps a MacBook awake with the lid closed for timed sessions, so long-running AI agents can keep working.
-
kotlin-footguns
kotlin-footguns is a set of agent skills that flag common Kotlin and Compose Multiplatform mistakes for developers building desktop and mobile apps.
-
AOCI-CODE
AOCI-CODE is an MCP server that gives coding agents a persistent, Git-versioned map of a codebase and its database schema for developers working on large systems.
-
LongHorizon
LongHorizon is an agent app that keeps AI agents working on long desktop and terminal tasks until results are verified for developers.
-
Ovis
Ovis is a free, open-source client that shows coding agents on your computer as chats you can answer from any browser or phone.
-
AIF
AIF is a local firewall that blocks unsafe actions by coding and personal AI agents before they run, for developers and power users.
-
coop-anything
Coop-anything is a set of playbooks and an MCP server that let an AI coding agent add co-op play to single-player games for friends.
-
zero
Zero is a terminal coding agent that edits files, runs commands, and keeps local sessions for developers who want to choose their own model and permissions.
-
dream-loop
dream-loop is a skill that helps an AI agent build games, apps, and 3D scenes with polished visuals by repeatedly comparing its work to a generated target image.
-
Lody
Lody is a shared workspace that lets a team share coding agent conversations and dispatch work to connected machines for developers.
-
website-rebuild-skill
website-rebuild-skill is a skill that has Claude Code or Codex rebuild a site from its code and verify the copy.
-
skills
skills is a set of agent skills that guide an AI coding agent through planning, building, checking, and documenting a change for developers and vibe coders.
-
agmsg
agmsg is a messaging tool that lets CLI AI coding agents like Claude Code and Codex send messages to each other locally for developers running several agents.
-
Empryo
Empryo is an AI coding agent that maps your code, edits functions by name, and runs your checks for developers.
-
IDA MCP
IDA MCP is an MCP server (a connector that lets AI apps like Claude use another tool) that lets AI agents reverse engineer binary files in IDA.
-
Reason Network
Reason Network is an agent app that lets your team's coding agents message each other across computers for developers working in separate sessions.
-
tty7
tty7 is a terminal app that keeps shells running after the window closes and lets AI coding agents drive other agents for developers.
-
openharness
Openharness is a desktop command center that runs and watches multiple coding agents across your computers from one window.
-
deja-vu
deja-vu is a local memory tool that lets coding agents search past sessions so they stop repeating solved bugs for developers using Claude Code, Codex, or Cursor.
-
opencode-telegram-bot
opencode-telegram-bot is a Telegram client that lets you run and monitor OpenCode coding tasks from your phone, with everything staying on your own machine.
-
ARTEX
ARTEX is an agent app that runs autonomous penetration tests in an isolated lab for security teams.
-
Figwright
Figwright is an MCP server that lets AI coding agents read Figma designs into code and write changes back to the canvas.
-
Tianshu use
Tianshu is a terminal coding agent that keeps goals, evidence, and test checks outside the chat so it finishes tasks and reports what it verified, for developers using DeepSeek.
-
Cloudroom
Cloudroom is a desktop app that runs AI coding agents on your Mac or in the cloud, so they keep working when your laptop is closed, for developers and vibe coders.
-
Cloudroom
Cloudroom is a desktop app that runs AI coding agents on your Mac or in the cloud, so they keep working after you close your laptop.
-
arena-skill
Arena-skill is a Claude Code skill that makes many Claude sub-agents compete in a bracket so you get a stronger answer when Claude's first attempt is poor.
-
PiDeck
PiDeck is a desktop app that manages AI coding agent sessions across several local projects for developers.
-
Shiping
Shiping is a desktop app that reads whatever is on your screen and answers questions about it, and listens to interview audio to suggest replies.
-
zoetrope
zoetrope is a terminal and browser viewer that draws a Claude Code or Codex session as a live flow graph for developers who want to see what their coding agents are doing.
-
SWE-AF
SWE-AF is an autonomous engineering team runtime that plans, codes, tests, and ships software changes as pull requests for developers.
-
Celesto
Celesto is a secure, persistent virtual computer that gives AI agents their own desktop for running code and browsing for developers.
-
Sno Station
Sno Station is an agent app that lets Codex, Claude Code, Cursor and similar agents share one memory and hand work to each other for people who use several AI coding tools.
-
Grandet
Grandet is a skill and MCP server that finds the lowest listed API price for an AI model and helps connect it for people who need cheap model access.
-
3dviz-pro-max
3dviz-pro-max is a skill that helps an AI coding agent build interactive 3D scenes with Three.js and Blender for creative visualization.
-
Agent Swarm
Agent Swarm is a self-hosted system that coordinates a lead agent and worker coding agents to finish company work for teams running their own operations.
-
agenttrail
Agenttrail is an agent app that shows what your local AI coding agents are doing across your project files for developers and project owners who run Codex or Claude Code.
-
AgentCraft
AgentCraft is an agent app that lets you manage a team of Claude coding agents through a Minecraft world for developers who want to watch and review AI work on their code.
-
Eleven
Eleven is a reverse-engineering app that lets an AI agent read, explain, and patch compiled programs and Android apps for developers and security researchers.
-
cezar
cezar is an agent app that runs many AI coding agents in parallel, locally or on a server, for developers who manage several coding tasks at once.
-
App Sandbox
App Sandbox is a virtual machine app that creates isolated Windows, Ubuntu, and macOS desktops for testing software and running computer-use agents.
-
sno-station-skills
Sno Station Skills is a set of 31 skills that adds peer review, quota handoffs, and daily reports to Claude Code and Codex for developers running long agent work.
-
Agent Office
Agent Office is a 3D office app that lets you run and watch coding agents at desks, each in its own GitHub project for developers.
-
Scrawl
Scrawl is a screen recorder that lets you show an agent a problem by marking up and narrating your screen, for developers using coding agents.
-
concord-mcp
Concord MCP is an MCP server that lets coding agents like Claude Code, Codex, and Cursor message each other, claim files, and hand off work for developers.
-
phi
phi is a fast terminal coding agent that edits code, runs commands, and connects to MCP tools for developers working in a repository.
-
claude-share
claude-share is a plugin that lets a teammate join your live Claude Code session through a shared link for developers pair programming.
-
Agents Universe
Agents Universe is a self-hosted platform that gives teams shared AI agents with project context for getting real work done.
-
PiG
PiG is a terminal coding agent that helps developers write and change code in a project, rebuilt in Go as a single binary.
-
PS5LM
PS5LM is a home model server that runs a language model on a jailbroken PS5 for anyone wanting private local AI on their network.
-
Mobile-use
Mobile-use is an agent app that lets you write, edit, and preview code with Claude Code on an Android phone.
-
Termio
Termio is a terminal-first app that runs and tracks coding agents so they keep working when you close your laptop, for developers using Claude Code or Codex.
-
agent-skill-gate
agent-skill-gate is a skill that makes an AI agent follow a fixed sequence of steps for converting an existing skill, checked by a program, for developers and skill authors.
-
Pi Pocket
Pi Pocket is a self-hosted, phone-friendly web app that lets you run and share Pi coding agent sessions from your phone.
-
genjutsu
genjutsu is a set of skills for Claude Code that adds motion, micro-interactions and design systems to web, Android and iOS interfaces for developers and designers building apps.
-
Kanzo
Kanzo is a self-hosted kanban board and MCP server that lets you and your coding agents share the same task list.
-
Whaleness
Whaleness is a mobile client that lets you follow and message a DeepSeek coding agent from your iPhone or Android phone.
-
Harp
Harp is a desktop terminal that runs many Claude Code and Codex agents side by side and shows which one needs you, for developers running several coding agents at once.
-
Orb
Orb is a desktop and iOS app that runs coding agents from one place across your subscriptions, API keys, and machines for developers.
-
seo-skills
seo-skills is a set of SEO instruction files that teach Claude Code, Cursor, and Codex to run SEO tasks for website owners and marketers.
-
Pi-Bolt
Pi-Bolt is a coding agent that starts faster and uses less CPU and memory than Pi on Node, for developers who work in the terminal.
-
Blender Agent Skills
Blender Agent Skills is a set of instruction packs that teach AI coding agents to do 3D modeling, rigging, and export work in Blender.
-
Mr. Mak Workspace
Mr. Mak Workspace is a desktop app that runs Codex and Claude Code chats in one place, with a visual workspace for reviewing their results.
-
slotstream
Slotstream is a local AI engine that runs a very large model on Apple Silicon Macs with 16 to 64 GB of memory, for people who want offline AI without a cloud account.
-
PGX
PGX is a lightweight Postgres runtime that creates thousands of short-lived, isolated databases for AI agents, tests, and CI jobs.
-
HERO-Anti-OverDefense
HERO-Anti-OverDefense is a paste-in instruction block that stops coding agents from building excess defenses and overbuilt code for simple feature requests.
-
CodeAF
CodeAF is a coding agent that runs multiple coding tasks at once in one window for developers working on open models.
-
Baize
Baize is a command-line coding agent that redacts personal data before it reaches the model, for people who vibe code or analyze data.
-
pi-dynamic-workflows
pi-dynamic-workflows is a plugin for the Pi coding agent that runs multi-agent workflows for large audits, reviews, and research.
-
0
0 is an agent app that finds and reviews security vulnerabilities in code for developers and security teams.
-
EvoFlow
EvoFlow is a desktop agent app that plans, runs, and recovers long multi-step tasks with a team of agents for people who want oversight of the work.
-
super-board
super-board is a skill set that turns a GitHub Project board into an automated build, test, and review loop for Claude Code, for developers who want tested pull requests from cards.
-
Agent Manager Lite
Agent Manager Lite is a macOS app that runs multiple separate Codex, Claude Code CLI, and Claude Desktop instances with their own accounts, keys, and sessions.
-
grok-self
grok-self is a command-line app that lets you chat with xAI's Grok AI from your terminal for people comfortable with a terminal window.
-
AlphaCode
AlphaCode is an agent app that writes, edits, and tests code from your terminal for developers, with a free built-in model.
-
mcp-gamehacking
mcp-gamehacking is an MCP server that gives Claude, Codex, and Cursor a set of reverse engineering and debugging tools for analyzing game binaries and anti-cheat systems.
-
Omalauncher
Omalauncher is an Android home screen app that runs an optional Linux system and sends prompts to coding agents like Claude Code and Codex.
-
npmscan-mcp-plugin
NPMScan plugin for Claude Code that checks npm packages for vulnerabilities, malware, and maintainer risks for developers and anyone managing dependencies.
-
Graphicle
Graphicle is a local MCP server that gives coding agents a code graph and project memory with cited file excerpts for developers.
-
MLView
MLView is a skill and VS Code viewer that turns an ML workflow into a source-linked interactive diagram for people reading ML code.
-
Locals
Locals is a local server that runs many AI coding agents at once on a Mac, faster and without sending data off the computer.
-
DSH Mobile
DSH Mobile is an agent app that lets you run a DeepSeek AI agent on an Android phone without root or Termux.
-
AxiomCode Graph
AxiomCode Graph is an MCP server that maps how code calls connect so AI coding agents can see what a change affects, for developers.
-
aidevops
aidevops is an OpenCode plugin and DevOps framework that runs AI agents for coding, Git workflows, and operations work.
-
Floe Agent
Floe Agent is an open-source AI agent workspace for iPad, iPhone and Android that keeps notes, files, code and a Linux environment on your device.
-
Gravitas
Gravitas is a skill that makes Gemini read files before editing, keep changes in scope, and prove its work with test results for developers using AI coding agents.
-
Nagi Skills
Nagi Skills is a set of skill files that teach Claude Code, Codex, and similar agents to plan ideas and verify finished work, for anyone using an AI agent.
-
OpenChatX
OpenChatX is a local agent app that lets ChatGPT run commands, edit files, and control your computer through one connection for people who want a customizable agent setup.
-
rederive
rederive is a skill that teaches you a codebase by asking you to design its parts yourself, for developers learning unfamiliar code.
-
Tracekit
Tracekit is a tool that records and checks every action an AI agent takes so you can see what it did and whether it was allowed, for developers and teams who need a record they can trust.
-
TaiSang
TaiSang is a self-hosted AI agent that reads and edits code, runs commands, and learns your work habits for developers using its web UI.
-
refactoring-ui-skill
Refactoring UI skill is a Claude skill that reviews web interface designs against a rulebook and generates design tokens for people building web UI with AI.
-
ACRYL
ACRYL is a desktop, web, and terminal workspace that keeps a project's context in one place so developers can switch between coding agents without losing their work.
-
Cache Tax
Cache Tax is a Claude Code mod that keeps your prompt cache warm during breaks and shows the estimated cost before a cold resend, for people who use Claude Code.
-
Dodaios
Dodaios is an open-source desktop app that runs coding agents, browser tasks and apps by voice or chat on your own machine for developers and power users.
-
OpenAgentCore
OpenAgentCore is a self-hosted agent runtime that lets developers run Codex, Claude Code or MiniMax Code on their own machines through the OpenAI SDK.
-
Octomind
Octomind is an agent app that runs an AI coding agent in your terminal, CI, or as a background daemon for developers working on repos.
-
k-style-ui-ux
k-style-ui-ux is a Claude Code, Codex, and Cursor plugin that turns a one-page product spec into a draft of Korean-style mobile app screens for people building early apps without a designer.
-
prismantis
prismantis is a Claude Code plugin that draws tables, charts, diagrams and code in color for people reading Claude Code replies in a terminal.
-
iphone-duo-skills
iphone-duo-skills is a set of skill files that teach an AI coding agent how to build iOS apps for the iPhone Duo foldable.
-
claude-skins
claude-skins is a plugin that changes how Claude Code looks, with icons, cards, charts and color themes, for people who use Claude Code in a terminal or desktop app.
-
HelixHarness
HelixHarness is a plugin that adds a team's own rules, knowledge and workflow to Codex or Claude Code for coding projects.
-
better-claude
better-claude is a set of plugins that add small quality-of-life features to Claude Code for developers who use it daily.
-
design.how
design.how is a set of agent skills that turns an app's existing UI into a design system and keeps new screens consistent with it.
-
Hatoba
Hatoba is a desktop SSH client with a built-in AI assistant that runs commands on your servers for developers and sysadmins who manage remote hosts.
-
claude-vibe-squad
claude-vibe-squad is an agent app that splits a coding goal into scoped tasks for separate AI coding agents, run locally for developers.
-
claude-flightdeck
Flightdeck is a Claude Code add-on that shows a live dashboard of context, cost, permission checks and subagents for people running Claude Code in a terminal.
-
Pi
Pi is a desktop app that lets developers watch, control, and coordinate Pi coding agents from one workspace.
-
MemoSync
MemoSync is a local workbench that lets you review, edit and audit the memory your coding agent keeps across sessions, for developers using Claude Code, Codex or Pi.
-
Eido
Eido is an agent app that helps developers describe a coding task, let an AI agent make changes, and review them in a macOS code editor.
-
Sloppy
Sloppy is a static analysis tool that catches messy code left by AI agents in PHP projects, for developers building with Laravel.
-
AICU-Graph
AICU-Graph is a self-hosted multi-agent platform that splits a complex task into a graph and assigns roles to AI coding agents for developers and teams.
-
console-skill
Console-skill is a set of 11 Claude skills that ports PlayStation 2 games you own to PC for players who want to mod them.
-
Agents Can Communicate
Agents Can Communicate is a local tool that lets AI coding sessions in different clients send messages and handoffs to each other for developers running parallel work.
-
my-better-claude
my-better-claude is a set of plugins that adds image previews, a prompt cache meter, a message queue, and a Codex review skill to Claude Code for developers.
-
Frink
Frink is a desktop app that runs several AI coding agents at once and starts multi-step workflows on a schedule or from events like new tickets for developers.
-
farol
farol is a CLI and GitHub Action that shows how risky a pull request merge is and which files to review first, for the person approving the change.
-
Agent-2
Agent-2 is an agent app that runs on your own machine to write code, run terminal commands, and carry out multi-step tasks for developers and security testers.
-
onsystem
onsystem is an MCP server that keeps coding agents on your design system for React and shadcn/ui code, for design-system and platform teams.
-
Autoloom
Autoloom is a desktop AI coding agent that checks whether changes are needed and verifies delivered code for developers using their own model provider.
-
Bittune
Bittune is an agent app that deploys and benchmarks AI model servers on your own GPUs for developers running vLLM or SGLang.
-
dsh-baton
dsh-baton is an MCP connector that hands coding tasks from Claude Code or Codex to a local DeepSeek coding agent for developers and vibe coders.
-
Teardown
Teardown is a toolkit that lets developers rebuild a software feature from how it behaves, without reading its source code, for teams that want a clean-room copy.
-
CodeLeveler
CodeLeveler is a local coding agent that reads a code repository, edits files, runs tests, and leaves changes for review by developers.
-
Agentaps
Agentaps is a desktop workspace that runs coding agents on your projects and lets you continue their chats from a phone browser.
-
PI WEB
PI WEB is a web UI that keeps Pi Coding Agent sessions running on your own machine so you can check on them from any browser.
-
AOCI-Wuch
AOCI-Wuch is a skill library that helps AI coding agents find and follow step-by-step guides for tasks like mobile app setup and Excel work.
-
Prevue
Prevue is a tool that lets AI coding agents see the Android Compose screens they build, redrawn in a browser for developers working without Android Studio.
-
Corgi
Corgi is an agent app that lets developers run and monitor several AI coding agents in one terminal.
-
Offrun
Offrun is a Mac app that runs several coding agents side by side so developers can keep work moving when one hits a usage limit.
-
Parsimony
Parsimony is a benchmark that ranks AI coding models by how much extra code they add to fix bugs, for developers comparing models.
-
Sphinx
Sphinx is a Git hook that quizzes you on what your AI coding agent's code does before it ships, for developers who use coding agents.