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.
What it is good for
- Improving a measurable number over many automatic attempts
- Raising test coverage or lowering bundle size overnight
- Hunting and fixing bugs in a codebase automatically
- Running a security audit with a checklist of threats
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Skill or plugin
- Tasks
- Works with
- Claude Code, OpenCode, OpenAI Codex, Git
Momentum
- Rank this week
- Not ranked yet
- Best rank
- None yet
- GitHub stars
- 6,786
GitHub numbers as of Nov 2, 2026. Updated weekly.
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is autoresearch free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use autoresearch?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does autoresearch work with?
- According to its own documentation, it works with Claude Code, OpenCode, OpenAI Codex, and Git.
- What is autoresearch good for?
- Improving a measurable number over many automatic attempts, raising test coverage or lowering bundle size overnight, hunting and fixing bugs in a codebase automatically, and running a security audit with a checklist of threats.
Similar agents to autoresearch
- 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.
- 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.
- 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.
- 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.
- 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.
- claude-hud
Claude HUD is a plugin that shows context usage, active tools, and running agents in Claude Code while you work.