Kapso
Kapso is a Python engine that runs experiments toward a goal, deploys the best solution, and keeps lessons from each run for machine learning developers.
What it is good for
- Finding the best machine learning approach through automated experiments
- Deploying a trained solution to Docker, Modal or similar targets
- Reusing lessons from past experiments on new projects
- Building predictive models on relational data
At a glance
- Who it is for
- Setup difficulty
- Technical ยท 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
- Framework or SDK
- Tasks
- Works with
- Claude Code, Codex, Docker, Modal, BentoCloud, LangGraph Platform
How to get started with Kapso
- Install Node.js 18 or newer, then install the Codex and Claude Code command-line tools and log in to both.
- Add a Leeroopedia key to your
.envfile asLEEROOPEDIA_API_KEY(recommended). - Install the package with
pip install leeroo-kapso(Python 3.10 or newer). - Run
kapso doctorto check the setup and see fixes for anything missing. - Optionally install the plugin in Claude Code, run
/kapso:setup, then/kapso:build <what you want>.
From the project's own documentation. If a step does not match what you see, the official pages have the latest instructions.
Before you try it
- Needs Node.js plus both Codex and Claude Code command-line tools logged in; there is no direct API fallback.
- An OpenAI key is optional and only used for knowledge graph and semantic search features.
- Leeroopedia is a hosted service; a new account comes with $20 of free credit.
- Requires Python 3.10 or newer.
Momentum
- Rank this week
- #18 in builder tools
- Best rank
- #18 week 46, 2026
- Stars gained last week
- +87
- GitHub stars
- 226
GitHub numbers as of Nov 16, 2026. Updated weekly.
Ranking history
Official links
Questions
- Is Kapso free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use Kapso?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does Kapso work with?
- According to its own documentation, it works with Claude Code, Codex, Docker, Modal, BentoCloud, and LangGraph Platform.
- How do I get started with Kapso?
- 1. Install Node.js 18 or newer, then install the Codex and Claude Code command-line tools and log in to both. 2. Add a Leeroopedia key to your .env file as LEEROOPEDIA_API_KEY (recommended). 3. Install the package with pip install leeroo-kapso (Python 3.10 or newer). 4. Run kapso doctor to check the setup and see fixes for anything missing. 5. Optionally install the plugin in Claude Code, run /kapso:setup, then /kapso:build <what you want>.
- What should I know before trying Kapso?
- Needs Node.js plus both Codex and Claude Code command-line tools logged in; there is no direct API fallback. An OpenAI key is optional and only used for knowledge graph and semantic search features. Leeroopedia is a hosted service; a new account comes with $20 of free credit. Requires Python 3.10 or newer.
- What is Kapso good for?
- Finding the best machine learning approach through automated experiments, deploying a trained solution to Docker, Modal or similar targets, reusing lessons from past experiments on new projects, and building predictive models on relational data.
Similar agents to Kapso
- RD-Agent
Automates data-driven AI research and development, with less emphasis on deployment and a scored bank of lessons.
- harness2
Refines the prompts, tools and skills around an agent rather than running experiments and deploying solutions.
- opal
Lets a coding agent rewrite the optimizer during model training, a narrower scope than whole experiment campaigns.
- Agent Zero
General-purpose agent that works on its own Linux computer, not focused on machine learning experiments.
- pydantic-ai
Code library for building agents with validated outputs, with no experimentation or lesson learning built in.
- Kestra
Kestra is an open-source orchestration platform that schedules and automates data, infrastructure, and AI agent workflows for technical teams.