← Latest products

Open-source implementation of Stanford's self-learning agent framework

🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai. We implemented Stanford's Agentic Context Engineering paper which shows agents can improve their performance just by evolving their own context.

LibraryOpen source

2,606 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Derive

    github.com

    An open home for AI artifacts and workflows

    Hacker News11 pts

  2. Agent Swarm

    github.com

    Multi-agent self-learning teams (OSS)

    Hacker News63 pts

  3. An A2A-compatible

    github.com

    open-source framework for multi-agent networks

    Hacker News42 pts

  4. SkillGraph

    github.com

    Open-source agentic framework with skills instead of tools

    Hacker News19 pts

  5. An Open Source project for enhancing AI Agents in taking action

    github.com

    Action library for AI Agent

    Hacker News47 pts