kayba-ai/recursive-improve
🪞 Make your agents recursively self-improve
This project helps AI developers and prompt engineers make their language model (LLM) agents smarter and more efficient over time. By observing how an agent performs on real tasks and identifying common issues like errors or wasted effort, this tool automatically suggests and applies fixes to the agent's code or prompts. The result is an agent that continuously improves its problem-solving abilities and resource usage.
153 stars.
Use this if you are building LLM-powered agents and want a systematic way to identify their weaknesses and automatically implement improvements for better performance and cost-effectiveness.
Not ideal if you are not working with LLM agents or if your agent's performance is already consistently perfect and doesn't require further optimization.
Stars
153
Forks
12
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 31, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/kayba-ai/recursive-improve"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ghostwright/phantom
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure...
dograh-hq/dograh
Open Source Voice Agent Platform
gmickel/flow-next
Plan-first AI workflow plugin for Claude Code, OpenAI Codex, and Factory Droid. Zero-dep task...
joseairosa/recall
Persistent cross-session memory for Claude & AI agents. Self-host on Redis/Valkey, or use the...
lintsinghua/claude-code-book
《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent...