progressive-agent
AGENTS.md2 starsChanged 9 months agoMITView on GitHub
This file is automatically updated by the agent. Each lesson is the result of a real mistake or discovery. Injected into the system prompt on every request. The agent learns from its own errors.
The file
Files
Agent Learnings
This file is automatically updated by the agent. Each lesson is the result of a real mistake or discovery. Injected into the system prompt on every request. The agent learns from its own errors.
Tool Usage Lessons
<!-- Lessons about how to use tools effectively -->Error Patterns
<!-- Common errors and their fixes -->User Preferences
<!-- Things the owner likes/dislikes about responses -->API Quirks
<!-- Quirks of external APIs the agent has discovered -->Performance Notes
<!-- What works fast vs slow -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.