Vibe Coding Discoverstash
View on GitHubOpen-source infrastructure for agents that learn from experience. Capture production traces and turn lessons into reusable knowledge and skills.
Stash captures agent traces and human corrections, curates durable knowledge, and makes it retrievable through a CLI, API, MCP, and skills. It is infrastructure for carrying lessons across agent runs without changing model weights.
Use Cases
Capture coding-agent sessions and human correctionsTurn agent experience into persistent knowledgeRetrieve shared knowledge in future agent runsPackage reusable agent instructions as skillsExpose agent memory through an MCP server
Built With
- Language
- Python
- Frameworks
- MCP
Tags
agent memory · continual learning · trace collection · knowledge base · skills · semantic search · multi-agent · MCP · coding agents · CLI