ouyang
by ttboy
Coding Agents & IDEsBrief
Local RAG system for agent memory using ChromaDB and sentence-transformers.
Description
What This Skill Does
Local RAG system that gives AI agents persistent memory across sessions. Uses ChromaDB for vector storage and sentence-transformers for local embeddings. Indexes session logs, daily notes, and markdown files for semantic search.
Runs entirely on local hardware with no external API calls, so memory stays private and works offline.
When to Use It
- Searching past conversations before answering a question
- Indexing daily notes so decisions persist across restarts
- Resuming context after an agent session ends and restarts
- Building a searchable log from agent session history
- Scheduling automatic memory updates every few hours via cron
Example Workflow
User asks: 'What did we decide about the API design last week?'
- 1
Run
recall 'API design decisions' --jsonto query ChromaDB - 2
Retrieve top matching chunks from indexed session digests
- 3
Include relevant context in the response to the user
Agent responds with relevant past decisions pulled from indexed memory files
Installation
clawhub install ttboy/ouyangRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.