LaunchKit · 2026
Back to Skills

Local RAG system for agent memory using ChromaDB and sentence-transformers.

0
0 downloads
by @ttboy

Setup & Installation

openclaw skills install @ttboy/ouyang

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install ouyang

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

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: 'What did we decide about the API design last week?'

AGENT
  1. 1Run `recall 'API design decisions' --json` to query ChromaDB
  2. 2Retrieve top matching chunks from indexed session digests
  3. 3Include relevant context in the response to the user
OUTPUT

Agent responds with relevant past decisions pulled from indexed memory files