Bỏ qua tới nội dung
TakoAPI
Quay lại kỹ năng

ouyang

bởi ttboy

Coding Agents & IDEs
—Chưa có đánh giá
Đánh giá của bạn

Tóm tắt

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

Mô tả

Kỹ năng này làm gì

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.

Khi nào nên dùng

  • 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

Quy trình ví dụ

ĐẦU VÀO

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

AGENT
  1. 1

    Run recall 'API design decisions' --json to query ChromaDB

  2. 2

    Retrieve top matching chunks from indexed session digests

  3. 3

    Include relevant context in the response to the user

ĐẦU RA

Agent responds with relevant past decisions pulled from indexed memory files

Cài đặt

clawhub install ttboy/ouyang

Chạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.

Liên kết