archon-memory

Ingest project documentation into Archon RAG sources with MD5 hashing.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/trezero/archon-trinity --skill archon-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: archon-memory
Source: https://github.com/trezero/archon-trinity/tree/main/integrations/claude-code/extensions/archon-memory
Command: npx skills add https://github.com/trezero/archon-trinity --skill archon-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill bridges a Claude Code assistant with an Archon RAG knowledge base to capture, index, and share long-term project documentation so assistants and teams can retrieve deep project context beyond ephemeral local memory.

Core Features & Use Cases

  • Project ingestion: discover README, docs/, and CLAUDE.md, read files in safe chunks, compute MD5 hashes, and ingest documents into Archon as inline RAG sources.
  • Sync and freshness checks: detect modified, added, or removed files, perform delete-and-readd syncs, poll ingestion progress, and update per-project state for reproducible updates.
  • Semantic search & shared knowledge: run project-scoped and cross-project semantic searches, add URL or local shared sources, and list shared knowledge across an ecosystem.
  • Task and project management: list, create, and update Archon tasks and query project metadata to coordinate multi-agent work.
  • Use case: Ingest a repo's docs, confirm indexing with a test query, keep .claude/archon-state.json current, and let multiple agents leverage the same knowledge base.

Quick Start

Use the archon-memory skill to ingest this project's documentation into Archon and then run a status check to verify indexing.

Frequently Asked Questions about archon-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I ingest project documentation into a RAG knowledge base?

To ingest project documentation into a RAG knowledge base, you can discover README, docs/, and CLAUDE.md files, read them in safe chunks, compute MD5 hashes, and ingest them as inline RAG sources.

How does semantic search work across multiple project documentation sets?

Semantic search across multiple project documentation sets works by running project-scoped or cross-project queries against an Archon RAG knowledge base to retrieve deep project context beyond local memory.

What is the best way to sync documentation files with a knowledge base?

The best way to sync documentation files with a knowledge base is to detect modified, added, or removed files, perform delete-and-readd syncs, poll ingestion progress, and update state files for reproducible updates.

Can I manage shared knowledge sources for multi-agent project work?

You can manage shared knowledge sources for multi-agent work by adding URL or local shared sources, listing shared knowledge across an ecosystem, and coordinating Archon tasks across agents using the same knowledge base.

Do I need a state file to track documentation indexing progress?

You need a state file like .claude/archon-state.json to track documentation indexing progress, verify reproducible ingestion, and keep project knowledge sources current during syncs.

Why does my project documentation ingestion require chunked reading?

Project documentation ingestion requires chunked reading with line limits to safely process large files, compute MD5 hashes for verification, and ensure reproducible RAG source creation.