gomaa

M4F-S

Gomaa — Autonomous Agent Memory OS.

Open M4F-S/gomaa → Does not match the four rules.

agent-memoryai-agentsclaudecursorhermes-agenthierarchical-memoryknowledge-graphllm-memorymcpmcp-servermodel-context-protocolobsidian

Does not say

no agent config and no instruction file at the root.

In its own words

AboutM4F-S/gomaa

Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.

README.md

Production-grade, local-first hierarchical memory engine for autonomous AI agents.

Gomaa equips AI agents (Hermes, OpenClaw, Claude Desktop, Cursor, Windsurf, CrewAI, LangChain) with permanent, structured long-term memory. It bridges human-readable Obsidian Markdown Vaults with high-speed PostgreSQL + pgvector (HNSW) or zero-config SQLite WAL, powering hybrid Reciprocal Rank Fusion (RRF) search, wikilink knowledge graphs, Ebbinghaus temporal decay, cross-agent fleet sharing, and asynchronous Google Drive cloud synchronization.

💡 Why Gomaa?

Most AI memory systems suffer from three fundamental flaws:

Black-Box Vector Blobs: Memories disappear into opaque vector databases. Humans cannot audit, correct, or curate what the agent learned.
Context Pollution: Without forgetting mechanisms, old noise accumulates and pollutes the agent's prompt window.
Domain Cross-Contamination: Research notes, credentials, and task scratchpads collide, causing hallucinations.

The repository's own description, then 8% of its README. Read the rest on GitHub ↗

Read from the repository's git tree on 2026-08-17.