engram-go

petersimmons1972/engram-go
★ 7 stars Go 🤖 AI/LLM Updated 1d ago
Self-hosted MCP memory server — 35 tools for persistent context across AI coding sessions. Runs on Docker with PostgreSQL + pgvector + Ollama.
View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "engram-go": {
      "command": "go",
      "args": [
        "run",
        "github.com/petersimmons1972/engram-go@latest"
      ]
    }
  }
}

README Excerpt

<p align="center"><img src="docs/hero.svg" alt="Engram — Persistent Memory for AI Agents" width="100%"></p> Every time you close your AI coding session, it forgets everything. The JWT library you chose. The expiry bug you spent an afternoon on. The pattern you explicitly rejected. Gone. Next session, the agent starts from zero and you start explaining.

Tools (11)

caused_bycontradictsdepends_onderived_fromfollowspart_ofrelates_toresolved_bysupersedessupportsused_in

Topics

ai-agentsai-memoryclaudeclaude-codedockergolangknowledge-graphllmmcpmemorymodel-context-protocolollamapgvectorpostgresql