Gentleman-Programming/engram

Health v2 · maintenance only

Adoption not part of the score

6184 stars · 655 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Engram is a persistent memory system for AI coding agents, shipped as a single agent-agnostic Go binary backed by SQLite with FTS5 full-text search. It exposes memory via MCP server, HTTP API, CLI, and an interactive TUI, integrating with agents like Claude Code, Cursor, Gemini CLI, and Codex.

Use cases

• give my AI coding agent persistent memory across sessions
• store and search project context for Claude Code
• share a memory brain across multiple AI agents
• remember decisions and notes between coding agent sessions
• set up MCP memory for Cursor or Windsurf
• full-text search of agent memories locally

When to choose

• you want local, zero-dependency persistent memory for any MCP-compatible coding agent
• you need one shared memory store across multiple agents
• you prefer a single self-contained binary with SQLite storage

When to avoid

• you need semantic vector-based memory rather than full-text search
• you want a hosted multi-tenant memory service without self-managing storage
• your agent does not support MCP or HTTP integration

Facets

cli-tool · maturity active

mcp search-engine database cli developer-tools developer-tools large-language-models databases windows cli cross-platform persistent-memory ai-coding-agents sqlite fts5 mcp-server tui agent-agnostic single-binary ai-agents macos linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Gentleman-Programming/engram")