# Gentleman-Programming/engram

Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.

Repository: https://github.com/Gentleman-Programming/engram
Canonical: https://ross.abutalabs.com/products/engram
Language: Go
License: MIT
License Family: permissive
Last push: 2026-08-26T10:52:32+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 81, longevity 14
- inputs: {"age_days": 198, "days_push": 7, "days_rel": 44, "gap_med": 0.0, "n_releases_24m": 97}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6184, forks 655 (observed 2026-08-28T04:09:37.997459+00:00)

## What it is
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
- artifact type: cli-tool
- maturity: active
- function: mcp, search-engine, database, cli, developer-tools
- domain: developer-tools, large-language-models, databases
- platform: windows, cli, cross-platform
- tags: persistent-memory, ai-coding-agents, sqlite, fts5, mcp-server, tui, agent-agnostic, single-binary, ai-agents, macos, linux

## Member repositories
- Gentleman-Programming/engram (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:37.997459+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:47:23.612927+00:00, confidence not recorded.
  - readme: https://github.com/Gentleman-Programming/engram (fetched 2026-08-28T04:09:37.997459+00:00, sha b82a8e2e6f56)
- Data as of 2026-08-30T08:39:29.467469+00:00.