MemoryAtlas

Engram

Gentleman Programming

Agent-agnostic persistent memory for AI coding agents: a single, dependency-free Go binary backed by SQLite + FTS5 full-text search, exposed via an MCP (stdio) server, an HTTP API, a CLI, and an interactive TUI. Works with any MCP client (Claude Code, Codex, Gemini CLI, Cursor, Windsurf, VS Code Copilot, OpenCode, and more).

Storage
A single local SQLite database (~/.engram/engram.db) with FTS5 full-text indexing — one binary, one file, no Node/Python/Docker dependencies. Designed so memory survives agent context compaction across sessions.
Retrieval
FTS5 full-text search exposed as MCP tools (and via HTTP/CLI/TUI); the agent writes and recalls memories over stdio. An 'Engram Cloud' hosted tier offers a shared brain alongside the local mode.
Self-host
Self-host: trivial
License
MIT
Pricing
Open-source (MIT) single binary, free to self-host (brew install); an 'Engram Cloud' managed/shared tier is available (pricing not captured). · Free + paid
GitHub stars
4,712
Last release
2026-06-20
Last commit
2026-06-20
First catalogued
2026-06-28

Strengths

  • Zero-dependency single Go binary over one SQLite file — trivial to self-host
  • Agent-agnostic via MCP: works across Claude Code, Codex, Gemini CLI, Cursor, Windsurf, VS Code, OpenCode and others
  • Explicit focus on surviving context compaction; CLI/HTTP/TUI surfaces in addition to MCP

Watch out

  • 'Engram Cloud' hosted-tier pricing not captured — priceTier and pricing need reviewer confirmation
  • MCP transport is stdio-only (no network MCP endpoint) and the HTTP API binds to loopback only — relevant for Dockerized/remote agents
  • Retrieval is full-text (FTS5) rather than semantic/embedding — note for comparability against vector-based systems

Best for

  • Coding agents needing a lightweight, local, agent-agnostic persistent memory that survives session and compaction boundaries

Benchmark results

No sourced results yet.

Sources

Last verified 2026-06-28 · updated by discover-frameworks