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. 'Engram Cloud' is an optional, self-hosted sync + dashboard layer (Docker/GHCR image you run yourself) for project-scoped replication across machines — local SQLite stays authoritative, not a vendor-hosted SaaS.
- Self-host
- Self-host: trivial
- License
- MIT
- Pricing
- Fully open-source (MIT), free to self-host end to end: the core binary (brew install) and the optional 'Engram Cloud' sync/dashboard layer (self-hosted via Docker Compose or the ghcr.io/gentleman-programming/engram image) are both free — there is no vendor-hosted managed tier or paid plan. · Free / OSS
- GitHub stars
- 5,947
- Last release
- 2026-07-20
- Last commit
- 2026-07-30
- 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; `engram setup gemini-cli` is a distinct one-liner from `engram setup antigravity-cli` (different config paths — `~/.gemini/settings.json` vs `~/.gemini/config/mcp_config.json` — both still documented as of 2026-07-15)
- Explicit focus on surviving context compaction; CLI/HTTP/TUI surfaces in addition to MCP
- No embedding model inference at query time — FTS5 is pure SQLite I/O, making retrieval latency predictable with no ML inference overhead
Watch out
- 'Engram Cloud' is a self-hosted sync/dashboard extra you run yourself (Docker Compose or ghcr.io image) — not a vendor-managed SaaS with its own pricing; there is no paid tier at all as of 2026-07-23
- 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
- Not a Python (or Node) package despite sharing a catalog family with pip-installable libraries: distribution is a single Go binary via Homebrew or `go install`, and the README states outright 'No Node.js, no Python, no Docker.' There is no PyPI wheel to `pip install`; a separate npm package (`gentle-engram`, latest pi-v0.1.9 released 2026-06-30) is a native memory provider for the unrelated 'Pi' agent tool, not a Python or general embedding SDK.
Best for
- Coding agents needing a lightweight, local, agent-agnostic persistent memory that survives session and compaction boundaries
How it integrates
Benchmark results
No sourced results yet.
Sources
- Monthly card re-verification — GitHub API repo metadata: 5,786 stars, license MIT confirmed, archived=false, last commit on the default branch 2026-07-30 (third-party)
- Engram README (vendor)
- GitHub API repo metadata (stars, MIT license, release) (third-party)
- GitHub API — stars 4738, latest v1.17.0 (2026-06-20); README confirms FTS5 only, no embedding model at query time (third-party)
- Engram INSTALLATION.md — brew install gentleman-programming/tap/engram; go install path; no npm/PyPI (vendor)
- Engram AGENT-SETUP.md — MCP stdio config (command: engram, args: [mcp]) for Claude Code, Cursor, Windsurf, VS Code, Gemini CLI, and others (vendor)
- GitHub API re-check — 4775 stars, pushed 2026-06-30; core binary's latest tag remains v1.17.0 (2026-06-20) (third-party)
- GitHub API re-check — 5464 stars, pushed 2026-07-08; latest tag v1.19.0 (2026-07-08), up from v1.17.0 (third-party)
- engram AGENT-SETUP.md — dedicated Gemini CLI section: `engram setup gemini-cli` registers mcpServers.engram in ~/.gemini/settings.json, writes ~/.gemini/system.md with the Memory Protocol, and sets GEMINI_SYSTEM_MD=1; a separate Antigravity CLI section (`engram setup antigravity-cli`) targets the distinct ~/.gemini/config/mcp_config.json path — confirms both agents remain independently supported post the 2026-06-18 Gemini CLI free-tier sunset (vendor)
- GitHub release pi-v0.1.9 (2026-06-30) — 'Declares gentle-engram as the Pi-native memory provider'; a separate npm package for the 'Pi' agent tool, not a Python distribution of Engram itself (vendor)
- Engram README — 'No Node.js, no Python, no Docker. One binary, one SQLite file.' Confirms there is no PyPI package for Engram. (vendor)
- GitHub API re-check — 5656 stars, MIT license confirmed, not archived, pushed 2026-07-20 (third-party)
- Engram Cloud docs — 'Self-hosted cloud runtime: engram cloud serve on infrastructure you control'; public image at ghcr.io/gentleman-programming/engram (linux/amd64, linux/arm64); explicitly 'Not cloud-only' and 'Not a replacement for local SQLite'. Confirms Engram Cloud is a self-hosted extra, not a vendor-managed paid SaaS — corrects prior priceTier of free-paid to free (vendor)
Last verified 2026-08-01 · updated by refresh-framework-cards