engram
Persistent memory system for AI coding agents — agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, and CLI.
The Lens
Engram gives it persistent memory. It's a Go binary with SQLite and full-text search that any AI agent can read and write to, so context survives across sessions.
It works via MCP server, HTTP API, or CLI, meaning it's agent-agnostic. Claude Code, Codex, OpenClaw, or anything else that speaks HTTP can use it. Your agent writes memories during a session and reads them back next time. Full-text search (FTS5) means it retrieves relevant context, not just raw dumps. MIT licensed, Go.
The catch: persistent memory is only useful if the agent writes good memories. Garbage in, garbage out. If the agent stores irrelevant context, it pollutes future sessions. SQLite is great for single-user but won't scale to a team sharing one memory store. And the MCP protocol is still young; not every agent supports it natively.
Free vs Self-Hosted vs Paid
fully freeFully open source under MIT. No paid tier, no hosted version. You run the Go binary on your machine. SQLite means zero infrastructure, no database server needed. Completely self-contained.
Free. Zero infrastructure cost: it's a single binary with embedded SQLite.
Similar Tools
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
Claude Code skills that turn any codebase into an interactive knowledge graph you can explore, search, and ask questions about (Multi-platform e.g., Codex are supported).
About
- Stars
- 2,274
- Forks
- 240
Explore Further
More tools in the directory
Get tools like this delivered weekly
The Open Source Drop — the best new open source tools, analyzed. Free.