Back to directory

engram

A persistent memory system for AI coding agents, packaged as a single agent-agnostic Go binary with a SQLite full-text search store behind it.

Visit website (opens in a new tab)engram.gentlemanprogramming.com
engram

Engram gives an AI coding agent memory that survives past the end of a session, storing it in SQLite with FTS5 full-text search and exposing it through a CLI, an HTTP API, an MCP server, and an interactive TUI. Any MCP-compatible agent can use it, including Claude Code, OpenCode, Gemini CLI, Codex, VS Code with Copilot, Antigravity, and Cursor, with no Node.js, Python, or Docker required.

Its documented operating contract asks an agent to search before repeating a decision, save completed fixes and durable constraints deliberately rather than raw transcripts, keep an evolving topic under one stable key, and leave a session summary with goals, discoveries, and next steps before ending.

Engram is written in Go and distributed under the MIT license.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.