Engram

Engram is a persistent memory system for AI coding agents that stores context in a local SQLite database.

Engram provides a persistent, searchable memory layer for AI coding agents so they do not lose context when sessions end. It runs as a single Go binary using SQLite and FTS5 for built-in full-text search without external processes. The tool is agent-agnostic and works with any MCP-compatible agent including Claude Code, Gemini CLI, Codex, VS Code, Cursor, and Windsurf. Features include fifteen MCP tools, an interactive terminal UI with vim keys, and Git sync for sharing memories across machines. It is designed for developers who want to avoid repeating context and re-explaining codebases across sessions.

Engram at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux, API, VS Code, CLI, self-hosted, open source
Pricing: Free
Released: February 2026
Category: AI coding tool
Website: engram.gentlemanprogramming.com

Key features

Agent-agnostic memory for MCP-compatible tools
SQLite and FTS5 full-text search
Single Go binary with zero dependencies
Interactive terminal UI with vim keys
Fifteen built-in MCP tools
Git sync using compressed chunks

Use it for

Retaining bugfixes and architecture decisions across sessions
Sharing agent memories across multiple machines
Browsing agent activity and stats with a web dashboard

Alternatives to Engram

AI Memory — Shared memory for coding agents that works across machines and team members.
claude-mem — It shares persistent, searchable agent memory across sessions and devices.
memsearch — It shares continuous context across Claude Code, Codex, and other AI coding agents.
Memorax Code — Carry project architecture and verified engineering decisions across coding sessions.
Tigerless Agent Memory — Maintains agent history in portable, greppable Markdown files without API keys.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
Chemical X — Stops wasting agent context on CLI noise and compiler dumps.
Agent Beacon — Retains coding agent knowledge across tools so errors do not repeat.
Turnbook — Saves every chat turn locally with zero model tokens and shares memory across AI apps.
Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
Supermemory — Integrates long-term memory into AI coding agents with a single prompt.
memU — It gives every connected agent a shared and inspectable memory layer.

All Engram alternatives