#146 · Primary category： AI Coding Assistants
engram
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
Project last updated：08/29/26
GitHub Stars
6.2K
Forks
659
Contributors
28
License
MIT
Why we included this project
When an AI coding agent ends a session, it usually starts the next one with no memory of what was decided or fixed in the last hour of work. Engram closes that gap by giving coding agents a durable, searchable memory that survives restarts. It ships as a single Go binary backed by SQLite with full-text search, so setup is light and there are no external services to run. Because it speaks the Model Context Protocol, the same memory store can be attached to Claude Code, Codex, Cursor, Windsurf, or whatever agent you happen to be using at the moment. For developers who juggle several tools, that means context travels with the project rather than staying locked inside one vendor's session.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.