remem
Active·★ 34·MIT·Updated 2026-10-21
`remem` is a local-first memory solution for AI coding agents like Claude Code and OpenAI Codex, preventing repetitive explanations by automatically capturing and injecting project context. It distills, searches, and stores project decisions, bug fixes, and preferences locally using SQLite, accessible via CLI, hooks, and a REST API.
#AI Agent Memory#Context Management#Coding Assistant#Retrieval Augmented Generation (RAG)#Local-first#SQLite Database#Rust Language
01
Features
01Automatic memory capture and injection for coding agents.
02Searchable history of project decisions, bug fixes, and rationale.
03Local-first memory storage with SQLite and SQLCipher encryption.
04Accessible via CLI, coding agent hooks, MCP tools, and REST API.
05Single Rust binary with no external database dependencies.
02
Compatibility
Rust
Built With
Verified via docs
Claude Code
Integration
Verified via docs
OpenAI Codex
Integration
Verified via docs
macOS
Platform
Verified via docs
Linux
Platform
Verified via docs
Homebrew
Package Manager
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/majiayu000/remem/main/install.sh | env REMEM_NO_CONFIG=1 sh
2
$ ~/.local/bin/remem install --target codex
04
Use cases
↳Avoiding repetitive project explanations to AI coding agents.
↳Searching and recalling past project decisions and bug-fix rationale.
↳Maintaining an auditable and project-scoped history of engineering memory.
↳Reducing the need for manual upkeep of large memory documentation files.
05
Alternatives
deja-vu★ 1.3k
Your agents already solved this. deja finds it — retroactive search and MCP recall over the session logs your coding agents already wrote. Cross-agent, SSH-portable, one zero-dep binary, fully local.
projectmem★ 868
Local-first AI coding memory for AI agents. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
Waggle-mcp★ 44
MCP server for external memory layer for AI agents + more . Download from pypi , and get started
MemWhale★ 153
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.
MCP-memento★ 11
Local-first MCP server that gives AI agents durable repo memory and fast semantic code context.
squish-memory★ 12
Local-first memory runtime for AI agents. One command to connect Claude Code, Codex, ChatGPT, MCP workflows, and local agents.
Comments
Log in to leave a comment
No comments yet. Be the first!