akitaonrails/ai-memory
Long-term memory and handoff tool for AI coding agents
- Chart
- Not on a chart right now
- Stars
- 16.1k
What it is
A Rust-based tool that connects more than twenty AI coding agents, including Claude Code, Codex, and Cursor, to a single shared memory. It captures session activity into a git-backed markdown wiki so work can resume across agents, machines, and teammates.
Who it is for
Developers and teams who switch between AI coding CLIs or machines and want to preserve project context.
Why it is trending
It gained 6,577 stars today and recently released v3.4.7. Unlike hosted or LLM-dependent memory tools, it runs as a single binary with zero LLM calls by default.
Main features
- Shared memory and typed claim-once handoffs across 20+ coding agents
- Git-backed plain markdown wiki with full-text, entity, and graph search
- Silent lifecycle hook capture with zero LLM API calls by default
- Built-in multi-user authentication and audit logging for teams
Summarized on November 17, 2026 from the README and repository data. It can be wrong; check the source before relying on it. Report a wrong summary