signalGitHub Trending2026-09-23
akitaonrails/ai-memory
ai-memory is an open-source solution that provides shared long-term memory for AI coding agents, working across 20+ harnesses including Claude Code, Codex, and Cursor. It stores memory as plain Markdown in a git-backed wiki, runs on a self-hosted server with multi-user auth and audit logs, and captures work via lifecycle hooks with a default path using zero LLM calls. It enables seamless handoffs between different agents and machines, with a measured write ceiling of ~700/s.
- for who
- Developers and teams using AI coding agents who need persistent shared context across tools and machines.
- why now
- Cross-agent memory tool debuts
- what changes
- Agent handoffs become seamless without repeating context, reducing setup overhead and improving continuity in multi-agent workflows.
- to do
- Deploy ai-memory on a self-hosted server and integrate its lifecycle hooks into your coding agent harnesses to enable shared memory.
key points
- Works with 20+ harnesses: Claude Code, Codex, Cursor
- Stores memory as Markdown in git-backed wiki with auth
- Measured write ceiling of ~700/s, default path zero LLM calls
#ai coding agent#long-term memory#open source project#multi-agent collaboration
score
score 8 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source