akitaonrails /ai-memory
Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors
★ 15,948⑂ 1,189👁 69⑃ 1,546● 755▤ 155
+87
Daily
+934
Weekly
+6,789
Monthly
15,948
stars
1,189
forks
69
watchers
1,546
prs
755
issues
155
releases
README
Long-term memory for AI coding agents. Quit Claude Code mid-task, start OpenAI Codex in the same directory, continue without re-explaining the architecture, the failed approaches, or the open questions. Website: aimemory.sh Why ai-memory Your coding agent probably has a memory feature already. Claude Code takes its own notes, Cursor remembers some things, and every platform is adding more. They all have the same limits: the notes live on one machine, belong to one agent, and drop out of view when you switch tools or hand the work to a teammate. ai-memory removes those limits. - It follows you across agents. More than twenty harnesses (Claude Code, Codex, Cursor, Gemini CLI, OpenCode, Grok, Devin, Kimi, Kiro, and others) feed one shared memory. Quit Claude Code mid-task, open Codex in the same directory, and the next agent picks up a handoff that says where you left off, what failed, and what is still open. Handoffs are a typed protocol: each one has an owner and is claimed exactly once. - It can carry the session, not just a summary. Start agents with ai-memory run: quit Claude Code, run ai-memory run codex, and Codex gets the shared workstream plus a private, temporary local projection of Claude's visible native history for exact details the bounded startup packet omitted. The remote server receives only the harness and session identity, never the local transcript path or body. Direct harness launches behave exactly as before. - It follows you across projects. A small profile of how you usually work (your package manager, test layout, architecture habits) reaches every new repository at session start, so you stop re-explaining yourself. It sits below each repository's rules file as a default. It is on by default for a single user, and on a shared server it is opt-in and private per person. See docs/cross-project-profile.md. - It follows you across machines. Memory lives in a server you run, on the same laptop, a homelab box, or anywhere else, so the project you left on the desktop is the project you resume on the laptop, with the same knowledge and the same open questions. - It works for a team. Point everyone at one server, and what one person's sessions learn, everyone's agents can retrieve. Knowledge is shared per project; personal handoffs stay personal. Multi-user auth, per-person attribution, and an audit log are built in and are not a paid tier. - Your memory is plain markdown. The source of truth is a git-backed wiki of ordinary .md files: grep it, open it in Obsidian, edit it by hand, rsync it. The database is a derived index that can always be rebuilt from the files. There is no vector store to maintain and no content locked in a binary blob. - It captures the work itself, silently. Lifecycle hooks record what happened (prompts, tool calls, session boundaries), sanitize it at a typed privacy boundary before anything is stored, and the server consolidates it i
Top issues
#1843RFC: surface what memory holds about a file when the agent opens it (opt-in)6 comments · 2026-10-29#2164Memory poisoning: track whether a compiled page came from a tool result5 comments · 2026-11-10#1429Standing rules: owner, review date and change acknowledgement5 comments · 2026-10-18#1854Investigate 3.3 local-embedding LongMemEval top-ten movement4 comments · 2026-10-29#1281Agent-to-operator decision requests on top of cross-project messaging: in scope?4 comments · 2026-10-14#1515Boundary question: optional `ai-memory-thesaurus` companion that tells the agent where the repository's docs cover each topic (follow-up to #700)3 comments · 2026-10-21#1471Lint: flag bulk review bumps and implicit supersession3 comments · 2026-10-19#1261Tamper-evident audit log (prev-hash chain)?3 comments · 2026-10-13
Latest release
v3.4.6 v3.4.6 2026-11-13Checksums (SHA256) cf76306e823d373c7c0c3ae5332a98ecfc91c43c89a893945071fb6311497a5f ai-memory-3.4.6-1.aarch64.rpm ed5a55bebc1b564c19462ad5b888bb1c4715f6d4bece386670c11401f2746ea1 ai-memory-3.4.6-1.x86_64.rpm a59f6325a4fc5e5a3bccc8f2bf8c20f73ce0065196b7b3493241a5a9b63da031 ai-memory-claude-plugin.zip 8fd17ec7152da065c894432a26e611e26ce02e2ce98355ddd87b8edd2694c3e4 ai-memory-hooks.tar.gz 5b8b9030c247b091ac2bacbf181f52f8fdba9d4ed47cdef23faab874d4c94d9f ai-memory-install-hooks 635d537b2ea0118f30c54f0bff813ce187d6664993766d69965447fe1d3253af ai-memory-linux-aarch64.tar.gz cde3c286bd81854a6b7
相关报道 (6)
QQ News本周 GitHub 涨得最猛的十个 AI 开源项目, GitHub 被 AI agent 占领了2026-10-25智源社区AI越用越聪明,自主+自进化是关键拼图丨盛大邓亚峰EverMind@AIGC20262026-05-2851CTO迎接智能体的「觉醒时刻」:EverOS全球公测开启Agent Memory自进化序章2026-04-15电子工程专辑EE Times China太抽象了,Alice 都来了。2026-04-08麻省理工科技评论AI“失忆症”有救了?终于有研究者把AI记忆这事说明白了2026-03-17新浪财经本周 AI 项目推荐|Mem0, Memories.ai......AI 记忆大爆炸2025-11-09
News & coverage (8)
noteI Made GitHub the Brain of an AI Reviewer2026-11-06HackerNoonHow I Built a Shared AI Memory System Using Markdown and GitHub2026-11-02cybernewsMilla Jovovich creates MemPalace AI memory tool with “perfect score” on benchmark, but devs aren’t buying it2026-04-08The 420.inRam-Altman: Linux Script Responds to OpenAI CEO’s Comments on Memory Usage2026-11-10InfoWorldFour agentic AI memory systems for smarter LLMs2026-07-08SDxCentralMilla Jovovich's AI memory project has a few things it would rather forget2026-04-14MediumMemPalace: Milla Jovovich’s AI Memory System — What the Benchmarks Actually Mean2026-04-11ForbesMilla Jovovich Goes Open Source Guns Blazing With Top AI Memory Code2026-04-09