Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
★ 117,321⑂ 10,191👁 362⑃ 3,402● 2,487▤ 407
+278
日增长
+2,208
周增长
+17,286
月增长
117,321
stars
10,191
forks
362
watchers
3,402
prs
2,487
issues
407
releases
README
🇨🇳 中文 •
🇹🇼 繁體中文 •
🇯🇵 日本語 •
🇵🇹 Português •
🇧🇷 Português •
🇰🇷 한국어 •
🇪🇸 Español •
🇩🇪 Deutsch •
🇫🇷 Français •
🇮🇱 עברית •
🇸🇦 العربية •
🇷🇺 Русский •
🇵🇱 Polski •
🇨🇿 Čeština •
🇳🇱 Nederlands •
🇹🇷 Türkçe •
🇺🇦 Українська •
🇻🇳 Tiếng Việt •
🇵🇭 Tagalog •
🇮🇩 Indonesia •
🇹🇭 ไทย •
🇮🇳 हिन्दी •
🇧🇩 বাংলা •
🇵🇰 اردو •
🇷🇴 Română •
🇸🇪 Svenska •
🇮🇹 Italiano •
🇬🇷 Ελληνικά •
🇭🇺 Magyar •
🇫🇮 Suomi •
🇩🇰 Dansk •
🇳🇴 Norsk
Your coding agent forgets everything between sessions. Claude-Mem remembers for it.
Quick Start •
How It Works •
Search Tools •
Documentation •
Configuration •
Troubleshooting •
License
Every new session, your agent starts from zero. It re-reads the same files, re-asks the same questions, and walks back into mistakes you already fixed together.
Claude-Mem runs a second agent beside it that takes notes while it works. The next session starts with a short index of what matters, and pulls in the details only when it needs them. Works with Claude Code, Codex, Cursor, OpenCode and 11 more agents. Copilot CLI, Goose, Roo Code, Warp and Zed can search your memory, but their sessions aren't recorded.
---
Quick Start
Installing for someone as an AI agent? If the user is available, run npx claude-mem install --setup browser on their computer and keep it running. It prepares the local runtime, then opens setup in their browser; if the page doesn't open, give them the printed URL. Every choice (agents, integrations, skills, model, usage analytics, the optional email) is made by the user on that page, so there are no terminal questions to relay. If the user is away, run npx claude-mem install --setup defer: it prepares the runtime and leaves setup waiting for their first visit, and their next session shows them the link. Don't make their choices for them.
bash
npx claude-mem install
The installer finds the agents on your machine and asks which ones to set up. Then just start working: observations stream in from your first prompt, and your second session in a project opens with memory from the first. (Copilot CLI, Goose, Roo Code, Warp and Zed get memory search only, so their sessions don't add to it.)
The installer sets everything up first, then asks you to sign in to claude-mem in your browser (email magic link, no card required to sign in). Choosing the claude-mem observer then starts its 30 Day Free Trial on a checkout page that asks for a payment method; once it completes, the installer saves your memory key. With the observer, memory runs off-plan, so you get up to 100% more usage from your plan. When the free trial ends, memory automatically falls back to your Anthropic plan unless you subscribe. After sign-in you pick your meTop issues
#3606[plan-18] Observer Response Pipeline — classify every output, never confirm a batch on failure, bound every history46 comments · 2026-08-16#3607[plan-19] Observer Subprocess Isolation — an explicit env, cwd, config, tool set and auth source for the headless generator, with loud degradation25 comments · 2026-08-16#3603[plan-15] Worker Port & Liveness Authority — one verified answer to "is a worker serving this port?"24 comments · 2026-08-16#3609[plan-21] SQLite Schema Evolution & Queue State Integrity — one DDL path guarded by introspection, immutable session keys, and queue/session states that can actually transition23 comments · 2026-08-16#3610[plan-22] Chroma Sidecar Contract — host-safe spawn with pinned deps and a clean env, single-writer upsert sync, honest fallback (or retire the sidecar)18 comments · 2026-08-16#3602[plan-14] Child Process Ownership — every process the worker spawns dies with the worker18 comments · 2026-08-16#3605[plan-17] Hook Wrapper Contract — thin, cheap, and fail-open on every host17 comments · 2026-08-16#2785[plan-12] Provider & Extensibility Roadmap — net-new capabilities, not defects17 comments · 2026-06-05
Discussions
#6173Add title0 comments · 2026-11-14#6103A month of sponsored agent usage for claude-mem contributors0 comments · 2026-11-13#6086Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-12#6078Turkish video about claude-mem (with English subtitles)0 comments · 2026-11-12#6044Compression trade-offs and honesty grading: do confidence labels survive summarization?1 comments · 2026-11-11#5671装上这个之后,我的额度消耗得非常快0 comments · 2026-11-10#54891230 comments · 2026-11-08#5338https://github.com/thedotmack/claude-mem/issues/new/choose0 comments · 2026-11-03
Latest release
v15.18.5 v15.18.5 2026-11-15Critical fixes - The tree-sitter CLI installs on networks where its download script keeps failing (6110, thanks @rigel905, closes 6109). On some networks tree-sitter-cli's own install.js had its request reset every time, or exited 0 on a truncated file. The pinned SHA-256 check correctly refused the file, but nothing recovered after that, so smart_search, smart_outline, smart_unfold and the File Read Gate stayed off on every worker start, and npx claude-mem repair aborted. Now, when the script fails or leaves anything but the pinned executable, claude-mem fetches the same release asset direct
相关报道 (12)
51CTO七牛云行业应用2026-10-30bilibili这周 GitHub 上涨星最猛的 10 个 AI 开源项目2026-10-17xGithubトレンド on X: "10/5 20:22 JST|GitHub Trendingから claude-mem をピックアップ。中身はスレッドへ。"2026-10-05techritualGitHub 每月飆升榜:開發者追蹤熱門開源項目新捷徑2026-07-26blog.csdn【GitHub】Claude-Mem 深度解析:为 Claude Code 装上“永久记忆脑“2026-05-07腾讯网斩获30.5k Star!Claude Code长期记忆插件Claude-Mem开源,实现跨会话上下文无缝保留2026-02-24新浪财经开源插件引爆大模型暗战:Claude‑mem爆红背后,是 AI 大厂最不想公开的赚钱秘密2026-10-28腾讯新闻本周最猛的10个 AI 开源项目2026-10-18CSDN博客0赏金、沟通遭拒!他怒曝6个Windows漏洞后被GitHub封号:“微软毁了我的人生”,7月14日将公开一切2026-05-2851CTOClaude Code进阶指南:装这九个Skill 才算真正上手 原创2026-03-25
News & coverage (11)
Hacker NewsInstalling claude-mem uploads your last 30 days of prompts to cmem.ai, no opt-in▲ 3 · 0 comments · 2026-10-29Hacker NewsClaude-Mem▲ 2 · 1 comments · 2026-03-28note[GitHub Daily Report] claude-mem takes the top spot with +1,723, impeccable ranks for the 12th consecutive day — 2026-11-012026-10-31note[GitHub 일일 보고] claude-mem이 +1,723으로 1위 교체, impeccable은 12일 연속 순위 진입 — 2026-11-012026-10-31noteDesign Differences Between agentmemory and claude-mem for Fixing Coding AI Amnesia2026-06-30ad-hoc-newsClaude-Mem löst das Amnesie-Problem von KI-Codierassistenten2026-02-03Augment Codeclaude-mem v13.8.0: Persistent Agent Memory Across Sessions2026-06-23Augment Codeclaude-mem hits 74.8K stars with agent memory persistence2026-05-11Augment Codeclaude-mem hits 65.8K stars as a persistent memory plugin for Claude Code2026-04-23Augment Codeclaude-mem hits 46.1K stars as persistent memory plugin for Claude Code2026-04-07