Commons
io.github.Neoo-Blue由 GitHub 帳號 Neoo-Blue 發布v0.37.1更新於 Nov 7, 2026
Shared memory, work claims and handoffs so parallel AI coding sessions stop colliding.
發布方自己的服務：Memory.fit
概覽
Commons 為 AI 助理提供共享的本機記憶與工作認領中心，讓並行的編碼工作階段共享決策、避免重複或互相覆蓋工作。
- 可以做什麼
- 記憶、搜尋與回想：混合檢索、鄰近對話輪次與日期解析
- 認領、完成與交接任務，讓並行工作階段避開已被佔用的工作
- 維護專案看板，記錄請求、目標與證據，以及等待你回答的問題
- 向其他代理傳訊息、喚醒它們，並把大任務拆成子任務
- 可選擇以自架中心執行，附儀表板、基礎設施地圖與憑證保險庫
- 適用情境
- 當你同時執行多個 AI 編碼工作階段（例如每個 git worktree 一個），希望它們共享決策、不重複或覆蓋彼此工作時使用。也適合想讓不同 AI 用戶端共用一個自架記憶與協作中心的團隊。
- 執行需求
- 以本機 stdio 程序執行；README 說明需要 uv，外掛透過 Claude Code 外掛市集安裝。預設設定把所有內容存在一個本機 SQLite 檔案中，不需帳號或 API 金鑰。可選的自架中心需要 Docker 或 Python 安裝、Postgres 密碼、儀表板權杖和保險庫金鑰，以及用於模型功能的供應商金鑰。環境變數包括 COMMONS_AGENT 和 COMMONS_TOOLS。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Commons，將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Commons
Run several Claude Code sessions at once without them redoing or overwriting each other's work.
Each session (say, one per git worktree) checks in with Commons before it starts a task. If another session already has it, it hears so and backs off. Finished work, decisions and handoffs are shared, so the next session builds on them instead of starting over. Everything lives in one local SQLite file: no API keys, no account, no telemetry.
Needs uv. Each folder is one agent (claude-code@<folder>), so run parallel sessions in
separate worktrees or checkouts with different folder names.
Two sessions, two worktrees, same task:
It works alongside claude-mem and Claude Code's own memory: those help one session remember, Commons keeps several
sessions from colliding. The plugin lists 19 tools (memory and coordination only). Credential and vault tools are not listed
and nothing asks for a key; they stay reachable through call() only if you set up a vault yourself. How it stays safe: docs/threat-model.md.
Beyond one machine: the hub
The same Commons runs as a small self-hosted hub, so sessions on different machines, and other AIs (Codex, Cursor, Gemini CLI, ChatGPT, Grok), share one view of who is doing what.
Commons is a self-hosted memory and coordination hub that every AI connects to over MCP. It works with Claude, ChatGPT, Grok, Cursor, Codex, Gemini and your own agents. They share memory, pick up each other's unfinished work, message and wake each other, learn how you like things done, and split big jobs into reviewed, debated, budgeted subtasks. One SQLite file (or Postgres) holds it all. A dashboard shows who is doing what and what it costs.
Docker: see docs/docker.md. Prefer to read it first? curl -fsSLO https://raw.githubusercontent.com/Neoo-Blue/commons-memory/main/install.sh && less install.sh && sh install.sh. No-script alternatives: uvx --from git+https://github.com/Neoo-Blue/commons-memory commons init (run without installing) · uv tool install "commons-memory[http] @ git+https://github.com/Neoo-Blue/commons-memory" · pipx install "commons-memory[http] @ git+https://github.com/Neoo-Blue/commons-memory"
Contents
Quickstart · Feature tour · Architecture · Connect any AI · Screenshots · Multi-agent · Security · Networking · Configuration · Troubleshooting · FAQ · Comparison · Roadmap · Changelog
Onboarding (self-hosted hub)
-
Copy
.env.exampleto.env, create the three secret files it lists (dashboard token, Postgres password, vault key), thendocker compose up -d(docker-compose.yml; the comments explain every option). -
Open the dashboard and go to Setup. A checklist shows what is missing:
- provider keys: TypeSafe (Jev), Anthropic, OpenAI, Google, xAI, OpenRouter, or a local Ollama;
- the decision agent's fallback order;
- your service credentials;
- features, all on by default.
Keys are stored encrypted in the vault and never shown again.
-
Add an AI on the Connect page: one terminal line connects every AI on a machine, one sentence connects a bot, one address connects a chat app. No key is copied anywhere, and every AI it connects can be woken the moment work arrives.
-
Each agent hands over its memories, keys and scheduled tasks; Setup shows who still owes what.
2-minute quickstart
Connect a second AI the same way and it can see the first one's memory immediately. Each client lists only the 32 core tools (6.1k tokens, against 40.4k for all 186); tools(query) finds the other 154 and call(tool, args) runs them. For other AIs (ChatGPT, Grok, Muse…), paste the universal prompt.
Feature tour
What each feature buys you
Measured where we have numbers (details in benchmarks/README.md); "not benchmarked" means the effect is real but not yet measured. Rival columns come from each project's own README and docs (checked 2026-10-13): ✓ has it, ◐ partial, · doesn't, — not compared.
¹ mem0's hosted platform reports LoCoMo 92.5 / LongMemEval 94.4 with its own scorer; that isn't comparable to runs scored here with one reader and judge for every system.
Architecture
Connect any AI
Add an AI on the dashboard's Connect page. It makes a join link (15 minutes, up to 5 AIs) and gives you three ways to use it:
- On a computer:
curl -fsSL http://HUB:8770/join/<code> | sh. It installs the commons client, finds every AI CLI on that machine (Claude Code, Codex, Gemini CLI, Cursor, OpenCode and more), gives each its own key, and runs the full setup below for each one. Running it again skips what is already connected. - A bot or another AI: send it "Join my Commons: read http://HUB:8770/join/
/agent and follow it." It joins on its own and names the command that wakes it; Commons runs that through a service that keeps a connection open to the hub, so it is woken behind NAT or a firewall with no port opened. - A chat app (claude.ai, ChatGPT, Grok): add a custom connector with
http://HUB:8770/mcpand sign in.
Every AI Commons connects can be woken. An agent that can't (it only checks in on its own) shows "Commons can't wake
it" in its drawer, with one sentence to send it that installs its wake service and keeps its key.
Prefer to do it by hand? On the machine where the AI runs:
It asks for the agent's key once (hidden, saved 0600), then does every step, each on by default:
- connects the AI to Commons over MCP;
- installs the master instructions it always loads (
CLAUDE.md plus a commons skill, AGENTS.md, GEMINI.md,
or a Cursor rule);
- installs auto-capture hooks;
- installs instant wake;
- hands over the AI's existing memories;
- verifies the connection.
Add --no-<step> to leave one out. The dashboard's Connect page builds this command with a checkbox per step.
Clients: claude-code, codex, gemini, cursor, opencode, copilot, cline, kilo, amp, factory, qwen, crush, goose, windsurf, zed, roo, warp.
Hosted chat apps (claude.ai, ChatGPT, Grok, Muse) can't run commands: paste PROMPT.md into their
custom instructions. It is generated from the same master instructions, so it never goes stale, and Commons hands
every agent the same playbook on its first check-in and whenever it changes.
Screenshots
Captured from a demo hub (python scripts/demo_seed.py demo.db): made-up agents, jobs and memories.
Multi-agent in 5 commands
Interactive AIs claim the same subtasks with pickup → claim_subtask → complete_subtask. Offline agents are woken through their channels, and stuck work escalates.
Security model
- Identity. HTTP requires an agent key or OAuth 2.1 token on every request (
401 otherwise). Only key hashes are stored. Each principal is rate-limited (429, COMMONS_RATE_PER_MIN).
- Access control. Per-project ACLs (
commons acl grant PROJECT AGENT --role read|write|admin). The sole author of a project can make it private. Trust scores weight search and the KB.
- No raw secrets in memory. Every write passes a gitleaks-style and entropy redactor. Secrets are stored as references (
env://, vault://, vault-dyn://, op://, infisical://) and used through short, agent-bound leases. commons secret-exec injects the value into a child process and masks it in that process's output.
- Tools. The MCP hub applies allow/deny/approve policies per agent and tool. Destructive calls need a human approval that is bound to the exact arguments. Upstream output is fenced as untrusted, and so is anything a stranger can write on a watched GitHub repo (issue and PR text, branch names, commit messages): it never reaches a job title, and issues and PRs from people outside the repo make no job unless you turn on
github_outside.
- Owner proof. The tokenless LAN dashboard can't tell you from an agent on the same network, so anything that could approve an agent's own request or reach a key (approvals, providers, settings, the vault, MCP policy, trust, routing, new agent keys) needs your owner password once one is set. You choose it on your first visit: for 30 minutes after Commons starts, the dashboard offers "Make this hub yours" to whoever opens it, from any browser, with no code (a restart reopens the window until a password exists; every claim notifies you;
COMMONS_CLAIM_MINUTES=0 means setup-code only). Each browser then stays signed in for 14 days. Want the whole dashboard behind it? Switch on dashboard_lock on Setup. Model providers, role models and resuming after the kill switch need an admin over MCP too.
- Review gates. Skills and gated subtasks need a different agent (or you) to approve. Kill switch, daily cost cap and per-job budgets.
- Network. Bind to loopback or a private network (below). The dashboard is tokenless only on private addresses; public binds require a token. Per-user dashboard tokens (
commons dashboard-user add) are optional: COMMONS_DASHBOARD_TOKENS=0 turns them off on a hub that sits behind its own sign-in, such as Cloudflare Access. Outbound webhooks are https-only and SSRF-checked (COMMONS_WEBHOOK_ALLOWLIST). Audit log for secrets, ACLs, approvals and escalations.
- Encryption at rest: SQLCipher (
COMMONS_DB_KEY) or disk encryption. Known gaps are tracked honestly in FLAWS_AND_GAPS.md.
Networking
- One machine: stdio MCP. Nothing listens on the network.
- Several machines (recommended): your tailnet / VPN.
commons serve --transport http --host <tailscale-ip> --port 8770 --dashboard. The dashboard follows --host. On localhost, LAN (RFC 1918) and tailnet (100.64.0.0/10) addresses it needs no token. Binding it to a public address requires COMMONS_DASHBOARD_TOKEN. Set COMMONS_DASHBOARD_REQUIRE_TOKEN=1 to demand a token everywhere.
- Don't bind
0.0.0.0 unless the host has no public interface. Use --host <private-ip>, TLS (--tls-self-signed or --tls-cert/--tls-key) and keep keys required.
- From anywhere:
commons expose up tailscale|cloudflare|ngrok|ssh|…. It refuses public exposure unless keys are enforced. Run it as a service with commons expose service systemd|launchd|windows. Details: docs/networking.md.
- Docker:
docker compose up -d, or the one-liner below (finalized in docs/docker.md):
Configuration
Everything works with defaults. These are the settings people usually change:
All 89 variables are in docs/configuration.md. It's generated from the code by scripts/gen_env_reference.py, and a test fails if a setting is undocumented.
Troubleshooting
FAQ
- Do I need a server? No. A single machine uses stdio and one SQLite file. Run
serve --transport http only when AIs on other machines need to connect.
- Which AIs work? Anything that speaks MCP (stdio or streamable HTTP). Others can use the HTTP
/bus/* and /agent/* endpoints or a CLI worker.
- Will it leak my secrets to models? Writes are redacted, secrets are only references, and values only reach child processes through
secret-exec.
- What does it cost? Commons itself makes no LLM calls unless you configure a planner, summarizer or providers. Usage reported by agents shows up on the dashboard.
- Can I move from SQLite to Postgres? Yes:
commons migrate-postgres postgresql://….
- Can I stop it? Yes. Run
commons pause (kill switch). commons dump exports everything as JSONL.
Benchmarks (v0.9.0; QA on v0.28, tool sizes on v0.30)
Measured on an 8-core Apple M1 laptop that was busy with other jobs, CPU only. Full tables, caveats and per-question
results are in benchmarks/README.md; every number is reproducible with commons bench.
Head-to-head, rivals run here on the same LoCoMo data (details in benchmarks/README.md):
Published numbers elsewhere use other readers, judges and subsets (mem0's paper: 66.9% with gpt-4o-mini; its
managed platform and Zep claim 92-95% under their own setups), so only the table above is apples to apples.
Comparison
Roadmap
- First PyPI release (the publishing workflow is in place;
uvx commons-memory / pipx install commons-memory work once it lands).
- Hosted dashboard auth via OIDC.
History: CHANGELOG.md.
Development
MIT licensed.
來源：README.md，提交 62d1ecb
工具
0版本歷史
7- v0.37.1最新Nov 7, 2026
- v0.36.1Oct 18, 2026
- v0.36.0Oct 18, 2026
- v0.34.1Oct 17, 2026
- v0.34.0Oct 17, 2026
- v0.33.1Oct 16, 2026
- v0.33.0Oct 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手；SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭，或保持端點能夠回應探測，以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分
其他 Memory 整合
Memory.fit
fit.memory官方發布者
託管式 Memory.fit 伺服器，讓 AI 讀取你的訓練、睡眠、恢復與飲食資料，並寫回每週計畫、每日目標和飲食計畫。
pg.ddx.io: the PostgreSQL community's memory
io.ddx.pg官方發布者
pg.ddx.io: the PostgreSQL community's memory 的託管 MCP 服務，由 pg.ddx.io 發布；無需登入；Streamable HTTP；29 個工具。
var.gg Naming Memory
gg.var官方發布者
遠端 MCP 伺服器，可依領域概念推薦並檢索韓、日、中、越、英多語言的程式識別字名稱，並提供 ERD 結構查詢。
Counterparts
ai.counterparts
為 Claude Code 與 Claude Desktop 提供的本地優先長期記憶：助理自行寫下關於你與專案的筆記，並在之後的對話中回想起來。
LAHZE - Persian AI Memory Platform
由 GitHub 帳號 pedramgholizadeh 發布
以波斯語為先的地理記憶平臺：發現地點，起草併發布僅限波斯語的記憶。AI 翻譯