llm-bus MCP server
Commit 3 Sep 2026Mengoordinasikan beberapa AI agent melalui shared event ledger, atomic task claims, dan advisory file leases untuk mencegah tabrakan kerja dan mengelola handoff.
Juga dikenal sebagai danieldoderlein/llm-bus
- Stars
- 9
- Tools
- —
- Unduhan, 30 hari
- —
- Versi terbaru
- 1.0.0
- Commit terakhir
- 3 Sep 2026
- Lisensi
- AGPL-3.0
Apa itu llm-bus MCP?
llm-bus adalah MCP server. Mengoordinasikan beberapa AI agent melalui shared event ledger, atomic task claims, dan advisory file leases untuk mencegah tabrakan kerja dan mengelola handoff.
Ringkasan dibuat dari README proyek
Tentang llm-bus MCP server
LLM Bus bertindak sebagai layer koordinasi untuk beberapa AI agent dan operator manusia guna mencegah tabrakan kerja dan mengelola handoff. Sistem ini berfungsi sebagai shared backplane di atas Model Context Protocol, menyediakan live event ledger yang dapat dibaca dan ditulis oleh semua partisipan. Sistem ini memungkinkan agent untuk berbagi pengetahuan secara horizontal alih-alih harus mencari ulang informasi yang sama, sehingga menghemat token dan waktu. Anda dapat melakukan self-host server ini menggunakan Node.js dan PostgreSQL atau menggunakan layanan terkelola.
Developer berinteraksi dengan server melalui MCP tools spesifik yang dikategorikan ke dalam grup seperti Orientation, Handoffs, Tasks, dan Leases. Sistem ini menggunakan atomic gap-free claims untuk memastikan dua agent tidak pernah mengambil task ID yang sama, serta advisory file leases untuk mencegah agent saling menimpa editan satu sama lain. Akses dikelola melalui bearer tokens yang memiliki scope per proyek dan dapat diatribusikan ke partisipan tertentu. Setup ini memungkinkan workflow agent secara paralel di berbagai worktrees atau branch tanpa memerlukan penyalinan konteks secara manual oleh manusia.
Apa yang bisa Anda lakukan dengannya
- 1Mencegah tabrakan editan paralelSeorang agent dapat meminta advisory lease pada sebuah file untuk memastikan tidak ada agent lain yang memodifikasinya secara bersamaan.
- 2Mengelola handoff tugasSeorang developer dapat menginstruksikan agent untuk mengirimkan handoff ke lane atau actor tertentu sebagai sinyal bahwa pekerjaan sudah siap untuk partisipan berikutnya.
- 3Sinkronisasi pengetahuan agentSeorang agent dapat melakukan query ke shared event ledger untuk menemukan informasi yang sebelumnya telah ditemukan oleh rekan timnya.
- 4Alokasi ID pekerjaan yang unikSeorang agent dapat menggunakan tool claim untuk mengambil identifier unik untuk sebuah task tanpa risiko adanya duplikasi assignment.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal llm-bus MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal llm-bus MCP di Claude Code
$ claude mcp add --transport http llm-bus https://mcp.llm-bus.com/mcpInstal llm-bus MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"llm-bus": {
"url": "https://mcp.llm-bus.com/mcp"
}
}
}Instal llm-bus MCP di VS Code
.vscode/mcp.json
{
"servers": {
"llm-bus": {
"type": "http",
"url": "https://mcp.llm-bus.com/mcp"
}
}
}Instal llm-bus MCP di VS Code CLI
$ code --add-mcp '{"name":"llm-bus","type":"http","url":"https://mcp.llm-bus.com/mcp"}'Instal llm-bus MCP di Codex
$ codex mcp add llm-bus --url https://mcp.llm-bus.com/mcpInstal llm-bus MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.llm-bus] url = "https://mcp.llm-bus.com/mcp"
Instal llm-bus MCP di Gemini CLI
$ gemini mcp add -s user --transport http llm-bus https://mcp.llm-bus.com/mcpInstal llm-bus MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"llm-bus": {
"url": "https://mcp.llm-bus.com/mcp",
"type": "http"
}
}
}Konfigurasi
DATABASE_URL
| Nama | Deskripsi | Tipe |
|---|---|---|
| DATABASE_URL | — |
Pengecekan otomatis
Berjalan 14 Nov 2026Laporan lengkap →Belum diverifikasi. Sebuah server memerlukan skor 80, tidak ada temuan serius, dan data yang cukup untuk kami periksa. Cara kerja checks · Yang perlu diperbaiki untuk menambah poin
- Source repository terhubung dan dapat dijangkaudanieldoderlein/llm-bus is public and reachablegithub.com/danieldoderlein/llm-bus ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernyaTidak diperiksa
- Provenance build (atestasi Sigstore)Tidak diperiksa
- Lisensi open source (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-09-03github.com/danieldoderlein/llm-bus ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerTidak diperiksa
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPHTTPS endpoint answered 401 (sign-in required)Lolos
README
Lihat di GitHubLLM Bus
Stop being the bridge between your agents. The live coordination layer for AI agents and the humans driving them - so you stop being the bridge. When two people each drive agents, or one person runs ten Claude Code sessions across branches and worktrees, the human becomes the manual relay: copying context between sessions, re-explaining what one agent already figured out, hoping a handoff landed. LLM Bus is the shared backplane over MCP that does the relaying: an attributable handoff channel and a shared event ledger every agent reads and writes, plus atomic gap-free work-claiming and advisory file leases so parallel agents never collide. It is not git and does not need git - it is a thin live layer over whatever the work surface already is (git, a Drive, email, nothing).
Open source under AGPL-3.0. Self-host it, or use the managed service at llm-bus.com.
Why
LLM Bus is the coordination layer that lets a team of agents work like a well-run team of people: handoffs that get acknowledged, a shared record everyone reads, claims and leases so nobody steps on anyone. The deep-dive is docs/coordination-layer.md. The problems it solves:
- Knowledge flows sideways instead of being re-derived. Knowledge trapped in one agent's context window is knowledge teammates re-derive and tokens you burn twice. The shared ledger is a record every agent reads and writes, so a sibling pulls what someone already figured out instead of rebuilding it.
- Handoffs land, and you can tell. Handoffs get dropped and you cannot tell if work shipped. Here they are attributable and acknowledged, anchored to a concrete artifact (a PR, ADR, commit, or migration) so the record points at real work.
- Run agents in parallel without collisions. Atomic gap-free
claimmeans two agents never grab the same id; advisory leases on real files mean they never clobber each other's edits. Proven under a 500-concurrent test. - The standup/ticket/shared-doc layer without the meetings. Coordinating otherwise means you act as the router or silent mistakes ship. The bus is the live relay: in our own runs an agent caught a peer's merge before it reached production.
What a real run looks like (our own dogfooding, not customer proof): in 8 days of our own
multi-agent runs - 9 agents, 4 projects, 591 events - 77.5% of all activity was handoffs and
acknowledgments, while claim was only 7.3%. 90.3% of handoffs were acknowledged, and 88% were
anchored to a concrete artifact.
Quickstart (self-host)
Requires Node >= 22 and PostgreSQL 16.
git clone https://github.com/danieldoderlein/llm-bus && cd llm-bus
npm ci
createdb llm_bus
export DATABASE_URL="postgres://$(whoami)@127.0.0.1:5432/llm_bus"
npm run migrate
npm run bootstrap-owner -- you@example.com # the operator owner (for /admin)
npm run seed-token -- you@example.com my-project my-agent --admin # mint a token
npm run dev # http://127.0.0.1:8787
Point an MCP client at http://127.0.0.1:8787/mcp with Authorization: Bearer <token>. For a real
deployment (TLS, the admin auth boundary, the kit) see SELFHOSTING.md -
read it before exposing /admin (there is one security-critical step).
Or skip all of that and use the hosted service: llm-bus.com.
MCP tools
| Group | Tools |
|---|---|
| Orientation | whoami, guide (the live coordination protocol), whats_new (session digest + cursor), list_projects |
| Handoffs | post (to lane/actor, with ref/tag/links), read_posts - reading a post addressed to you MARKS IT READ; there is no separate ack |
| Tasks | task_create/assign/start/stop/block/resolve/ship/answer/edit/cancel/reopen, task_depend/task_undepend, list_tasks |
| Allocation | claim (collision-free id, bare + qualified), seed_sequence, latest_claims, list_sequences |
| Leases | lease (advisory, reports contention), release, who_holds |
| Presence | register (lane), who_is_active - liveness is implicit (any call refreshes it) |
| Knowledge | query_events (exact filters) |
| Identity / admin | list_participants, admin_provision, admin_rotate, admin_revoke, create_invite |
A decision or signoff is a TASK WITH OPTIONS assigned to whoever decides - there is no separate review
inbox. ack, review and answer_review are retired; they remain only as tombstones that answer a
cached client once with a redirect to the replacement.
There is also a push channel, deliberately NOT a tool: GET /api/wait (bearer-authed) holds a request
open until the calling participation has work, so an idle agent does not poll. A tool call happens
inside a model turn and would block it; this is meant to be held by a separate process.
Query is exact-match only. Responses are small and stable by design (context cost).
The model
Owner - a human with a globally-unique handle (the public identity); signs in via OAuth or SSO
- Projects - coordination spaces (sequences/events/posts/leases/tasks/presence live here)
- Participants - identities the owner creates (agent OR human): the unique entity "on the ledger"
- Participation - a participant granted into a project; carries a TOKEN
A bearer token resolves to (participation -> project + participant + owner). MCP tools never accept
a project or identity as input - both come from the token, so every act is attributable and every
read/write is project-scoped. One token per participant, shared across its sub-agents (they collapse
to one identity). Projects and owners are fully isolated.
Identity. Every owner has a globally-unique handle (the public identity; email stays private). A
participant is addressed handle/label (e.g. alice/claude-1) - the bare handle is the human as a
first-class actor - so the bus actor is unambiguous across owners. The qualified handle/label is
what shows in handoffs, presence, whoami, and the ledger; exact-match filters (query_events,
list_tasks) take the qualified form.
The web admin and invites
A server-rendered web admin (/admin, owner-scoped) manages projects, participants, tokens
(mint/rotate/revoke), and invites. Onboarding is "one MCP endpoint + a token": hand out a grant
card, or a one-use expiring invite the invited party's agent redeems to self-connect.
The adherence kit (kit/)
Client-side onboarding that makes claim un-skippable without ever blocking work: a fail-open
reconcile hook (a number claimed by another identity blocks with the correct next number; service
down -> warn and proceed), paste-ready CLAUDE.md blocks, and a one-command installer.
Stack
TypeScript / Node >= 22 (ESM/NodeNext), the official @modelcontextprotocol/sdk over Streamable
HTTP, PostgreSQL, zod, pg. No web framework (hand-rolled HTTP + server-rendered admin). Bearer
tokens are sha-256-hashed at rest, revocable, project-scoped.
npm run verify # tsc + 15 integration tests against real Postgres (500-concurrency, full MCP
# round-trip, isolation, fail-open hook, admin, OAuth, invites)
License, self-hosting, and the hosted service
LLM Bus is AGPL-3.0. The entire coordination engine is open and self-hostable. The commercial offering is the managed service - frictionless OAuth onboarding plus a cross-org invite network, so the people you collaborate with are one click away - not a feature you have to pay to unlock. AGPL keeps a competitor from cloning the code into a closed rival. See decision 008 for the open-core boundary.
Copyright (C) 2026 DRD AS - owner and operating entity of the hosted service. Created by Daniel R. Döderlein (doderlein.com) - inventor and creator. See NOTICE.
Contributing
Contributions welcome - see CONTRIBUTING.md. We develop LLM Bus on LLM Bus: contributors get a participation on the public dev project, so you use the bus while you help build it.
Docs
- docs/coordination-layer.md - the coordination layer for agent teams (the deep dive).
- SELFHOSTING.md - run your own instance (deployment + the admin security boundary).
- USING.md - operate it: create projects, add participants, hand out invites.
- SECURITY.md - the security model and how to report a vulnerability.
- docs/architecture.md - the technical structure.
- docs/decisions/ - the decision log (why the system is the way it is).
Pertanyaan tentang llm-bus MCP
Bagaimana cara menambahkan llm-bus MCP ke Claude Code?
Jalankan claude mcp add --transport http llm-bus https://mcp.llm-bus.com/mcp di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan llm-bus MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Bagaimana cara mencegah dua agent mengedit file yang sama secara bersamaan?
Server menyediakan advisory leases pada file asli untuk memastikan agent yang berjalan secara paralel tidak saling menimpa editan satu sama lain.
Apa persyaratan teknis untuk self-hosting?
Untuk melakukan self-host, Anda memerlukan Node versi 22 atau lebih tinggi dan PostgreSQL 16.
Apakah ada cara agar agent tidak terus-menerus melakukan polling untuk pekerjaan baru?
Ya, tersedia push channel melalui GET /api/wait yang akan menahan request tetap terbuka sampai pekerjaan tersedia, sehingga mencegah agent yang idle melakukan polling.