LLM Bus

by danieldoderlein

354 downloads

Not rated

GitHub

About

Atomic gap-free id claims, advisory file leases, a shared event ledger + digest, presence, prose handoffs, and a task graph - so multiple agents (Claude Code, Cursor, Codex) stop colliding and re-deriving each other's work. Native Streamable HTTP, one claude mcp add. Open source

Details

Author: danieldoderlein
Downloads: 354
Categories: Developer Tools, AI, Automation, Project Management, Communication

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name LLM Bus

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

From the repository

Add LLM Bus to Claude Code with claude mcp add. It uses native Streamable HTTP and can be self‑hosted or accessed at llm‑bus.com.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "llm bus": {
            "llm-bus": {
                "type": "http",
                "url": "https://mcp.llm-bus.com/mcp",
                "headers": {
                    "Authorization": "Bearer <YOUR_TOKEN>"
                }
            }
        }
    }
}

McpServers

{
    "llm-bus": {
        "type": "http",
        "url": "https://mcp.llm-bus.com/mcp",
        "headers": {
            "Authorization": "Bearer <YOUR_TOKEN>"
        }
    }
}

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 overMCPthat 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 underAGPL-3.0. Self-host it, or use the managed service atllm-bus.com.

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-freeclaimmeans 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, whileclaimwas only 7.3%. 90.3% of handoffs were acknowledged, and 88% were anchored to a concrete artifact.

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 athttp://127.0.0.1:8787/mcpwithAuthorization: Bearer <token>. For a real deployment (TLS, the admin auth boundary, the kit) seeSELFHOSTING.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.

Query is exact-match only. Responses are small and stable by design (context cost).

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 addressedhandle/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 qualifiedhandle/labelis what shows in handoffs, presence,whoami, and the ledger; exact-match filters (query_events,list_tasks) take the qualified form.

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.

Client-side onboarding that makesclaimun-skippable without ever blocking work: afail-openreconcile 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.

TypeScript / Node >= 22 (ESM/NodeNext), the official@modelcontextprotocol/sdkover 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 008for the open-core boundary.

Contributions welcome - see CONTRIBUTING.md. We develop LLM BusonLLM Bus: contributors get a participation on the public dev project, so you use the bus while you help build it.

- 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).

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Official MCP server for Buildable AI-powered development platform. Enables AI assistants to manage tasks, track progress, get project context, and collaborate with humans on software projects.

Coordination layer for AI agents across isolated developer local environments (devices)

Project management inside every AI coding tool — plans what's next, tracks every decision, stops drift.

An MCP server for AI-to-AI collaboration, enabling autonomous workflows and role-based task management between different AI models.

Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client, with persistent identity, real-time messaging with @mentions and threads, task handoffs, shared workspace context, semantic search, and replayable MCP App widgets.

What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.

CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.

Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.

Objective-native planning board for agent-led development

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

LLM Bus

About

Details

Jump to

Setting up with Highlight

Setting up with Cursor

JSON

JSON

JSON

Setting up with Claude Desktop

JSON

JSON

JSON

Setting up with Windsurf

JSON

JSON

JSON

Setting up with Cline

JSON

JSON

JSON

Setting up with Goose

JSON

JSON

JSON

From the repository

Claude Desktop / Cursor

McpServers

License, self-hosting, and the hosted service

Install

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

License, self-hosting, and the hosted service

Install

More like this

@mendableai/firecrawl Mcp Server

Umut Naci

Playwright

Sentry

Github

Fetch