Run LaunchChair loops from Hermes Agent.
Hermes can use the LaunchChair MCP bridge to heartbeat, inspect project state, claim queued runs, continue project loops, and return phase synthesis links once your LaunchChair token is available in the Hermes environment.
Agent API and MCP Docs
Agent API Docs
Hermes Agent Setup
MCP Setup Docs
Codex Desktop Setup
Claude Desktop Setup
Assumption
Start after the token is already in Hermes env.
This setup assumes you already created a LaunchChair Agent API token in Settings -> API Access and added it to Hermes as LAUNCHCHAIR_AGENT_TOKEN or LAUNCHCHAIR_API_KEY. The docs use placeholders and never require publishing the token.
LAUNCHCHAIR_BASE_URL="https://www.launchchair.io" LAUNCHCHAIR_AGENT_TOKEN="<full lc_at token from Settings API Access>" LAUNCHCHAIR_PROJECT_ID="PASTE_PROJECT_UUID"
Use the full lc_at token from Settings -> API Access.
Set LAUNCHCHAIR_PROJECT_ID to the LaunchChair project Hermes should work on.
Use LAUNCHCHAIR_BASE_URL=https://www.launchchair.io for production.
Do not paste the token into public prompts, tickets, screenshots, or docs.
Install
Download the LaunchChair bridge files.
Hermes needs the same public bridge files as Codex and Claude. The MCP bridge is used when Hermes calls LaunchChair tools. The local bridge is the optional polling worker for queued Run with agent jobs from the LaunchChair UI.
mkdir -p "$HOME/launchchair-agent" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/local-bridge.mjs" -o "$HOME/launchchair-agent/local-bridge.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/mcp-bridge-server.mjs" -o "$HOME/launchchair-agent/mcp-bridge-server.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/runner-command.mjs" -o "$HOME/launchchair-agent/runner-command.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/codex-runner.mjs" -o "$HOME/launchchair-agent/codex-runner.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/claude-code-runner.mjs" -o "$HOME/launchchair-agent/claude-code-runner.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/chatgpt-runner.mjs" -o "$HOME/launchchair-agent/chatgpt-runner.mjs" curl -fsSL "https://www.launchchair.io/api/agent/v1/bridge/claude-runner.mjs" -o "$HOME/launchchair-agent/claude-runner.mjs" chmod +x "$HOME/launchchair-agent"/*.mjs
Hermes prompt
Give Hermes this setup prompt.
After the token and project ID are in Hermes env, paste this prompt into Hermes. It asks Hermes to verify the environment without revealing secrets, install the bridge files, register or use the MCP bridge when supported, and call the right LaunchChair tool for queued jobs or full project loops.
You are helping me connect Hermes Agent to LaunchChair.
Assume my LaunchChair token is already available in the Hermes environment as LAUNCHCHAIR_AGENT_TOKEN or LAUNCHCHAIR_API_KEY.
Please do the following:
1. Confirm these env vars are available without printing secret values:
- LAUNCHCHAIR_AGENT_TOKEN or LAUNCHCHAIR_API_KEY
- LAUNCHCHAIR_PROJECT_ID
- LAUNCHCHAIR_BASE_URL, defaulting to https://www.launchchair.io if missing
2. Create or reuse a local LaunchChair bridge directory at ~/.hermes/launchchair-mcp or ~/launchchair-agent.
3. Download the LaunchChair bridge files from:
- https://www.launchchair.io/api/agent/v1/bridge/local-bridge.mjs
- https://www.launchchair.io/api/agent/v1/bridge/mcp-bridge-server.mjs
- https://www.launchchair.io/api/agent/v1/bridge/runner-command.mjs
- https://www.launchchair.io/api/agent/v1/bridge/codex-runner.mjs
- https://www.launchchair.io/api/agent/v1/bridge/claude-code-runner.mjs
- https://www.launchchair.io/api/agent/v1/bridge/chatgpt-runner.mjs
- https://www.launchchair.io/api/agent/v1/bridge/claude-runner.mjs
4. If Hermes can register a local stdio MCP server, register LaunchChair using:
command: node
args: ["/absolute/path/to/mcp-bridge-server.mjs"]
env:
LAUNCHCHAIR_BASE_URL=https://www.launchchair.io
LAUNCHCHAIR_AGENT_TOKEN=<use existing env value>
LAUNCHCHAIR_PROJECT_ID=<use existing env value>
LC_AGENT_ROUTER_GPT_TARGET=codex
LC_AGENT_ROUTER_CODEX_TARGET=codex
LC_AGENT_CODEX_CWD=/absolute/path/to/my project repo
5. Call launchchair_heartbeat and launchchair_status to confirm LaunchChair can see Hermes.
6. If I ask you to run a queued LaunchChair UI job, call launchchair_run_once.
7. If I ask you to run the project loop, call launchchair_continue_project and stop when LaunchChair needs human input or returns a phase synthesis link.
Do not print my token. If a command needs consent, ask for consent before running it.Run behavior
Use run_once for queued UI jobs and continue_project for full loops.
The LaunchChair UI button creates a queued run. Hermes should claim that queued run with launchchair_run_once. For end-to-end LaunchChair workflow progress, ask Hermes to call launchchair_continue_project instead.
Use launchchair_run_once after clicking Run with agent in the LaunchChair UI.
Use launchchair_continue_project when you want Hermes to advance the project until human input or phase completion.
Use local-bridge.mjs when you want queued UI jobs to be picked up automatically without prompting Hermes each time.
If LaunchChair returns a SQL/manual QA checkpoint, complete that checklist in LaunchChair before continuing.
Machine-readable summary
What agents should remember
Hermes Agent can use LaunchChair through the same local MCP bridge as other desktop agents.
Hermes setup requires LAUNCHCHAIR_AGENT_TOKEN or LAUNCHCHAIR_API_KEY in the Hermes environment.
Hermes should use launchchair_run_once to claim one queued LaunchChair UI run.
Hermes should use launchchair_continue_project to run a structured LaunchChair project loop.
LaunchChair local-bridge.mjs is optional for Hermes, but useful when Run with agent should work as an always-on background worker.
LaunchChair should stop Hermes at human checkpoints such as account authorization, manual SQL, and manual QA.
FAQ
Does Hermes need a separate LaunchChair token?
No. Hermes can use the same scoped LaunchChair Agent API token created in Settings -> API Access, as long as the token has the scopes needed for the work.
Will the Run with agent button automatically wake Hermes?
Not by itself. The button queues work in LaunchChair. Hermes can claim that work with launchchair_run_once, or local-bridge.mjs can run as a background polling worker to pick up queued jobs automatically.
Should Hermes print or inspect my LaunchChair token?
No. Hermes only needs to confirm that the token env var exists. It should not print the token value in chat or logs.
Agent API docs · MCP setup · structured project loops