@launchchair/agent

LaunchChair Agent

LaunchChair Agent packages the LaunchChair CLI, MCP bridge, local bridge, and runner scripts used by Codex, Claude Code, ChatGPT, Claude, and Hermes workflows.

Use it when you want an agent to create or discover LaunchChair projects, run product phases, continue project loops, pick up Run with agent jobs from LaunchChair, or expose LaunchChair tools through MCP.

Install Locally For Testing

From this package directory:

npm pack
npm install -g ./launchchair-agent-*.tgz
launchchair help
launchchair doctor

After publishing:

npm install -g @launchchair/agent
launchchair help
launchchair doctor

Login

Approve the CLI once in your browser. LaunchChair creates a scoped Agent API token after approval and the CLI stores it locally:

launchchair login
launchchair doctor
launchchair whoami

Manual fallback when you already have a token from LaunchChair Settings -> API Access:

launchchair login --token "<full lc_at token from LaunchChair Settings API Access>"

The CLI stores local config at:

~/.launchchair/config.json

Tokens are masked in CLI output. Do not paste real tokens into public docs, screenshots, issue comments, or chat summaries.

Guided Setup

Use setup as the easiest path. It saves the build folder, writes a small AGENTS.md pointer into that folder, starts browser login when no token is saved yet, writes the MCP config for your agent, and then proves the server can complete MCP initialize and tools/list before reporting success.

Codex Desktop:

launchchair setup codex --cwd /absolute/path/to/repo-or-empty-folder

If you prefer Codex Desktop's custom MCP form, copy paste-ready fields instead:

launchchair setup codex --cwd /absolute/path/to/repo-or-empty-folder --copy-config

Claude Desktop + Claude Code (Claude Code is registered at user scope when its CLI is installed):

launchchair setup claude --cwd /absolute/path/to/repo-or-empty-folder

Configure only one Claude client when needed:

launchchair setup claude-desktop --cwd /absolute/path/to/repo-or-empty-folder
launchchair setup claude-code --cwd /absolute/path/to/repo-or-empty-folder

Terminal / CLI agents:

launchchair setup terminal --cwd /absolute/path/to/repo-or-empty-folder

If you do not want browser login during setup, add --skip-login. You can also save an existing token during setup:

launchchair setup codex --cwd . --skip-login
launchchair setup codex --cwd . --token "<full lc_at token from LaunchChair Settings API Access>"

Setup writes client configuration by default. Use --copy-config, --ui-fields, or --print-config only when you intentionally want manual configuration. Authenticated setup exits nonzero if the MCP handshake or required tool discovery fails; --skip-mcp-check is an explicit diagnostic escape hatch, not the recommended first-run path.

For a fresh project before a repo exists, point --cwd at an empty folder. LaunchChair can run ideation, validation, positioning, pricing, and MVP blueprint before code exists; Stack Setup and Build MVP can later use that folder as the build target.

Use setup terminal when the agent runs inside a normal shell instead of Codex Desktop or Claude Desktop MCP. It writes the same project-local AGENTS.md pointer, saves the build folder, and prints the CLI commands the agent should use: launchchair projects, launchchair create, launchchair continue, launchchair run-once, and launchchair bridge.

Common Commands

launchchair setup codex --cwd /absolute/path/to/repo-or-empty-folder
launchchair setup claude --cwd /absolute/path/to/repo-or-empty-folder
launchchair setup claude-code --cwd /absolute/path/to/repo-or-empty-folder
launchchair setup terminal --cwd /absolute/path/to/repo-or-empty-folder
launchchair projects
launchchair projects --query LeafLore
launchchair scorecards --project-id <project-id>
launchchair scorecards --project-name LeafLore
launchchair create --name "SignalLift" --one-liner "Distribution workspace for technical founders" --project-type b2b --save-project
launchchair continue --stop-phase-key market_validation
launchchair continue --completion-target "rerun Product Ideation until ICP Pain Score is above 85"
launchchair run-once
launchchair bridge
launchchair mcp-config codex
launchchair mcp-config codex --ui-fields --copy-config
launchchair mcp-config claude
launchchair install-agent-md --cwd /absolute/path/to/repo-or-empty-folder

Feature projects can be created and planned from the CLI for every authenticated LaunchChair workspace:

launchchair create \
  --name "Retention Engine" \
  --project-kind feature \
  --feature-description "Add account-level lifecycle nudges to an existing SaaS dashboard" \
  --problem "Activated users forget the next valuable action after onboarding" \
  --product-description "Existing B2B SaaS dashboard with auth, billing, and workspace teams" \
  --plan-to-build-board \
  --save-project

# Optional: continue from feature planning into Build MVP
launchchair create \
  --name "Retention Engine" \
  --project-kind feature \
  --feature-description "Add account-level lifecycle nudges to an existing SaaS dashboard" \
  --problem "Activated users forget the next valuable action after onboarding" \
  --full-loop \
  --max-steps 12 \
  --build-max-steps 25

MCP Config

Print a Codex MCP config example:

launchchair mcp-config codex
launchchair mcp-config codex --ui-fields

Print a Claude Desktop MCP config example:

launchchair mcp-config claude

The recommended config launches the MCP server through the exact Node executable and CLI file path generated by launchchair setup or launchchair mcp-config. It also pins LAUNCHCHAIR_CONFIG_DIR to the exact directory used by launchchair login, so Codex and Claude users do not need to paste tokens into MCP config after browser login—even when the desktop app starts with a different home or shell environment. The server uses standard newline-delimited JSON-RPC over stdio, as required by MCP clients.

Use LAUNCHCHAIR_AGENT_TOKEN only as a manual fallback when you skip launchchair login, need a per-client token override, or your desktop app cannot read the saved CLI config. If you use a desktop custom MCP form, run launchchair mcp-config codex --ui-fields or launchchair mcp-config claude --ui-fields and paste the printed command, each argument, env vars, and working directory exactly as shown.

Local Bridge

Use the local bridge when the LaunchChair web app's Run with agent button should queue work and your local agent should pick it up:

launchchair bridge

For a one-shot test:

launchchair run-once

Runner Targets

Codex:

launchchair config set codex-cwd /absolute/path/to/repo-or-empty-folder
launchchair bridge

Claude Code:

launchchair config set claude-code-cwd /absolute/path/to/repo-or-empty-folder
LC_AGENT_ROUTER_GPT_TARGET=claude_code LC_AGENT_ROUTER_CODEX_TARGET=claude_code launchchair bridge

ChatGPT and Claude API runner fallbacks require provider API keys:

OPENAI_API_KEY=... launchchair bridge
ANTHROPIC_API_KEY=... launchchair bridge

Fresh Agent Chats

This package includes AGENTS.md. Fresh Codex, Claude, and Hermes chats should read that file before searching an empty repo. Product ideation, market validation, positioning, pricing, MVP blueprint, and project loops are LaunchChair API/MCP tasks. Local repo inspection starts later, usually at Stack Setup or Build MVP.

Docs

• CLI docs: https://www.launchchair.io/docs/cli
• MCP docs: https://www.launchchair.io/docs/mcp
• Agent API docs: https://www.launchchair.io/docs/agent-api
• Machine-readable catalog: https://www.launchchair.io/api/agent/v1/docs