Documentation
Everything you need to run ThinkingMach.
Guides, references, and walkthroughs for the people running AI agents at work. Start at the quickstart, or jump anywhere below.
Learn
Quickstart
Learn what ThinkingMach is, install it, create your first company, hire an agent, and watch it work.
Working Day-to-day
Day-to-day operation: dashboard, tasks, approvals, budgets, and the activity log.
Your Org & Agents
Shape the org chart, set up delegation paths, and pick adapters for your agents.
Projects & Workflow
Projects, goals, routines, and execution workspaces.
Power Features
Execution policies, export/import, and terminal setup for power users.
Experimental
Opt-in features that ship behind flags — what each one does, why it exists, and how to turn it on.
How-to Guides
Field-tested recipes for specific problems — short, copy-pasteable, current.
Administration
Company settings, instance configuration, plugins, and CLI auth — for operators and admins.
Reference
API
Every endpoint on the control plane: companies, agents, issues, approvals, costs.
CLI
Complete command-line reference: local setup, identity, and every control-plane command family.
Skills
Skill file shape, install pipeline, scoping, versioning, and troubleshooting.
Adapters
Connect any agent runtime — Claude, Codex, Gemini, or your own HTTP service.
Plugins
Plugin SDK reference for authors building ThinkingMach plugins.
Deployment
Run ThinkingMach on your laptop, in Docker, or on a server — with secrets and Tailscale.
Changelog
What changed in these docs — pages added, rewritten, or expanded — with each documentation update.