• Product
  • Latest
Sign InGet started free
HomeProductLatest
DocsCareersAboutThe Hamster Method
Sign InGet Started

Same-day shipping for your product team

© 2026 Wheel Go Fast, Inc. All Rights Reserved.

GitHubEmail support
Product
  • Briefs
  • Plans
  • Blueprints
  • Agents
  • Connections
  • CLI
  • Taskmaster
Latest
  • Thoughts
  • Changes
Resources
  • Docs
  • Careers
  • About
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
Studio/Agent Context

Your agent already knows what to build.

Your agent doesn't just get a task description. It gets the brief, the reasoning, the team's decisions, and the acceptance criteria — synced into your repo as markdown files in real time.

zsh — hamster
> "Let's build the auth feature"
Reading .hamster/briefs/auth.md ...
Reading .hamster/briefs/auth/tasks/HAM-102.md ...
I can see 3 acceptance criteria and a method
for error handling. Starting with session management.
tryhamster.com
Brief/Plan/Context

Auth Feature

Ready5 tasks
HAM-101Audit current auth flow3/3
Colin Thornton
HAM-102Design session management1/3
Claude Code
HAM-103Wireframe token refresh flow0/2
Azikara
HAM-104Design team invitation screen0/4
Codex
HAM-105Implement role-based access0/3
Gemini

Compatibility and optionality

One Hamster, any CLI, IDE, or model.

Claude CodeCodexGeminiCursorCopilotWindsurfClineRoo CodeAiderAmpGrok
Taskmaster

When your briefs, plans, and tasks live inside a vendor's tool, switching costs are brutal. A better model drops and you're stuck — or you start over.

Hamster is the central repository of work, not the model. Briefs and plans stay in one place. The agent is interchangeable. Use Claude for deep reasoning, Gemini for speed, an open-weight model for sensitive code — or a different model for every task on the board.

New frontier model ships on Tuesday? Point it at your .hamster/ directory and keep going.

MCP

Agents write back too.

The Hamster MCP server gives your agent 20 tools to mark tasks done, create subtasks, and update status — directly from the coding session. When the agent finishes a task, it updates the plan. No one has to do it manually.

zsh — hamster mcp
> hamster mark-done HAM-102
✓ Task HAM-102 marked done in Hamster Studio
✓ Plan progress: 9/12 tasks complete
20 tools available — tasks, briefs, blueprints, skills, methods

Install

One command to install.

Install the Hamster CLI, initialize your repo, and start working. Your agent has full project context from the first prompt.

curl -sSL https://tryhamster.com/cli/install | bash
01

Install the CLI

Run the install command and authenticate with your Hamster workspace. Under a minute.

02

Initialize your repo

Run `hamster init`. Creates a .hamster/ directory and starts syncing your project context.

03

Work normally

Open your coding agent. The context files are already there. Ask it to build something — it knows what that means.

Key capabilities

The full brief, not just a title

The difference between "implement auth" and a brief with the strategy, constraints, compliance requirements, and team decisions. Your agent gets the latter.

20 MCP tools built in

Mark tasks done, create subtasks, update status — all from the coding session.

Works offline

Context files are local. Your agent reads them even without a network connection.

Any MCP-compatible agent

One server, every tool. Claude Code, Cursor, Gemini CLI, Codex, and more.

Skill file generation

The CLI generates structured project maps so your agent understands the full codebase.

No new workflow

You don't pull context in. It's just there. Work the way you already work.

Wire your agent into the plan.

Free to start. No credit card required.

Get started free