Tinker
Tinker is a training API for researchers and developers that provides fine-grained control over model training and fine-tuning while abstracting away infrastructure complexities.
Control every aspect of model training and fine-tuning
- Fine-tuning language models for specific tasks
- Reinforcement learning research and experimentation
- Rapid prototyping of training algorithms
- Custom model training without infrastructure management
- Sign up for a Tinker account and obtain API credentials
- Choose a supported model from the available list
- Use the forward_backward function to perform forward and backward passes
- Apply optim_step to update model weights
- Use sample to generate tokens for evaluation or interaction
- Save state with save_state to resume training later
The easiest way to deploy a managed agent.
Find & fix live vulnerabilities in Vibe Apps with 1-prompt.
A terminal, a real browser, and Claude Code under one roof
Annotate anything for humans and their agents
Archify reveals the components, APIs, and behavior behind any web page directly in your browser. It operates 100% locally, with no data leaving your device, and requires no account.
AI platform for deep video understanding
See it once. Ask forever.
Tamamon is a free macOS desktop pet that grows as you code with Claude Code. It reads your Claude usage to evolve the pet, but never accesses your code or data. The pet appears on your desktop, reacts to your activity, and can be fed and played with.
Your time travel debugger
The Web Data API for AI Agents and Developers
AI-powered schematic design tool for PCB making
Instant, hardware Isolated Sandboxes for AI agents
Keep any Mac window visible in a floating mini screen
The web performance & security company
Caps Lock keeps your Mac awake, even with the lid closed
Platform for building with Google's Gemini AI models.
Comment on your AI agent's code & collaborate on changes
Screen recordings that edit themselves
