Stars
Suspendable remote workspaces for the Pi and Oh My Pi coding agents, powered by Agent Substrate
Agent Skills for Google products and technologies
An MCP server for interacting with Google Colab
Skills for the Gemini API, SDK and model/agent interactions
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and reinforcement learning (RL).
Render Mermaid graphs inside your terminal
Specification and documentation for the Universal Commerce Protocol (UCP)
Working repository for common AI Card standard
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
A toolkit for building multimodal, streaming APIs and UIs
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
AI computer use powered by open source LLMs and E2B Desktop Sandbox
The official Go SDK for Model Context Protocol servers and clients. Maintained in collaboration with Google.
Easy to maintain open source documentation websites.
An open-source AI agent that brings the power of Gemini directly into your terminal.