Astra planner and JEV controller for Minecraft, with native recording, tested routes, and run verification.

Browser extension tools that work with your agent harness primitives such as annotation

Chrome DevTools for coding agents

autonomous systems engineering cli agent for any cloud environment: AWS, GCP, Cloudflare, etc

AI-powered tool that helps you debug, analyze, and understand your applications using Pydantic Logfire.

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

Unified MCP server for querying OpenTelemetry traces across multiple backends (Jaeger, Tempo, Traceloop, etc.), enabling AI agents to analyze distributed traces for automated debugging and observab…

Agentic kubectl

The LLM Evaluation Framework

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.

Eval Protocol (EP) is an open solution for doing reinforcement learning fine-tuning on existing agents — across any language, container, or framework.

Open-source observability for your GenAI or LLM application, based on OpenTelemetry

SoTA open-source TTS

Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

Generative UI SDK for React

AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.

Model Context Protocol Servers

Get the main content of any page as Markdown.

GitHub's official MCP Server

Late Interaction Models Training & Retrieval

⚙️ Create and run workflows (RPA 2.0)

The Sphinx documentation generator

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

A guidance language for controlling large language models.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.