The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…

Qwen-CUA: Native Computer Use for (Almost) Everything — a screenshot-driven agent that operates computers with keyboard and mouse, jointly developed by the Qwen Team and XLang Lab.

WebWorld is a large-scale web world model that helps train web agents in a simulated browser, avoiding the latency and safety issues of the real web.

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions [TMLR2025]

WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?

Fully automatic censorship removal for language models

Generate, format and mask agent traces with ease.

Open Frontier Intelligence

Implementation of Reinforcement Learning Algorithms (From Reinforcement Learning An Introduction By Sutton & Barto)

Implementation of all RL algorithms in a simpler way

Test that your Claude Code skills, MCP servers, and CLIs actually work when an agent uses them — sandboxed YAML suites, activation checks, A/B experiments, CI gates.

CLI for common Playwright actions. Record and generate Playwright code, inspect selectors and take screenshots.

Lightweight coding agent that runs in your terminal

slime is an LLM post-training framework for RL Scaling.

Optimize prompts, code, and more with AI-powered Reflective Optimization

Official repository for SaaS-Bench: realistic, locally deployable SaaS workflows for GUI agent evaluation.

Give your AI agent access to your live Chrome session — works out of the box, connects to tabs you already have open

Official AHE code — Agentic Harness Engineering: observability-driven automatic evolution of coding-agent harnesses (concurrent w/ meta-harness). NexAU-AHE reaches 84.7% ± 2.1 pass@1 on Terminal-Be…

A library of HTML slide templates designed so any coding agent can pick the right one and produce a beautiful deck on the user's behalf, automatically.

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Heuristic Learning Blog Post

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

The agent that grows with you

My learning notes for ML SYS.

Convert AI coding agent sessions (Claude Code, Cursor, Codex, Gemini, OpenCode, Kimi Code) into self-contained, embeddable HTML replays

LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and m…

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

🌎💪 BrowserGym, a Gym environment for web task automation