Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

⚔️ Official code of "Search Arena: Analyzing Search-Augmented LLMs".

[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use

Public repository for Skills

official code for "Large Language Models as Optimizers"

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Klavis AI (YC X25): MCP integration platforms that let AI agents use tools reliably at any scale

Envoy SDS server with AWS ACM backing

Gopher Hawaiian Shirts

Curated list of datasets and tools for post-training.

A collection of LLM memes

A high performance and flexible authorization/permission engine built for developers and inspired by Google Zanzibar

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents

Pure Go minimal Doom implementation

"RAG-Anything: All-in-One RAG Framework"

τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Code and Data for Tau-Bench

MCP Think tool prebuilt binaries and code

A Tool to Visualize Claude Code's LLM Interactions

🖱️ An interface that transforms actions into prompts for LLMs

Intelligent automation and multi-agent orchestration for Claude Code

Kubernetes IN Docker - local clusters for testing Kubernetes

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.