Public repository for Agent Skills

Skills Catalog for Codex

Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravit…

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

A live benchmark and evaluation framework for open-ended deep research in the wild.

科学上网🕸️之跑路机场名单收集（2020-2026），欢迎投稿。Ad🔗🈲🙅❌

"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

The open source coding agent.

Claude Code Snapshot for Research. All original source code is the property of Anthropic.

A public repository for running search benchmarks across multiple search providers

Step-DeepResearch

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

Make Any Website into CLI & Use your logged-in browser by AI agent.

The is the release repo for the in-VR app (still here for legacy)

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

LaTeX Thesis Template for Tsinghua University

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

The agent engineering platform.

The absolute trainer to light up AI agents.

Build and run agents you can see, understand and trust.

[ICLR 2026] Meta-RL Induces Exploration in Language Agents

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

Dataset and code for EMNLP2020 paper "HybridQA: A Dataset of Multi-Hop Question Answeringover Tabular and Textual Data"

A tool for extracting plain text from Wikipedia dumps

WideSearch: Benchmarking Agentic Broad Info-Seeking

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.