Lists (7)
AI Resources
AI-related resource repositories.73 repositories
Databases
Database repositories.8 repositories
LLM
LLM-related repositories.269 repositories
LLM Apps
LLM Applications.52 repositories
LLM Datasets
LLM dataset repositories.6 repositories
LLM Frameworks
Frameworks for using LLMs.104 repositories
LLM Prompt Engineering
LLM Prompt engineering repositories.19 repositories
Starred repositories
Open-source framework for computer use agents: VeriGen verifiable task synthesis, online RL training (AgentRL), and OSWorld/ScienceBoard evaluation.
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
macOS CLI tool for emulating mouse and keyboard events
Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models
Fully open data curation for reasoning models
FrontierSmith, a new system that uses AI to synthesize open-ended coding problems at scale
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
Reference code for the Meta-Harness paper.
Ongoing research training transformer models at scale
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
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, …
[ICLR 2026 Oral] ScaleCUA is the open-sourced computer use agents that can operate on cross-platform environments (Windows, macOS, Ubuntu, Android).
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Gym-Anything: Turn any Software into an Agent Environment
Framework for evaluating and improving agents
Lightweight coding agent that runs in your terminal
PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai
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…
A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
slime is an LLM post-training framework for RL Scaling.
🌎💪 BrowserGym, a Gym environment for web task automation
An agentic skills framework & software development methodology that works.