Lists (3)
Stars
Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
A first-principles climb from the absolute bottom of hardware to the top of GPU architecture.
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Reverse engineer anything with agents, from app behavior down to native binaries.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
StarCraft: Brood War AI — a neural network trained by self-play RL.
ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.
On-policy distillation for agents without the environment: replay teacher prefixes instead of live rollouts.
Z.ai's coding agent harness. Powerful, intelligent, extensible.
ARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravi…
Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)
CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.
Benchmarking LLM agents on Cyber Threat Investigation.
Manage Multimodal Agentic Context Lifecycle with Lance
Python toolkit for quantitative finance
A CLI for interacting with Google Colab runtimes
A Programming Paradigm for Spatiotemporal Composability
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
A space exploration game built by Claude Opus 5
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
Orchard-Agentic is a collection of open-source work on agentic modeling