MASA-Safe-RL: A safe reinforcement library for providing a common interface for different constraints and environments
GitHub repository with 6 stars and 6 forks.
Language: Jupyter Notebook
Topics: benchmark, constrained-reinforcement-learning, constraint-satisfaction-problem, deep-learning, deep-reinforcement-learning, gymnasium, jax, machine-learning, reinforcement-learning, safe-reinforcement-learning
Trending score 0.09, activity score 0.32, stars gained +0, forks gained +1.
2026-06-05: 6 stars and 6 forks.
MASA-Safe-RL: A safe reinforcement library for providing a common interface for different constraints and environments
GitHub repository with 6 stars and 6 forks.
Trending score: 0.09; stars gained: +0; forks gained: +1.
Language: Jupyter Notebook
Topics: benchmark, constrained-reinforcement-learning, constraint-satisfaction-problem, deep-learning, deep-reinforcement-learning, gymnasium
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
GitHub repository with 9,099 stars and 584 forks.
Trending score: 2.37; stars gained: +326; forks gained: +20.
Language: Jupyter Notebook
Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform
GitHub repository with 16,980 stars and 4,249 forks.
Trending score: 1.87; stars gained: +8; forks gained: +6.
Language: Jupyter Notebook
Topics: generative-ai, llm, vertex-ai, langchain, gemini, gemini-api
LLM Zoomcamp - a free online course about real-life applications of LLMs. In 10 weeks you will learn how to build an AI system that answers questions about your knowledge base.
GitHub repository with 5,606 stars and 1,014 forks.
Trending score: 1.87; stars gained: +93; forks gained: +13.
Language: Jupyter Notebook
GitHub repository with 2,680 stars and 331 forks.
Trending score: 1.82; stars gained: +48; forks gained: +12.
Language: Jupyter Notebook
Build LLM agents and multi-agent systems from scratch, with MCP, Skills, and A2A
GitHub repository with 125 stars and 44 forks.
Trending score: 1.70; stars gained: +32; forks gained: +14.
Language: Jupyter Notebook
Examples and guides for using the OpenAI API
GitHub repository with 73,980 stars and 12,523 forks.
Trending score: 1.57; stars gained: +24; forks gained: +12.
Language: Jupyter Notebook
Topics: openai, chatgpt, gpt-4, openai-api
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training
GitHub repository with 506 stars and 80 forks.
Trending score: 3.00; stars gained: +33; forks gained: +4.
Language: TypeScript
Topics: agent, agents, ai, android, automation, benchmark
🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.
GitHub repository with 774 stars and 2 forks.
Trending score: 1.88; stars gained: +102; forks gained: +0.
Language: Python
Topics: agentic-ai, benchmark, llm, proactive-agent, search, search-agent
Minecraft-style voxel benchmark for comparing AI models (Arena + Sandbox)
GitHub repository with 244 stars and 17 forks.
Trending score: 1.14; stars gained: +13; forks gained: +0.
Language: TypeScript
Topics: ai, benchmark, llm, nlp, voxel, comparison-benchmarks
AMD Strix Halo local LLM guide: direct 100.0 t/s 30B Qwen MoE on Ryzen AI MAX+ 395 / Radeon 8060S. Setup, benchmarks, raw evidence.
GitHub repository with 88 stars and 4 forks.
Trending score: 0.98; stars gained: +7; forks gained: +0.
Language: Python
Topics: amd, benchmark, gfx1151, inference, llama-cpp, llm
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
GitHub repository with 1,273 stars and 328 forks.
Trending score: 0.92; stars gained: +7; forks gained: +1.
Language: Python
Topics: benchmark, llm, ai, language-model-agent, conversational-agents
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
GitHub repository with 7,061 stars and 783 forks.
Trending score: 0.91; stars gained: +4; forks gained: +1.
Language: Python
Topics: evaluation, benchmark, large-language-model, chatgpt, llm, llama2