[ICCV 2025] A Benchmark for Multi-Step Reasoning in Long Narrative Videos
GitHub repository with 27 stars and 0 forks.
Language: Python
Topics: benchmark, dataset, evaluation-kit, llm, multi-step-reasoning, video-reasoning, video-understanding, vlm
2026-06-05: 27 stars and 0 forks.
🔍 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
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 7,060 stars and 784 forks.
Trending score: 0.91; stars gained: +4; forks gained: +1.
Language: Python
Topics: evaluation, benchmark, large-language-model, chatgpt, llm, llama2
MTEB: Massive Text Embedding Benchmark
GitHub repository with 3,289 stars and 618 forks.
Trending score: 0.84; stars gained: +4; forks gained: +1.
Language: Python
Topics: benchmark, clustering, information-retrieval, sentence-transformers, sts, text-embedding
Time-Series Anomaly Detection | Algorithms + Datasets + Tutorials
GitHub repository with 281 stars and 58 forks.
Trending score: 0.59; stars gained: +2; forks gained: +1.
Language: Python
Topics: anomaly-detection, benchmark, time-series
The agent that grows with you
GitHub repository with 181,177 stars and 31,085 forks.
Trending score: 5.95; stars gained: +1,867; forks gained: +361.
Language: Python
Topics: ai, ai-agent, ai-agents, anthropic, chatgpt, claude
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
GitHub repository with 12,594 stars and 817 forks.
Trending score: 5.69; stars gained: +2,829; forks gained: +175.
Language: Python
Topics: agent, ai, anthropic, claude-code, compression, context-engineering
Academic Research Skills for Claude Code: research → write → review → revise → finalize
GitHub repository with 27,254 stars and 2,241 forks.
Trending score: 5.52; stars gained: +1,079; forks gained: +89.
Language: Python
Topics: academic-pipeline, academic-writing, ai-research, claude, claude-code, literature-review
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
GitHub repository with 140,059 stars and 20,110 forks.
Trending score: 5.04; stars gained: +317; forks gained: +58.
Language: Python
Topics: ollama, ollama-webui, llm, webui, self-hosted, llm-ui
LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US markets.
GitHub repository with 40,774 stars and 38,952 forks.
Trending score: 4.88; stars gained: +836; forks gained: +443.
Language: Python
Topics: a-stock, ai-agent, aigc, llm, quant, quantitative-finance
GitHub repository with 29,986 stars and 4,219 forks.
Trending score: 4.88; stars gained: +688; forks gained: +114.
Language: Python
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 504 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 7,060 stars and 784 forks.
Trending score: 0.91; stars gained: +4; forks gained: +1.
Language: Python
Topics: evaluation, benchmark, large-language-model, chatgpt, llm, llama2