madengine is a streamlined CLI tool for running and benchmarking AI models on ROCm GPUs, offering a production‑ready workflow for local single node or remote multi node execution with integrated performance monitoring.
GitHub repository with 8 stars and 14 forks.
Language: Python
Topics: amd-gpu, automation-framework, benchmarking, clustering, distribution, inference, profiling, training
2026-06-05: 8 stars and 14 forks.
AMD CDNA/RDNA (MI300 gfx942 / MI350 gfx950 / RDNA4 gfx1201) GPU kernel optimization knowledge base, packaged as a Claude Code skill. 7,400+ merged-PR references + 53 ISA-grounded synthesis pages. Inspired by MIT Han Lab's KernelWiki.
GitHub repository with 5 stars and 0 forks.
Trending score: 0.03; stars gained: +0; forks gained: +0.
Language: Python
Topics: amd-gpu, cdna, flash-attention, gemm, gpu-kernels, hip
The agent that grows with you
GitHub repository with 181,271 stars and 31,102 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 12,882 stars and 829 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 27,324 stars and 2,248 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
Latest Bazzite Deck, GNOME, and KDE images for AMD BC-250 boards with cyan-skillfish-governor-smu, GPU frequency scaling, and the MangoHud/radeontop 655% telemetry fix
GitHub repository with 10 stars and 0 forks.
Trending score: 0.32; stars gained: +1; forks gained: +0.
Topics: amd, bazzite, bc250, image-based, linux, steam-deck
ML software (llama.cpp, ComfyUI, vLLM) builds for AMD gfx906 GPUs, e.g. Radeon VII / MI50 / MI60
GitHub repository with 238 stars and 29 forks.
Trending score: 0.14; stars gained: +0; forks gained: +0.
Language: C#
Topics: amd-gpu, comfyui, llamacpp, vllm, torch
Performance monitoring and benchmarking suite
GitHub repository with 1,907 stars and 266 forks.
Trending score: 0.04; stars gained: -1; forks gained: +0.
Language: C
Topics: likwid, hardware-performance-counters, threading, x86, c, lua
Local LLM, embedding, reranker, and Whisper inference for Mac + AMD discrete GPU. Ollama- and OpenAI-compatible HTTP APIs. Apache-2.0.
GitHub repository with 5 stars and 1 forks.
Trending score: 0.04; stars gained: +0; forks gained: +0.
Language: Go
Topics: amd-gpu, apache-2, golang, inference, llamacpp, llm
AMD CDNA/RDNA (MI300 gfx942 / MI350 gfx950 / RDNA4 gfx1201) GPU kernel optimization knowledge base, packaged as a Claude Code skill. 7,400+ merged-PR references + 53 ISA-grounded synthesis pages. Inspired by MIT Han Lab's KernelWiki.
GitHub repository with 5 stars and 0 forks.
Trending score: 0.03; stars gained: +0; forks gained: +0.
Language: Python
Topics: amd-gpu, cdna, flash-attention, gemm, gpu-kernels, hip