A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
GitHub repository with 1,435 stars and 134 forks.
Language: Python
Topics: int4, quantization, rounding, transformers, vllm, mxfp4, nvfp4, gguf, sglang, llms
Trending score 1.06, activity score 1.59, stars gained +6, forks gained +0.
2026-06-05: 1,435 stars and 134 forks.
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
GitHub repository with 1,435 stars and 134 forks.
Trending score: 1.06; stars gained: +6; forks gained: +0.
Language: Python
Topics: int4, quantization, rounding, transformers, vllm, mxfp4
🤖🗜️⚡️ Local LLM server for Apple Silicon. 5.4× faster end-to-end on long contexts vs Ollama, 33% less RAM, INT3 support for Qwen3. OpenAI + Ollama drop-in. Built for repeated long-context workloads on memory-constrained Macs.
GitHub repository with 7 stars and 0 forks.
Trending score: 0.07; stars gained: +0; forks gained: +0.
Language: Python
Topics: apple-silicon, inference-engine, int4, kv-cache, llama-cpp-alternative, llm
The agent that grows with you
GitHub repository with 181,384 stars and 31,127 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 12,942 stars and 833 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 27,327 stars and 2,249 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
GitHub repository with 30,002 stars and 4,224 forks.
Trending score: 4.88; stars gained: +688; forks gained: +114.
Language: Python
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
GitHub repository with 4,221 stars and 528 forks.
Trending score: 4.88; stars gained: +476; forks gained: +68.
Language: Python
An opinionated list of Python frameworks, libraries, tools, and resources
GitHub repository with 301,341 stars and 28,044 forks.
Trending score: 4.60; stars gained: +518; forks gained: +24.
Language: Python
Topics: awesome, python, collections, python-frameworks, python-libraries, python-tools
A SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.
GitHub repository with 1,435 stars and 134 forks.
Trending score: 1.06; stars gained: +6; forks gained: +0.
Language: Python
Topics: int4, quantization, rounding, transformers, vllm, mxfp4
🤖🗜️⚡️ Local LLM server for Apple Silicon. 5.4× faster end-to-end on long contexts vs Ollama, 33% less RAM, INT3 support for Qwen3. OpenAI + Ollama drop-in. Built for repeated long-context workloads on memory-constrained Macs.
GitHub repository with 7 stars and 0 forks.
Trending score: 0.07; stars gained: +0; forks gained: +0.
Language: Python
Topics: apple-silicon, inference-engine, int4, kv-cache, llama-cpp-alternative, llm
258 KB WASM runtime for Needle a 26M-parameter tool-calling transformer. Runs in browser, Cloudflare Workers, and Node.js. No backend required.
GitHub repository with 36 stars and 5 forks.
Trending score: 0.00; stars gained: +0; forks gained: +0.
Language: Rust
Topics: agent, ai, browser-ai, cloudflare-workers, edge-ai, embedded-ai