Stars
Build effective agents using Model Context Protocol and simple workflow patterns
Post-training with Tinker
Speed-optimized streaming neural speech enhancement network
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
ArcticInference: vLLM plugin for high-throughput, low-latency inference
Rich is a Python library for rich text and beautiful formatting in the terminal.
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Benchmark and optimize LLM inference across frameworks with ease
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
Tool for generating high quality Synthetic datasets
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Python binding for curl-impersonate fork via cffi. A http client that can impersonate browser tls/ja3/http2 fingerprints.
MiMo-Audio: Audio Language Models are Few-Shot Learners
Real-time terminal monitor for InfiniBand networks - htop for high-speed interconnects
Intelligent Router for Mixture-of-Models
A powerful framework for building realtime voice AI agents 🤖🎙️📹
Semantic search and document parsing tools for the command line
MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone
A command-line interface tool for serving LLM using vLLM.
OCR, layout analysis, reading order, table recognition in 90+ languages
CLI tool for configuring and monitoring Claude Code
Collection of scripts and notebooks for OpenAI's latest GPT OSS models