Vllm

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

Spark-x2.6 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

🤖 Desktop AI Assistant with Local Model Support - OpenAI SDK compatible agent with memory system, file operations, web search, and modern UI. Supports vLLM, Ollama, Qwen, Llama, and more.

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~165 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.

Self-hosted LLM gateway. One Go binary turns your Macs and Linux boxes into a private inference cluster — multi-machine routing, sharding via llama.cpp-RPC, per-user keys + quotas + audit, OpenAI- and Anthropic-compatible APIs behind one endpoint. Point Cursor / Claude Code / Aider / SDKs at it.

Versatile Almost Local, Eventually Reasonable Assistant 🔫

MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.

Android in docker solution with noVNC supported, video recording, mcp server and AI-agent

AI 基础知识 - GPU 架构、CUDA 编程、大模型基础及AI Agent 相关知识。

Versatile Almost Local, Eventually Reasonable Assistant 🔫

Spark-x2.5 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models

Run OpenClaw on a local model. Zero API cost. One OpenAI-compatible endpoint over Ollama, llama.cpp, vLLM or LM Studio — plus AirLLM for models bigger than your GPU.

Translate entire books with AI you already have.

Home Assistant LLM integration for local OpenAI-compatible services (llamacpp, vllm, etc)

Run any agent on any model, models stored as OCI images

UltraRAG: A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

Versatile Almost Local, Eventually Reasonable Assistant 🔫

High-throughput and low-latency LLM serving engine featuring PagedAttention, continuous batching, and CUDA kernel optimizations.