Qwen3.8-27B and Qwen3.6-35B-A3B local inference engine for Vulkan and Metal

Mirror Apple Notes to Supernote devices as .note files

MCP proxy server that reduces LLM context overhead with on-demand tool loading from multiple upstream servers.

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on App…

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & En…

Token-efficient MCP adapter for Pi coding agent

A harness optimized to smaller LLMs

F# pipeline engine for multi-stage AI workflows

FsMcp is an idiomatic F# toolkit for building Model Context Protocol (MCP) servers and clients with type safety, computation expressions, and zero boilerplate.

Extensible interactive notebook platform. Every feature is an extension built on the same public interfaces available to third party authors. Runs in VS Code and the browser.

Generate audiobooks from e-books, 50+ TTS engines with voice cloning and 1696 languages!

Socratic is a framework for building reliable vertical AI agents by letting human experts teach agents interactively, turning tacit domain knowledge into a continuously improving knowledge base.

Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)

Assistant: AI Helper Plugin for KOReader : lets you interact with AI language models (Claude, GPT-4, Gemini, DeepSeek, Ollama etc.) while reading

[JMLR 2026] UQLM: A Python package for LLM hallucination detection using uncertainty quantification

Next-generation AI roleplay system

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…

100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.

Python tool for converting files and office documents to Markdown.

MacOS menu‑bar utility to adjust Apple Silicon GPU VRAM allocation

Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!

Make use of Intel Arc Series GPU to Run Ollama, StableDiffusion, Whisper and Open WebUI, for image generation, speech recognition and interaction with Large Language Models (LLM).

Designing with types requires a lot of code - this library fixes that

Clef Library Binding Generator

Hedgehog with batteries included: Auto-generators, extra combinators, and more.

F# Extensions to the Rhino.Scripting libray.

Proof of Concept using MLIR and LLVM to build binaries from F# code