vMLX - Use MLX models easily - JANGQ (GGUF for MLX) - Not dependant on mlx_vlm

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

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.

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.

MCP server to connect an MCP client (Cursor, Claude Desktop etc) with your ZenML MLOps and LLMOps pipelines

Adaptive Python web scraping toolkit + MCP server for AI agents. Self-healing selectors that survive site changes, TLS-fingerprint stealth to bypass anti-bot filters, CSS/XPath parsing, and 24 built-in scrapers, clean, structured, LLM-ready data from any URL.

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fresh-context execution, durable verified state, independent auditing, recoverable progress, and native Claude Code / Codex / OpenClaw integration.

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage generator and hand-authored long-form blogs 🌱

Experiment task scheduling made easy.

A collection of notes on Data Science

Binary Ninja plugin to provide MCP functionality.

Learn AI and LLMs from scratch using free resources

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task

Generate production-ready Python and AI stacks by combining frameworks, data engines, tooling, and cloud deployment.

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

Diagnose and Fix CUDA / GPU environments compatibility issues locally, in Docker, and CI/CD. CLI + MCP server available.

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Synapse is a local-first personal memory operating system designed for AI agents. It provides durable, typed, and highly reliable long-term memory using only local SQLite — giving agents the ability to remember, update, and reason over facts across sessions with full user control.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on Claude Code, portable across Codex, Cursor & other Skills hosts.

Preline UI is an open-source set of prebuilt UI components based on the utility-first Tailwind CSS framework.