The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
- apple-intelligence
- apple-silicon
- cli
- foundationmodels
100,822 visible repositories in the index
25–48 of 141 · Most stars
The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.
Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
AI coding assistant for Xcode
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
See what Claude Code and Codex actually send to the API — and what each part costs.
A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
Model router for agentic systems. Routes every prompt to the right model in <50ms. Cut costs 40-70% with just an endpoint change.
⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.
🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
Translatedtext2vec, text to vector. A text vector representation tool that converts text into vector matrices. It implements text representation and text similarity calculation models such as Word2Vec, RankBM25, Sentence-BERT, and CoSENT, and works out of the box.
Costrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion.
原样镜像官方 Codex 桌面应用:每 15 分钟探测、SHA256 可校验、国内直连下载、 Mac 可增量更新 | Verbatim, verifiable mirror of the official Codex desktop app — probed every 15 min, with a Sparkle delta-update feed.
Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.
NoFWL Desktop Application
A self-hosted CPA / CLIProxyAPI management panel and AI gateway observability dashboard for requests, usage, cost, quota, failures, and account health.
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
Unofficial ChatGPT desktop app for Linux (formerly the Codex app), built locally from OpenAI’s official macOS app. Includes Chat, Work, and Codex. Packages for Debian/Ubuntu (.deb), Fedora/openSUSE (.rpm), Arch (pacman), Nix/NixOS, and AppImage, with Wayland and X11 support.
Cascading runtime for AI agents. Optimize cost, latency, quality, and policy decisions inside the agent loop.
Claraverse is a opesource privacy focused ecosystem to replace ChatGPT, Claude, N8N, ImageGen with your own hosted llm, keys and compute. With desktop, IOS, Android Apps.
Local-first desktop widget for tracking token usage, costs, limits, and session activity across 54+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync.
Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.