AI Tools Radar › Categories › Local / on-device AI
Local & on-device AI tools
Tools that run models locally or on-device: Ollama, llama.cpp, MLX, Apple silicon and offline AI apps. 45 items in today's radar (data fetched 21 Oct 2026, 14:13 (Berlin time)). Categories are assigned by fixed keyword rules on GitHub topics, repo names, descriptions and Show HN titles; an item can be in several categories. How categories work.
All 393Agents & automation 196Coding assistants & dev tools 168Chat apps & assistants 28LLM inference & serving 36RAG & search 28Training & fine-tuning 11Models & research 36Image, video & audio generation 52Voice & speech 21Computer vision 8MCP, skills & plugins 146Evaluation & observability 22Data & datasets 30Local / on-device AI 45Security & sandboxing 33Learning & resources 48Other 16
Trending on GitHub today (5)
| Repository | Stars today | Total stars | Language | License | Created |
|---|---|---|---|---|---|
| 1. MadsLorentzen/ai-job-search The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it. | 3,861 | 62,160 | Python | MIT | 2026-03-18 |
| 2. xerj-org/xerj Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora. | 2,660 | 12,608 | Rust | Apache-2.0 | 2026-06-30 |
| 3. Comfy-Org/ComfyUI The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world. | 1,206 | 141,213 | Python | GPL-3.0 | 2023-01-17 |
| 4. ollama/ollama Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | 437 | 184,129 | Go | MIT | 2023-06-26 |
| 5. lyogavin/airllm AirLLM 2.8T LLM inference with single 4GB GPU | 386 | 40,040 | Jupyter Notebook | Apache-2.0 | 2023-06-12 |
Trending on GitHub this week (8)
| Repository | Stars this week | Total stars | Language | License | Created |
|---|---|---|---|---|---|
| 1. debpalash/VoiceStudio VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages. | 17,057 | 79,695 | Python | AGPL-3.0 | 2026-04-09 |
| 2. MadsLorentzen/ai-job-search The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it. | 12,848 | 62,160 | Python | MIT | 2026-03-18 |
| 3. xerj-org/xerj Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora. | 8,074 | 12,608 | Rust | Apache-2.0 | 2026-06-30 |
| 4. Comfy-Org/ComfyUI The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world. | 3,364 | 141,213 | Python | GPL-3.0 | 2023-01-17 |
| 5. lyogavin/airllm AirLLM 2.8T LLM inference with single 4GB GPU | 1,694 | 40,040 | Jupyter Notebook | Apache-2.0 | 2023-06-12 |
| 6. ethanplusai/harvey Autonomous AI sales agent powered by Claude Code or Codex. Finds prospects, writes cold emails, sends campaigns, handles replies, books meetings. No API keys needed — runs on your Claude or Codex subscriptions. | 1,505 | 1,910 | Python | MIT | 2026-03-12 |
| 7. ollama/ollama Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | 1,391 | 184,129 | Go | MIT | 2023-06-26 |
| 8. UFund-Me/Qbot [🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant | 88 | 18,712 | Jupyter Notebook | MIT | 2022-11-23 |
New repos of the last 30 days (32)
| Repository | Age | Total stars | Language | License | Created |
|---|---|---|---|---|---|
| 1. Niko1221/Strata Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input. | 26 d | 29,588 | C++ | MIT | 2026-09-24 |
| 2. ARahim3/DigUp 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. | 12 d | 5,295 | Swift | MIT | 2026-10-08 |
| 3. mw00/project-maya Project Maya - run GLM-5.3-Flash (321B MoE) and DeepSeek-V4.1-Flash-1017 (748B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools. | 14 d | 1,350 | C++ | MIT | 2026-10-06 |
| 4. StayLameBro/backburner Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable | 19 d | 1,092 | Python | MIT | 2026-10-01 |
| 5. StartLuxLabs/StartLux-Decision Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX. | 22 d | 1,073 | Python | Apache-2.0 | 2026-09-29 |
| 6. LiCinCan/blender-ai-mcp-addon AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon and plugin, copilot for 3D, bpy Python scripting, MCP integration. | 5 d | 958 | Python | MIT | 2026-10-15 |
| 7. jev-chat/jev-chat-windows JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动 | 29 d | 830 | Python | Other | 2026-09-21 |
| 8. franzenzenhofer/big-arrow-on-the-screen Let your AI agents paint big arrows, boxes and text on your Mac screen. One CLI, click-through, gone by itself. Skill for Claude Code and Codex. MIT. | 13 d | 797 | Swift | MIT | 2026-10-08 |
| 9. GTKottman/mortiflix-oss A motion design studio on your own machine: Claude makes the video step by step, you approve every stage. Bring your own Claude Code or API key. | 15 d | 650 | JavaScript | AGPL-3.0 | 2026-10-05 |
| 10. cobanov/PS5LM llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8 | 19 d | 621 | C++ | GPL-3.0 | 2026-10-01 |
| 11. i12bp8/decomp.wtf archived What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally. | 8 d | 531 | Python | MIT | 2026-10-13 |
| 12. strands-agents/box Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon, with Linux support planned. | 18 d | 449 | Rust | Apache-2.0 | 2026-10-02 |
| 13. chenxiachan/textfold Fold papers, web pages, files, and AI replies into five levels of detail. Zoom from an overview to the original text. | 16 d | 405 | Python | Apache-2.0 | 2026-10-04 |
| 14. Hybirdss/Hycli Websites, ready for AI. Turn website tasks into verified CLI and MCP actions, with a local dashboard and 20 languages. | 11 d | 398 | Rust | Apache-2.0 | 2026-10-09 |
| 15. kanaworksai-hue/audio-studio-mcp Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key. | 3 d | 397 | Python | MIT | 2026-10-18 |
| 16. sitor-ai/frametell Frametell: turn your ideas and material into vivid explainer videos with an AI director agent. Local-first, any model. | 11 d | 357 | TypeScript | AGPL-3.0 | 2026-10-10 |
| 17. Nongfsq/ftop A small, quiet system monitor for Apple Silicon Macs: one floating glass panel that works at any size. | 14 d | 338 | Swift | MIT | 2026-10-06 |
| 18. Graphicle-AI/graphicle Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client. | 6 d | 334 | Rust | Apache-2.0 | 2026-10-14 |
| 19. VecSzn/PolyStrata Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost. | 14 d | 324 | C++ | MIT | 2026-10-06 |
| 20. LosaLosSantos/aurelio-finance Open-source personal finance app with an AI financial advisor: track your net worth, investments, ETFs, cash and debts on your own computer. | 14 d | 320 | Python | MIT | 2026-10-06 |
| 21. AienTech/dossier A self-hosted job search app that writes tailored resumes and cover letters from your profile. | 17 d | 302 | TypeScript | AGPL-3.0 | 2026-10-03 |
| 22. Chengjun023/agent-smith Token 超支？快给史密斯打电话！ Better Call Smith. Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts. | 20 d | 301 | Python | MIT | 2026-09-30 |
| 23. Atoll92/agent-standup Your Claude Code, Codex and Mistral Vibe sessions as a live, animated team call: who is working, who waits on whom, who needs you. VS Code extension, terminal command, desktop app. Runs locally, zero tokens. | 11 d | 300 | HTML | MIT | 2026-10-10 |
| 24. tswawa/WechatVibe 微信聊天分析工具，支持本地 Laya 与 API 模型，提供意图识别、情绪感知、人物画像、群聊画像、好感度分析和 MBTI 聊天推测。 | 28 d | 283 | Python | Apache-2.0 | 2026-09-23 |
| 25. FavioVazquez/showtime A local video studio for your coding agent. Describe a video in one sentence: your agent directs, your machine renders. Claude Code, Codex, Cursor, Devin and more. No API keys, no uploads. | 22 d | 272 | Python | MIT | 2026-09-28 |
| 26. openspline/openspline Give a face to your voice AI in 5 lines of code. Generate realtime avatar video connected to your voice AI locally | 21 d | 270 | Python | MIT | 2026-09-29 |
| 27. ANDRETRIPOL/OpenGhost Open desktop AI agent for Windows, macOS and Linux, written from scratch: its own agent engine, its own browser tooling and its own drawing engine that shows what it explains. | 25 d | 266 | JavaScript | MIT | 2026-09-25 |
| 28. Indras-Mirror/Xolotl Xolotl (formerly Strata-DSV4.1): DeepSeek-V4.1-Flash, all 552B, on one gaming PC (RTX 4090 + 90 GB RAM) at ~27 tok/s, plus GLM-5.3-Flash, Qwen3.8-Flash-Next and Qwen3.8-27B. A heavily extended fork of Strata: MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API. | 14 d | 262 | C++ | MIT | 2026-10-06 |
| 29. pullboard-dev/pullboard Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it. | 14 d | 246 | JavaScript | MIT | 2026-10-07 |
| 30. crow-hq/llm-wiki-v2 Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW classifier routing: 89% right note vs 62%, 2.1× faster ingest, 68% fewer tokens. | 26 d | 244 | Python | AGPL-3.0 | 2026-09-24 |
| 31. d2r-mobile/d2r-mobile Diablo II: Resurrected on iPhone, iPad, Apple silicon Mac and Android (in development). Offline play, touch controls, one-tap Runewords and 100-level Greater Rifts. Metal on Apple; Vulkan on Android. Includes Reign of the Warlock. Open source; bring your own Switch game files. 暗黑2重制版 · iOS / macOS / Android. | 9 d | 244 | C | MIT | 2026-10-12 |
| 32. raullenchai/esp32-thinks A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk. | 8 d | 236 | Shell | MIT | 2026-10-12 |
AI launches on Show HN (5)
| Show HN post | Points | Comments | Posted |
|---|---|---|---|
| 1. Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware HN discussion · by albinstman | 329 | 86 | 2026-10-17 |
| 2. Show HN: Pulse Local, a Mac budgeting app whose AI models run on your machine HN discussion · by niztk | 122 | 71 | 2026-10-13 |
| 3. Show HN: Breadcrumb, record everything on your mac + context manager for AI HN discussion · by jv22222 | 49 | 8 | 2026-10-01 |
| 4. Show HN: Free open source Adobe Lightroom alternative, completely local with AI HN discussion · by thesnarkitecht | 47 | 66 | 2026-10-08 |
| 5. Show HN: Strot – Compile an LLM's intent once, run decisions locally HN discussion · by solohunter001 | 23 | 14 | 2026-10-19 |