Rank 1
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.
+4.3k stars this week
Trending local LLM tools
Running language models on your own hardware keeps your data private, works offline and costs nothing per token. The tooling moves quickly: inference engines like llama.cpp and MLX, the GGUF model format, runners like Ollama and LM Studio, and the chat apps, clients and plugins built on top of them.
This page follows the #local-llm topic, ranked by stars gained this week relative to size, with the small projects speeding up the most under Emerging.
Follow #local-llm
Rising this week
Full #local-llm rankingRank 2
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
+14.7k stars this week
Rank 3
Project Maya - run GLM-5.3-Flash (321B 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.
+704 stars this week
Rank 4
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
+910 stars this week
Rank 5
AI assistant and MCP server for Blender: visual chat, scene tools, model selection, multi-agent workflows. Works with OpenAI, Claude, Gemini, Ollama and OpenCode. Blender AI automation, bpy scripting, 3D modeling, geometry nodes and MCP integration.
+311 stars this week
Rank 6
llama.cpp on a jailbroken PS5: run any GGUF model natively on the console, starting with Qwen 3.8
+307 stars this week
Rank 7
An agent that moves into your Android phone and becomes its soul — not an assistant, not a tool. Any app, no integrations, on-device, one APK.
+284 stars this week
Rank 8
Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
+489 stars this week
Rank 9
Nongfsq/ftop
NewA small, quiet system monitor for Apple Silicon Macs: one floating glass panel that works at any size.
+183 stars this week
Rank 10
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.
+148 stars this week
Emerging
All emergingSmall repos, under 1,000 stars, growing at least twice as fast as in a usual week.
Rank 1
Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
49× its usual pace: +489 this week vs ~10
+489 stars this week
Rank 2
AssetFurnace: the most complete open-source image-to-3D pipeline (Oct 2026). Prompt or picture → textured, rigged, animated game character, locally on Apple Silicon or NVIDIA. Pixal3D, TRELLIS.2, Hunyuan3D, SF3D, auto-rig and 21 moves. For indie game devs and 3D artists. Free, Apache-2.0.
35× its usual pace: +175 this week vs ~5
+175 stars this week
Rank 3
Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent，免 Root 免 Termux
15× its usual pace: +60 this week vs ~4
+60 stars this week
Rank 4
Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images
19× its usual pace: +57 this week vs ~3
+57 stars this week
Rank 5
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
6× its usual pace: +910 this week vs ~165
+910 stars this week
Rank 6
On-device ComfyUI style node graph for image/video diffusion models on Android. Local SD1.5, SDXL, Flux, Z-image, Anima, Qwen Image 2.1, Krea 2, text to image, img2img, inpainting, outpainting, controlnet, LoRA, IPAdapter and WAN 2.2 5B video generation/ video motion transfer on the Qualcomm Hexagon NPU. Fully offline, no server, no account.
3× its usual pace: +27 this week vs ~10
+27 stars this week
Rank 7
A self-contained native runtime and model format for local AI video generation.
2× its usual pace: +24 this week vs ~10
+24 stars this week