- Unsloth★77.2k
Run and fine-tune LLMs and diffusion models locally —…
- Ollama★182.1k
The simplest way to run open language models on your…
- vLLM★93.1k
A high-throughput and memory-efficient inference and…
- Web LLM★19.2k
High-performance In-browser LLM Inference Engine
- Text Generation Webui★47.7k
Open-source desktop app for local LLMs. Text, vision,…
- Koboldcpp★11.9k
KoboldCpp - Run GGUF AI models locally with a KoboldAI…
- Jan★44.8k
Jan is an open source alternative to ChatGPT that runs…
- Open Webui★153.9k
User-friendly AI Interface (Supports Ollama, OpenAI…
- Cactus★6.1k
Quantization, kernels, runtime and inference engine for…
- llama.cpp★130.2k
LLM inference in C/C++
- lobehub★83.0k
🤯 LobeHub is your Chief Agent Operator, organizing your…
- litellm★60.1k
The fastest, litest AI Gateway. Rust core with Python…
- exo★47.7k
Run frontier AI locally.
- Fabric★44.2k
Fabric is an open-source framework for augmenting…
- FastChat★39.6k
An open platform for training, serving, and evaluating…
- llmfit★37.5k
Hundreds of models & providers. One command to find…
- AionUi★33.3k
Open-source 24/7 Cowork app for OpenClaw, Hermes,…
- llamafile★26.2k
Distribute and run LLMs with a single file.
- kotaemon★25.8k
An open-source RAG-based tool for chatting with your…
- MaxKB★22.9k
🔥 MaxKB is an open-source platform for building…
- llm★12.6k
Access large language models from the command-line
- assistant-ui★12.4k
Typescript/React Library for AI Chat 💬🚀
- Soup★8.1k
Fine-tune LLMs from one YAML. Layer streaming trains an…
- shimmy★5.9k
⚡ Pure-Rust WebGPU inference engine — OpenAI-API…
- DeskcommCRM★4.4k
Open-source AI sales OS — self-hosted CRM with native…
- ComfyUI-GGUF★4.1k
GGUF Quantization support for native ComfyUI models
- ramalama★3.1k
RamaLama is an open-source developer tool that…
- ext-apps★2.9k
Official repo for spec & SDK of MCP Apps protocol -…
- atomic-agent★2.7k
Atomic Agent is a local-first AI agent. Runs…
- maid★2.7k
Maid is a free and open source application for…
- handy-ollama★2.5k
动手学Ollama,CPU玩转大模型部署,在线阅读地址:https://datawhalechina.githu…
- comfyui_LLM_party★2.4k
LLM Agent Framework in ComfyUI includes MCP sever,…
- node-llama-cpp★2.2k
Run AI models locally on your machine with node.js…
- ReadAny★2.7k
AI e-book reader with semantic search, RAG chat, notes,…
- token-monitor★2.6k
Local-first widget tracking token usage and costs…
- webclaw★2.4k
Fast Rust scraper that turns web pages into clean data…
- WhisperJAV★2.3k
Noise-robust subtitle generator powered by Whisper and…
- kalosm★2.2k
Run controllable pre-trained AI models locally, written…
- claude-real-video★2.2k
Let any LLM actually watch a video — frames plus…
- Orkas★2.2k
Local-first desktop where a commander LLM directs…
- agent-safehouse★2.1k
Sandbox for local AI agents so they only touch what…
- meridian★2.1k
Local API bridge to run Claude and Antigravity inside…
- memmy-agent★2.0k
One shared local memory hub so every AI agent remembers…
- obsidian-textgenerator-plugin★2.0k
Generate text inside Obsidian with cloud or local AI…
- llm-space★2.0k
Desktop lab for prototyping AI agents — inspect steps,…
- skales★1.9k
Personal AI agent that takes goals and works alone…
- waku-agent★1.9k
Local-first agent harness with loop, memory, and evals…
- AIaW★1.8k
Elegant AI chat client with workspaces, plugins, and…
- ai-file-sorter★1.8k
AI file organizer that sorts and renames files by…
- OpenOSINT★1.7k
AI OSINT agent with 20 tools and REPL — for authorized…
- lemonai★1.6k
Self-evolving general AI agent running fully locally, a…
- Agentlas-OS★1.6k
Agent hub that spins up a fresh orchestrator per task,…
- nobodywho★1.5k
Lightweight inference engine for running LLMs…
- BrowserAI★1.5k
Run local LLMs like Llama and DeepSeek right inside…
- sre★1.3k
Cloud-native runtime for building and running agentic…
- ollama-gui★1.3k
Clean web interface for chatting with your local Ollama…
- GoModel★1.2k
Go-built AI gateway unifying many providers with…
- solomd★1.2k
Local-first markdown editor that coding assistants can…
- rizzo-pii★1.1k
Local-first privacy guard that strips PII before…
- opendroid★1.1k
Autonomous Android agent that sees and taps your phone…
- starnet★1.0k
Pixel-art desktop where your local-first AI agents…
- Dark-Moon★992
Autonomous AI pentesting with 50 specialist agents on a…
- selfhost-ai★939
One-command installer for a full self-hosted AI stack…
- local-talking-llm★892
A talking LLM voice assistant that runs fully offline…
- WebMCP★883
Early proposal and implementation for connecting LLMs…
- api-relay-audit★865
Local security auditor for AI API relays — catches…
- argo★829
Desktop AI agent platform with one-click models and…
- can-i-finetune-this★792
Check if your GPU can fine-tune an LLM — memory…
- comfyui-mcp★785
Agent-native control plane for ComfyUI — generate media…
- whatcanirun★247
Find the best local models for your hardware — and how…
- helmor★1.3k
A local workbench for multi-agent software development.
- agent-sessions★889
Browse and resume your AI coding-agent sessions on…
- gpt-home★651
ChatGPT for your home, running on a Raspberry Pi.
- airunner★1.3k
Offline inference engine for art.
- skillpack★1.2k
Pack and deploy local AI agents designed for your team…
- ClawBio★1.1k
A utility for clawBio - The first bioinformatics-native…
- alethe-agents★804
Local-first desktop workspace designed for running.
- Agent★642
Agent! now supports macOS 14.6 or later, Apple Silicon…
- Molio★431
Local-first personal knowledge layer for AI agents.
- pizza-bot★419
Local-first inbox designed for long-running AI agents,…
- pentest-harness★405
Pentest Harness — Heaven for Hackers.
- chatgpt-subtitle-translator★389
Token efficient translation utility built on ChatGPT or…
- getspecstory★1.3k
Turn your AI coding chats into reusable skills with IDE…
- agent-console★800
Local-first dashboard of tokens, models, and cost for…
- ChatLLM-Web★636
Private AI chat and model studio that runs in your…
- thClaws★1.2k
Open source AI agent harness in native Rust - GUI, CLI,…
- localgpt★1.1k
Dreaming explorable worlds: local AI assistant.
- pasteguard★761
AI gets the context.
- TrustLLM★633
[ICML 2024] TrustLLM: LLM trustworthiness evaluation…
- ai-text-detector★446
A cautious, explainable AI-like text risk analysis tool…
- ownmem★423
Open source, Git-native memory for AI coding agents -…
- agentdock★1.2k
Secure MCP runtime letting AI agents operate your local…
- Skills-Manager★1.0k
Write an agent skill once, sync it to 32 AI coding…
- codanna★744
Local code-intelligence MCP server and CLI for coding…
- agents★583
Open-source marketing agents for Claude, ChatGPT, and…
- agnt★545
A local-first OS for building and running AI agents.
- roam-code★517
Local codebase intelligence CLI and MCP for coding…
- velorn★497
AI-native video editing on real timelines with local…
- zhigeng★490
A local-first context and memory layer for your AI…
- subsai★1.7k
Whisper-powered subtitle generation: Web UI, CLI, and…
- entroly★472
Cut AI context cost with reversible, byte-exact…
- mcp-google-map★467
18 Google Maps tools and 3 agent skills over MCP or CLI.
- ServBay★455
An AI-native local dev tool giving agents a real…
- LlamaPen★450
A no-install GUI for Ollama and other local LLM…
- marm-memory★416
A local-first 3-in-1 AI memory layer and MCP server.
- prismor★399
Self-hosted control plane: approve or block rogue agent…
- PhoneClaw★1.3k
Self-hosted local llm: turns phones into local ai agent…
- SiliconScope★975
Run siliconscope locally: sudoless apple silicon system…
- rustunnel★659
Rustunnel, in Rust — built for self-hosted, secure…
- code-context-engine★425
Code-context-engine, in Python — built for save 94% on…
- airllm★35.5k
Run a 70B LLM on a single 4GB GPU — layer-by-layer…
- mlc-llm★23.2k
Compile and run LLMs anywhere - phones, laptops,…
- omlx★22.6k
A fast LLM inference server for Apple Silicon, managed…
- Qwen3-Coder★16.8k
Qwen3-Coder - Alibaba's open code model series for…
- MNN★16.2k
Alibaba's lightweight, blazing-fast inference engine…
- nano-vllm★15.7k
A lightweight vLLM implementation built from scratch in…
- ChatGLM2-6B★15.5k
Open bilingual (Chinese-English) 6B chat LLM with…
- vllm-omni★7.1k
vLLM-Omni — efficient inference for omni-modality…
- DeepSeek-Coder-V2★7.0k
DeepSeek-Coder-V2 — DeepSeek's open code model family…
- lemonade★5.8k
Discover and run local AI apps, serving optimized LLMs…
- gemma★5.8k
Google DeepMind's Gemma open-weight LLM library —…
- Step-3.5-Flash★2.1k
StepFun's open 196B MoE model that activates 11B…
- TokenSpeed★2.5k
TokenSpeed — a speed-of-light LLM inference engine…
- GPT4All★77.4k
GPT4All — run local LLMs on any device: a free desktop…
- BitNet★41.2k
BitNet — Microsoft's official inference framework for…
- Strata★33.3k
Strata — one-click Qwen3.8-Flash-Next inference on…
- GPT-OSS★20.5k
GPT-OSS — OpenAI open-weight language models:…
- OLMo-core★1.8k
OLMo-core — the current PyTorch building blocks for the…
- colibri★49.3k
Tiny C engine that runs huge MoE models on the machine…
- FreeToken★17.2k
Run 290B+ frontier MoE models on your own gaming PC at…
- Kimi K3 in C★12.1k
Kimi K3, 2.78 trillion parameters, running on one CPU…
More sitemap pages: VideoImageAudioAI MusicAI 3DClippingAI ChatAI AgentsRAG & KnowledgeAutomationProductivityDev ToolsDesignWritingSelf-HostedEasy Install