Top 50 trending new tools
The most-starred local-AI projects created on GitHub in the last 30 days, ranked by stars. Checked 2026-11-12; refreshed Mon, Thu & Sat.
Official Inference Code of EAGLE-4
eagle-hq/EAGLE-4
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
synchopate/llama-modchip
Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run on Claude, ChatGPT/Codex, Gemini or Grok, with MCP tools, their own computer and browser, routines, memory and approvals. Web, desktop and phone apps. Docker Compose + Postgres. AGPL-3.0.
agentes-chat/agentes-chat
Self-hosted metasearch and grounding engine for AI agents, based on SearXNG. Rust, JSON API, optional page text.
sahenjp/RustXNG
Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai
nace-ai/kapitsa
Your own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Open-source, self-hosted alternative to Grok Bot, Claude Duet and OpenAI dots. Rust + React.
alexsergivan/kwant
An easier way to use AI on your own computer. A free, open-source alternative to Claude and ChatGPT that runs open-weight models like Gemma and gpt-oss locally on Mac, Windows and Linux. Private, and works offline.
FrigadeHQ/hob
🔥🔥 The extremely fast inference engine for decision model
OmniJev/Flide
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
StartLuxLabs/StartLux-Prism
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
JMS1717/ming-voice
The AI-native engine for teams and their agents. Multi-harness, multi-agent, self-hosted.
mdiri-ai/SoduWork
Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.
YOLOW92/pagesift
A browser extension for easy on-device translation with a local LLM (PLaMo). Private, free, no server needed.
jammaru/sakutto
Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.
christos-antono/NPCTalk
A privacy-first local coding agent that consults frontier AI models without exposing your source code.
lemonadesaltbagel/airlock
🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки
justxor/deepseek-local-guide-ru
Local privacy proxy for AI coding agents. Keep PII and secrets out of LLMs with deterministic pseudonymization.
lemonadesaltbagel/veil
PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-correct), OpenAI-compatible local server, report and logs.
Magnvs7/Promethevs
Kindi 0.5: local LLM inference on low-cost NVIDIA GPUs (Kepler to the RTX 50 series and the CMP 170HX), AMD Radeon 780M, 840M and 8060S, and CPUs. Bonsai 2B-27B, AH-Nanbeige4.3-33B and experimental Nemotron, with an OpenAI-compatible server.
ahtx/kindi
Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built into the app.
drawthingsai/local-code-community
Linger is An Open-Source Personal Agent That Runs Fully on Your PC. We aim to break Big Tech’s grip on AI by bringing powerful local AI to everyday computers through efficient model–harness co-design, so everyone can run their own.
simplexai-labs/linger
Memory efficient and high performance Mixture-of-Experts inference for Apple Silicon
davide-troiani/moeshift
Finds the corrections you keep repeating to Claude Code and turns them into evidence-backed CLAUDE.md rules. Local CLI, no LLM by default, plus a public rule pack mined from claude-code issues
globalmpc/nomore
一个基于 Octop 构建的开源、可自托管的企业级 AI 工作空间，集成了 AI 专家资源、员工电脑本地任务执行、模型与访问权限的统一管理，以及团队即时通讯功能。An open-source, self-hosted enterprise AI workspace built on Octop, with AI experts, local task execution on employee computers, centralized models and access, and team messaging.
colorAi/Octop-Enterprise
构屎 GOUJI — 纯 C++/CUDA 的三值 mini LLM。2 bit/权重，零 Python；联想记忆工具路由，零训练参数；143 个缺陷与 29 个变异测试记录在案。
3145544645/gouji
RTX 5070 Ti Laptop 12GB 跑 Qwen3.8-27B：NInfer + KVMem、256K 逻辑上下文、RAM KV、MTP、快速缓存续接与 dsh 本地 Agent / 搜索 / 浏览器。含源码、Windows 部署及实测。
CSUNX233/Sparkle-Qwen27b-Kvmem-ninfer
Local LLM router: a 31 MB task profiler + model-card matcher that picks the cheapest model likely to succeed. HTTP, CLI, Python and MCP.
aicodeking/PandaOrchestrator
A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decoding, KV cache. Every conclusion carries its evidence grade and reproducible conditions.
Lowaltitudeflight/local-llm-tuning-guide
DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.3x the vLLM kit's decode speed.
Elevatormusic/DeepSeek-V4.1-Flash-1017-EXL3-TensorFold-2x-DGX-Spark
You type. It already knows. Local LLMs that read and think while you type.
Mafdet-AI/mafdet
A simulator for LLM Inference prefix cache
cacheMon/PrefixSim
A self-hosted AI gateway for enterprises. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
XGrowthLab/xhub
GPU coordination for local AI companions on AstrBot / DeepSeek Harness: persona LLM, IndexTTS voice and ComfyUI selfies take turns on one 12 GB card. No proxy.
xiaoxiao150/vram-switcher
ChatGPT-style generative UI for Open WebUI: photo galleries, live maps with real routes, multi-day trips, budgets, calculators, live weather & stocks, link previews, and one-click Word/Excel/PowerPoint exports via ArtCraft. One file, no API keys.
Jumbomuffin777/Frontier-UI
Self-hosted AI marketplace, token billing engine & OpenAI-compatible Go API gateway with atomic PostgreSQL ledger, escrow commerce, and Stripe/DOKU/QRIS payments.
yanstd888/node2mint
Capri — an AI desktop companion for Windows with local/API models, Hugging Face, optional voice, memory and permission-based desktop tools.
CapriChooms/CapriCore
Open-source Grok Bot alternative. Pots is an AI coworker that reads every channel, decides what matters, and acts on its own computer. Self-hosted, any model.
Crokily/pi-durable-bot
Abliterated DeepSeek-V4.1-Flash-1017 (FP8 dense, FP4 experts) on 4x RTX PRO 6000 with vLLM-Moet r21, DSpark + FLy verification and top_p 1.0: 463 tok/s single-stream agent decode at 30k-120k context, 1082 tok/s over 8 streams, 1M context, Flex-start GCE VM
hanxiao/DeepSeek-V4.1-Flash-1017-FP8-abliterated-4x-RTX-PRO-6000
Uncensored DeepSeek-V4.1-Flash IQ2_XS on Google Colab
leonxger/deepseek-colab
Alfred: a local-first voice assistant for Home Assistant, with no LLM. Control your smart home, Plex/Jellyfin and Spotify with natural speech. Private beta sign-up aiming for January. Watch this repo to follow along.
MyAlfredAI-App/alfred-voice-assistant
Pools consumer laptops into one local runtime for Meta Llama models. Measures the free VRAM each machine reports, splits the model across CUDA and Metal devices through llama.cpp RPC, and rebuilds the pipeline when a worker drops out.
Dharshaneshwaran/hyperpod
OpenAI-compatible API for built-in macOS functionality. 100% certified!
mattt/preowned
Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки
pipedude/yahont-ce
This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind an agent's chat box runs a loop: step after step, the model proposes an action and the harness carries it out, until it stops.
Agentic-System-Lab/agent-loop-visualizer
Open-source platform for AI chat agents that answer from your own knowledge base. Hybrid RAG search in PostgreSQL, MCP and custom tools, guardrails and human handoff. Put agents on a hosted chat page, a website widget, Slack, Teams, WhatsApp, Telegram or a REST API. Self-host with Docker and open-weight models.
chatvia/chatvia
Stable, high-throughput inference server for multi-GPU NVIDIA V100 (SM70): Qwen3.8 Flash-Next with AWQ / NVFP4, multimodal input, CPU/disk KV offload, and MTP or DFlash2 speculative decoding.
Leonccaa/ReVolta
The free, open source Cursor alternative. An AI code editor that runs on your own API key, your Claude Code or Codex plan, local models, or free models.
noah-thing/open-cursor
Next-Gen LLM Chat and Dialogue Integration for JainaCore 3.3.5a - Multi-Provider Local and Cloud AI with Semantic Caching
Nightdalefaun/resocket-mod-llm-chatter
Local open-source video editor and educational TypeScript agent harness. Bring your own LLM and ASR keys. Powered by Dojo Video Engine.
PansaLegrand/dojo-video-harness
Open-source live workspace where AI agents work alongside your team in real time: live docs, sheets and slides, a shared browser, a Linux desktop and full-duplex voice. Bring Claude Code, Codex, Gemini CLI or any LLM. Self-hosted, MIT. Built by MemoAir (memoair.ai).
MemoAir-labs/Airlink