AI & ML · This month's GitHub chart
AI & ML repositories pooled from every language chart and re-ranked by stars gained. As of Thu, Nov 19, 4 PM GMT+9.
- 1
HKUDS/DeepTutor
AI-powered lifelong personalized tutoring platform
DeepTutor is a Python-based personalized AI tutoring system. It combines document reading, book editing, quizzes, and learning records on top of custom knowledge bases.
+19,065this month
- 2
harry0703/MoneyPrinterTurbo
Automated AI short-video generation tool
An automated workflow tool that generates high-definition short videos from a topic or keyword by handling scripting, footage matching, subtitles, background music, and editing. It can be used through a WebUI, API, CLI, or AI Agent.
+12,482this month
- 3
TauricResearch/TradingAgents
Multi-agent LLM financial trading framework
A research framework where specialized LLM agents mirror a trading firm's roles to analyze markets and make trading decisions. Analysts, researchers, traders, risk managers, and portfolio managers collaborate and debate to determine strategies.
+11,672this month
- 4
JustVugg/colibri
Hierarchical inference engine for large MoE models
colibri is a C-based inference engine that runs large mixture-of-experts models on consumer hardware. It keeps dense layers and hot experts in RAM or on a GPU while streaming cold experts from disk.
+9,414this month
- 5
ruvnet/RuView
WiFi-based spatial intelligence and vital sign sensing platform
RuView turns ordinary WiFi Channel State Information (CSI) into real-time spatial intelligence, detecting presence, breathing, heart rate, and movement without cameras or wearables. It runs locally on low-cost ESP32 sensors and edge models without requiring cloud connectivity.
+6,357this month
- 6
CopilotKit/OpenBot
Self-hostable open-source workspace for AI coworkers
OpenBot is a modular, self-hostable workspace for running AI coworkers with your choice of models, agents, and tools. It runs as a standalone desktop app or on Kubernetes and lets users watch bots use browsers and tools while requiring approval before actions.
+6,310this month
- 7
kuafuai/andee
On-device personal AI agent for Android and macOS
An on-device personal AI agent for Android and macOS that reads the screen and operates any app without integrations or root access. It supports any OpenAI-compatible model and keeps memory and passwords stored locally on the device.
+6,259this month
- 8
AstrBotDevs/AstrBot
Multi-platform AI agent chatbot framework
An open-source AI agent chatbot platform that connects mainstream instant messaging apps with LLMs. It supports MCP, skills, knowledge bases, a WebUI, and an agent sandbox for building conversational AI workflows.
+5,306this month
- 9
cjpais/Handy
Offline open-source speech-to-text desktop app
Handy is a cross-platform desktop application that transcribes speech via a keyboard shortcut and pastes the text directly into any active text field. All audio processing runs locally on your computer without sending data to the cloud.
+5,234this month
- 10
ggml-org/llama.cpp
C/C++ inference engine for LLMs and MLLMs
Built on top of the ggml library, llama.cpp enables LLM and MLLM inference with minimal setup across a wide range of hardware.
+4,861this month
- 11
ollama/ollama
Local and cloud runner for open AI models
Ollama is a tool for running and managing open models such as Kimi, GLM, MiniMax, DeepSeek, Qwen, and Gemma locally or in the cloud. It provides a CLI, a REST API, and Python and JavaScript libraries to chat with models or connect them to existing agents and applications.
+4,822this month
- 12
Anil-matcha/Open-Generative-AI
Open-source AI image and video generation studio
Open-source studio for generating AI images, videos, audio, and lip sync using models such as Flux, Midjourney, Kling, Sora, and Veo. It runs without content filters and supports self-hosting as well as desktop apps.
+4,659this month
- 13
elie222/rakazo
Open-source self-hosted AI bot platform
Rakazo is an open-source, self-hosted alternative to Grok Bot where you choose your own AI models and sandboxes. Each bot gets persistent memory, routines, and a computer with a browser, terminal, and files.
+4,644this month
- 14
FareedKhan-dev/kimi-k3-in-c
Portable C99 inference engine for Kimi K3 on a single CPU
A portable C99 inference engine that runs the 2.78-trillion-parameter Kimi K3 model on a single CPU without BLAS, frameworks, or GPUs. It streams the 1.56 TB checkpoint from disk so it can run in 8.24 GB of RAM while producing byte-identical output across memory budgets.
+3,319this month
- 15
infiniflow/ragflow
Agent-native RAG and context engine
RAGFlow is an open-source RAG engine and agent-native database that extracts knowledge from complex unstructured data to build a context layer for LLMs. It provides an end-to-end workflow covering document parsing, chunking, and agentic retrieval.
+2,197this month
- 16
78/xiaozhi-esp32
MCP-based voice AI chatbot firmware for ESP32
An ESP32 voice chatbot firmware that connects large models such as Qwen and DeepSeek with multi-terminal control over the MCP protocol. It communicates over Wi-Fi, wired Ethernet, or 4G using WebSocket or MQTT+UDP.
+2,092this month
- 17
opensandbox-group/OpenSandbox
Fast sandbox runtime for AI agents
OpenSandbox provides isolated environments for AI applications to execute code, run commands, manage files, and operate browsers or desktops. It lets you start locally with Docker and deploy to Kubernetes through a unified sandbox API.
+1,660this month
- 18
metadist/synaplan
Open-source multi-channel AI assistant platform
Synaplan is an open-source AI platform for building assistants on your own documents and deploying them across web, WhatsApp, email, Outlook, Nextcloud, and ownCloud. It lets you mix local and cloud models while displaying the cost of every answer.
+1,060this month
- 19
ashhart/TensorFold
Zig-based LLM inference engine for Metal, CUDA, and Vulkan
TensorFold serves language models from a Zig binary on Apple Silicon and NVIDIA GPUs. It reads checkpoints, tokenizes requests, and runs Metal or CUDA kernels directly without requiring Python or MLX.
+966this month
- 20
facebookresearch/faiss
Dense vector similarity search and clustering library
Faiss is a library for efficient similarity search and clustering of dense vectors, including datasets larger than RAM. It is written in C++ with Python/numpy wrappers and optional GPU implementations.
+693this month
- 21
Mesh-LLM/mesh-llm
Distributed GPU and memory pooling for LLM inference
Mesh LLM pools GPUs and memory across multiple machines and exposes them as a single OpenAI-compatible API on localhost port 9337. It automatically decides whether to run a model locally, route it to a peer, or split it across nodes using Skippy stages.
+659this month
- 22
farzaa/clicky
Screen-aware AI tutor living next to your cursor
An open-source macOS menu bar AI tutor that sees your screen, talks with you, and points at UI elements with a cursor overlay. It is the codebase behind HeyClicky, connecting Claude, AssemblyAI, and ElevenLabs through a Cloudflare Worker proxy.
+333this month
- 23
kaishi00/hermes-conduit
Native SwiftUI iOS client for Hermes Agent
Conduit is a native app for iPhone, iPad, and Apple Watch that connects to your self-hosted Hermes Agent dashboard. It shares the same sessions, profiles, bots, and scheduled jobs as your desktop setup so you can pick up conversations anywhere.
+322this month
- 24
techjarves/Uncensored-Local-AI-Multiplatform
Cross-platform Flutter app for offline local AI models
A cross-platform Flutter application that runs open-source GGUF AI models directly on Android, iOS, and desktop devices without cloud dependency. All conversations stay on-device and work completely offline after downloading a model.
+303this month
- 25
ggml-org/Llama-Windows
Windows system tray app for local LLMs
Llama is a Windows 11 WinUI 3 tray app for running llama.cpp models locally. It manages a local llama serve process via its REST API and stores models in the standard Hugging Face cache.
+236this month