AI & ML · Today's GitHub chart
AI & ML repositories pooled from every language chart and re-ranked by stars gained. As of Thu, Nov 19, 3 PM GMT+9.
- 1
google-research/paper-orchestra
Multi-agent framework for automated AI research paper writing
PaperOrchestra is a multi-agent framework that turns raw research materials such as ideas and experimental logs into submission-ready LaTeX manuscripts. Specialized agents handle outline generation, literature review, section writing, content refinement, and plotting.
+1,524today
- 2
jingyaogong/minimind
64M-parameter LLM trained from scratch in 2 hours
MiniMind is an open-source project for training a 64M-parameter language model from scratch using native PyTorch. It implements the full LLM pipeline—from data cleaning and pretraining to SFT, reinforcement learning, and tool use—without relying on high-level wrapper libraries.
+687today
- 3
n8n-io/n8n
Fair-code AI agent and workflow automation platform
n8n is a fair-code platform for building and deploying AI agents and workflows by combining a visual canvas with custom code. It runs self-hosted or in the cloud and connects to over 1,500 integrations.
+325today
- 4
microsoft/BitNet
Official inference framework for 1-bit LLMs
bitnet.cpp is the official inference framework for 1-bit LLMs such as BitNet b1.58, providing optimized kernels for fast and lossless inference on CPUs and GPUs. It delivers significant speedups and energy reductions across x86 and ARM platforms.
+325today
- 5
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.
+306today
- 6
ethanplusai/sellbird
Open-source outreach platform using Claude or ChatGPT plans
Sellbird is an open-source outreach platform that finds target companies and decision makers, verifies email addresses, writes personalized cold emails, sends them, and handles replies. It runs locally on your machine and holds all outgoing emails in an outbox until you approve them.
+237today
- 7
huggingface/transformers
Model-definition framework for text, vision, audio, and multimodal ML
Transformers is a model-definition framework for inference and training across text, computer vision, audio, video, and multimodal machine learning models. It centralizes model definitions so they work across major training frameworks and inference engines.
+205today
- 8
openai/whisper
General-purpose speech recognition and translation model
Whisper is a general-purpose speech recognition model trained on a large dataset of diverse audio. A single Transformer sequence-to-sequence model handles multilingual speech recognition, speech translation, language identification, and voice activity detection.
+197today
- 9
tensorflow/tensorflow
Open-source machine learning framework
An end-to-end open-source platform for building and deploying machine learning models. Originally developed by Google Brain, it offers an ecosystem of tools, libraries, and community resources.
+111today
- 10
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.
+106today
- 11
QuantumNous/new-api
Self-hosted open-source AI gateway
A Go-based self-hosted AI gateway that connects upstream model services and exposes unified OpenAI-, Anthropic-, and Gemini-compatible APIs. It centralizes model routing, access control, usage tracking, and cost accounting with a built-in web console.
+80today
- 12
Chevey339/kelivo
Cross-platform Flutter LLM chat client
Kelivo is an open-source Flutter LLM client for Android, iOS, macOS, Windows, and Linux. It lets you connect API keys or supported accounts to use multiple models in one app while keeping conversations and settings local.
+80today
- 13
incoai/splash
Local LLM inference engine for Apple silicon
Splash is a local inference engine for Apple silicon that runs coding agents and OpenAI- or Anthropic-compatible applications on a Mac. It combines DFlash 2 speculative decoding, specialized Metal kernels, and automatic memory planning.
+49today
- 14
qwdwqfwq/topconf-paper-figure-gallery
Curated gallery of top AI conference paper figures
A static web gallery of curated Figure 1 and teaser images from ICLR, ICML, NeurIPS, CVPR, ACL, and AAAI (2023-2026). It also includes FigureForge, a browser-based tool for drafting new paper figures using existing ones as layout references.
+39today
- 15
openvinotoolkit/openvino
Open-source AI inference optimization and deployment toolkit
OpenVINO™ is an open-source toolkit for optimizing and deploying deep learning inference. It converts models from frameworks like PyTorch, TensorFlow, and ONNX so they can be deployed without the original frameworks.
+24today
- 16
carla-simulator/carla
Open-source simulator for autonomous driving research
CARLA is an open-source simulator built to support the development, training, and validation of autonomous driving systems. Alongside open-source code and protocols, it provides free digital assets such as urban layouts, buildings, and vehicles.
+20today
- 17
screenpipe/screenpipe
Local screen and audio recorder for workflow discovery
Screenpipe is a source-available application that continuously records your screen and audio locally to discover recurring workflows. You can review the captured steps and hand them off to your existing AI agents or automation tools.
+18today
- 18
vllm-project/vllm-ascend
Hardware plugin for running vLLM on Huawei Ascend NPU
A community-maintained hardware plugin that enables vLLM to run on Huawei Ascend NPUs. It follows vLLM's hardware-pluggable interface to decouple Ascend NPU integration.
+14today
- 19
alibaba/spring-ai-alibaba
Agentic AI framework for Java developers
A Java framework built on Spring AI for developing agentic, workflow, and multi-agent applications. It provides built-in context engineering and a graph-based runtime for long-running stateful agents.
+8today
- 20
Neroued/ninfer
Native C++/CUDA inference engine for RTX 5090 and DGX Spark
NInfer is a native C++/CUDA inference engine for selected models such as Qwen3.6, Qwen3.8, and GLM-5.3-Flash on RTX 5090 and DGX Spark. It runs text and image/video generation through a local CLI or OpenAI- and Anthropic-compatible HTTP APIs.
+7today
- 21
ddalcu/mlx-serve
Native local AI inference server and app for Apple Silicon
A native AI inference server and macOS app built with a Zig backend and Swift frontend that runs without Python on Apple Silicon. It supports chat, coding agents, images, video, music, speech, and 3D models offline while speaking OpenAI, Anthropic, and Ollama APIs.
+5today