AI & ML · Rising repositories, Wed, Nov 18
Stars gained in a day measured against the repository’s size, so small projects growing fast come first. As of Wed, Nov 18, 6 AM GMT+9.
Only repositories with at least 40 stars today. Growth is against the stars they had before today.
- 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.
+71%+1,175 that day
- 2
vstorm-co/agenticos
Open-source self-hosted AI agent platform for teams
AgenticOS is an open-source, self-hosted platform built on Pydantic AI for building, running, and governing AI teammates on your own infrastructure. It brings together shared chat, RAG, skills, a real browser, and 4,700+ MCP servers in one place.
+12%+42 that day
- 3
Helldez/BigMoeOnEdge
Streaming inference engine for oversized MoE models
A llama.cpp-based inference engine that runs Mixture-of-Experts models larger than device memory by streaming needed experts from flash storage. It includes desktop and mobile apps alongside an OpenAI- and Anthropic-compatible local server.
+4.8%+46 that day
- 4
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.
+2.1%+186 that day
- 5
NVIDIA-NeMo/Switchyard
LLM model routing library for AI agents
Switchyard is an open-source Rust library that helps AI agents choose which model handles each request. It combines efficient and more capable models to balance task success, cost, and latency.
+1.1%+41 that day
- 6
a-ghorbani/pocketpal-ai
On-device AI assistant app for phones
A React Native mobile app that runs language models directly on your phone without an account or internet connection. It handles chat, voice input and output, and tool use locally on the device.
+0.9%+85 that day
- 7
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.
+0.3%+188 that day
- 8
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.
+0.1%+71 that day