Trending AI reposUpdated daily from GitHub

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，接入openClaw，真正的个人语音助手，时延低至800ms，Mac等低配置也可运行，支持打断

One SQL interface for 60+ tools (e.g., GitHub, Notion, Airtable). Plug into any LLM through MCP.

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.

Bringing BERT into modernity via both architecture changes and scaling

NBA sports betting using machine learning

A neurosymbolic perspective on LLMs

自然语言处理、知识图谱、大语言模型，Agent等技术的前沿追踪、研究与应用。

Emu Series: Generative Multimodal Models from BAAI

Learn LLM internals step by step - from tokenization to attention to inference optimization.

"Your Fully-Automated Personal AI Assistant"

A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more.

The React library for LLMs

Create characters in Unity with LLMs!

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

Optimized Agentic and LLM Bulk Processing Over Your Data

A program that provides LLMs with the ability to complete complex tasks using plugins.

A collection of AI Agents papers (Updated biweekly)

A curation of awesome tools, documents and projects about LLM Security.

Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

WARNING: Katib project is DEPRECATED, users should migrate to OptimizationJob and Kubeflow Trainer

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.

Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st solution for LSVOS)

Create architecture diagrams from code automatically using large language models (LLMs).

Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.

Native iPhone app for your Hermes agent

ROSA 🤖 is an AI Agent designed to interact with ROS1- and ROS2-based robotics systems using natural language queries. ROSA helps robot developers inspect, diagnose, understand, and operate robots.

LLM(😽)

playwright for windows computer use

Trench — Open-Source Analytics Infrastructure. A single production-ready Docker image built on ClickHouse, Kafka, and Node.js for tracking events. Easily build product analytics dashboards, LLM RAGs, observability platforms, or any other analytics product.

The backend agents build with - Multimodal database, orchestration, and serving in one file

The open-source React.js Autonomous LLM Agent

Tool for generating high quality Synthetic datasets

《构筑大语言模型应用：应用开发与架构设计》一本关于 LLM 在真实世界应用的开源电子书，介绍了大语言模型的基础知识和应用，以及如何构建自己的模型。其中包括Prompt的编写、开发和管理，探索最好的大语言模型能带来什么，以及LLM应用开发的模式和架构设计。

A curated list of awesome resources, tools, and other shiny things for LLM prompt engineering.

🔥 Real-time NVIDIA GPU dashboard

A fast and lightweight framework for creating decentralized agents with ease.

A beautiful, cross-platform downloader for YouTube, TikTok, Instagram, and 1800+ sites (yt-dlp GUI) with AI video summaries and post-processing

大模型（LLM）全栈学习路线与中文教程🔥：覆盖 Prompt Engineering、RAG、AI Agent、MCP、微调、模型部署、Transformer、AI 编程与大厂面试，从入门到生产实践。

A durable process per agent, with memory that survives restarts

Fast Multimodal LLM on Mobile Devices

⚡ Langchain apps in production using Jina & FastAPI

WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

One sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.

A curated list of awesome LLM agents frameworks.

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

A high-performance inference engine for LLM, VLM and DiT models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.

The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".