Trending AI reposUpdated daily from GitHub

DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.

[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

LLMs as Copilots for Theorem Proving in Lean

A set of tools that gives agents powerful capabilities.

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

AI-powered tool for efficient abstract and PDF screening in systematic reviews.

Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)

Evaluate and improve models and agents using environments

Your Software Factory - build faster and better with multi node agents that work 24/7

Helping Ethical Hackers use LLMs in 50 Lines of Code or less..

👨‍🏫 ChatTutor: Visual and Interactive AI Tutor

Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.

An elegent pytorch implement of transformers

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

Jlama is a modern LLM inference engine for Java

Full stack framework for building cross-platform mobile AI apps

The simplest way to run Alpaca (and other LLaMA-based local LLMs) on your own computer

E2M converts various file types (doc, docx, epub, html, htm, url, pdf, ppt, pptx, mp3, m4a) into Markdown. It’s easy to install, with dedicated parsers and converters, supporting custom configs. E2M offers an all-in-one, flexible, and open-source solution.

👨‍💻 An awesome and curated list of best code-LLM for research.

Join a time-traveling adventure where you meet history’s legends while learning Generative AI technologies! ✨

[NeurIPS '25] Knowledge Graph Generation from Any Text

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

Understanding R1-Zero-Like Training: A Critical Perspective

A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

Your Open Autonomous Android Agent — A production-ready, self-planning AI assistant powered by local/remote LLMs and accessibility-driven screen automation.

Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.

AI辅助长篇小说创作，卡片式创作，支持基于 JSON Schema的结构化 AI 生成与上下文引用，可扩展性强。

A collection of autonomous agents 🤖️ powered by LLM.

AttackGen is a cybersecurity incident response testing tool that leverages the power of large language models and the comprehensive MITRE ATT&CK framework. The tool generates tailored incident response scenarios based on user-selected threat actor groups and your organisation's details.

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Local-first privacy guard: anonymize your documents before sharing with LLMs.

DeepSeek Harness 自媒体工作台插件：一句话记灵感，一键生成脚本、封面、配图和分镜

List of language agents based on paper "Cognitive Architectures for Language Agents"

[TMLR 2024] Efficient Large Language Models: A Survey

RayLLM - LLMs on Ray (Archived). Read README for more info.

Pyscripter is a feature-rich but lightweight Python IDE

该项目包括一个基于 GPT 等大语言模型的长篇小说生成器，同时还有各类小说生成 Prompt 以及教程。我们欢迎社区贡献，持续更新以提供最佳的小说创作体验。

Must-read Papers on Knowledge Editing for Large Language Models.

LongBench v2 and LongBench (ACL 25'&24')

LLM KV cache compression made easy

集成了openai-api、coze、deepseek、cursor、windsurf、qodo、blackbox、you、grok、bing 绘画 多款AI的聊天逆向接口适配到 OpenAI API 标准接口服务端。

A family of diffusion models for text-to-audio generation.

A professional list on Large (Language) Models and Foundation Models (LLM, LM, FM) for Time Series, Spatiotemporal, and Event Data.

Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

Fully Open Framework for Democratized Multimodal Training

Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation