Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows
- ai
- ai-art
- art
- asset-generator
142,273 visible repositories in the index
841–864 of 1,943 · Most stars
Offline inference engine for art, real-time voice conversations, LLM powered chatbots and automated workflows
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
专为小说创作打造的跨平台、用户友好、AI Native 的一站式 Vibe Writing 工具。A cross-platform, user-friendly, AI-native, all-in-one Vibe Writing tool designed specifically for novel writing.
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Implementation of the node2vec algorithm.
OmniEdu: Open Foundation Models for Learning and Teaching
A UI made in Pyside6 to make training LoRA/LoCon and other LoRA type models in sd-scripts easy
This project converts the API of Anthropic's Claude model to the OpenAI Chat API format.
a security scanner for custom LLM applications
Dream 7B, a large diffusion language model
The repository host gives no description.
[ICML'26 & COLM'26] Agent0 Series: Self-Evolving Agents from Zero Data
An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Extract structured data from documents quickly and accurately.
Understanding R1-Zero-Like Training: A Critical Perspective
This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.
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。
The repository host gives no description.
TrustRAG:The RAG Framework within Reliable input,Trusted output
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'
This repository allows reproduction of Poetiq's record-breaking submission to the ARC-AGI-1 and ARC-AGI-2 benchmarks.
HOTA (and other) evaluation metrics for Multi-Object Tracking (MOT).