A RAG LLM co-pilot for browsing the web, powered by local LLMs
Repository Index
103,113 visible repositories in the index
769–792 of 1,321 · Most stars
DSH Plugin Radar — open-source ecosystem radar for DeepSeek Harness plugins: continuous discovery (21k+ candidates), k8s runtime validation (13k+ tests), 15-min snapshots; the catalog is a generated artifact — 开源 DSH 插件生态雷达:持续发现 2.1 万+ 候选、k8s 运行级实测 1.3 万+、15 分钟快照;插件目录为自动生成的产物
- dsh-plugin
- agent-plugins
- deepseek-harness
- dsh
Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.
- agent-rl
- dapo
- gspo
- opd
OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.
- chineseocr
- ocr
- ocr-pytorch
- scene-text-detection
OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)
A conversational Q&A agent configuration system, self-hosted deployment solutions, and a convenient all-in-one application SDK, allowing you to create intelligent Q&A bots for your GitHub repositories
Knowledge Graph,Question Answering System,基于知识图谱和向量检索的医疗诊断问答系统
Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.
A ChatGPT C# client for MacOS, Windows, Linux, Android, iOS and Browser. Powered by Avalonia UI framework.
DataComp for Language Models
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
- apple-silicon
- deep-learning
- huggingface
- large-language-models
Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.
- ai
- embeddings
- javascript
- llm
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
- decision-models
- jev
- laya
- local-inference
Knowledge is a tool for saving, searching, accessing, exploring and chatting with all of your favorite websites, documents and files.
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
Pre-trained ELMo Representations for Many Languages
- nlp
- elmo
- multilingual
The official Neovim plugin for Supermaven
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
- agent
- function-calling
- llm
- reinforcement-learning
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
- ai
- ai-infrastructure
- developer-tools
- llms
font vectors used for fontjoy.com
BrowserGym, a Gym environment for web task automation
Local AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
Traditional Mandarin LLMs for Taiwan
- langauge-model
- llm
- taiwan
- traditional-mandarin