KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.
🚀 Less chaos. More flow.
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro, OpenAI, Claude, and custom providers. Supports OpenAI-compatible API, Claude API, Gemini protocol conversion, GPT, Grok Build, Claude Opus, Gemini Pro, Kimi, MiniMax, provider pools, smart routing, and automatic failover.
- aicoding
- free
- antigravity
- codex
Desktop application of new Bing's AI-powered chat (Windows, macOS and Linux)
Real-time Claude Code usage monitor with predictions and warnings
World's first open-source enterprise world model.
TypeChat is a library that makes it easy to build natural language interfaces using types.
- ai
- llm
- natural-language
- types
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
System prompt builder. Assembles agent identity from workspace config and spark.toml. Part of Unicity AOS.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Use your locally running AI models to assist you in your web browsing
- chat-application
- chrome-extension
- open-source
- localllm
A collection of libraries to optimise AI model performances
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
Open source inference engine that tunes its kernels on your hardware to find the fastest way to run each model. 2x faster than Ollama. Works on Apple Silicon, NVIDIA, AMD, Intel, or just a CPU.
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Fast, flexible LLM inference
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
TranslatedSelf-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows. Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
Providing a free OpenAI GPT-4 API ! This is a replication project for the typescript version of xtekky/gpt4free
Open Source LLM Gateway 🦚
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.