jidechao
Follow
Stars
一个基于 OpenAI Agents SDK 的智能助手系统，实现了 ReACT 推理模式（Reasoning and Acting），支持多轮工具调用、对话历史管理、流式响应以及 MCP 工具集成。
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes. Features Docker deployment and management UI, requirin…
[NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
A simple, secure MCP-to-OpenAPI proxy server
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
LangChain4j is an open-source Java library that simplifies the integration of LLMs into Java applications through a unified API, providing access to popular LLMs and vector databases. It makes impl…
"Your Fully-Automated Personal AI Assistant"
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Pseudo Streaming SenseVoice with Hotwords
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 ba…
A powerful framework for building realtime voice AI agents 🤖🎙️📹
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
[ICLR 2025] The official implementation of paper "ToolGen: Unified Tool Retrieval and Calling via Generation"
[ICLR 2025] The First Multimodal Seach Engine Pipeline and Benchmark for LMMs
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts…
Docs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%