拼好RAG:手搓并融合了GraphRAG、LightRAG、Neo4j-llm-graph-builder进行知识图谱构建以及搜索;整合DeepSearch技术实现私域RAG的推理;自制针对GraphRAG的评估框架| Integrate GraphRAG, LightRAG, and Neo4j-llm-graph-builder for knowledge graph construction and search. Combine DeepSearch for private RAG reasoning. Create a custom evaluation framework for GraphRAG.
- deepresearch
- deepsearch
- evaluation
- graphrag
🤖Self-Modifying Framework from the Future 🔮 World's First AMS
No-code multi-agent framework to build LLM Agents, workflows and applications with your data
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
- community-detection
- graph-clustering
- deepwalk
- networkx
AI code-writing assistant that understands data content
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
Use Claude Code's autonomous agent loop with DeepSeek V4 Pro, OpenRouter, or any Anthropic-compatible backend. Same UX, 17x cheaper.
chat with private and local large language models
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
Lumina-T2X is a unified framework for Text to Any Modality Generation
Run a 1-billion parameter LLM on a $10 board with 256MB RAM
A lean, self-hosted AI agent that everyone can use. Each person gets an assistant with its own private computer, their files, skills, app connections and scheduled jobs.
- chatbot
- ai-chatbot-framework
- ai-chatbot
- conversational-ai
Your Automatic Prompt Engineering Assistant for GenAI Applications
- ai
- prompt
- llm
- ai-experiments
Extract structured data and insights from documents using LLMs and decision models
A colab gradio web UI for running Large Language Models
- colab
- colab-notebook
- colaboratory
- gradio
An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
AICI: Prompts as (Wasm) Programs
:cloud: :rocket: :bar_chart: :chart_with_upwards_trend: Evaluating state of the art in AI
Mezon is a new way to communicate with your team. It's faster, better organized, better for WFH.
- bot-framework
- chat
- chat-application
- communication
🤖 Create agentic apps in a second with your prompts. Everything you need to create an LLM Agent - tools, prompts, frameworks, and models - all in one place.
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Train your Agent model via our easy and efficient framework
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
A highly-customizable web-based client for Azure Bot Services.
- bot-framework
- adaptive-cards
- azure-bot-services
- chat