Pinned Repositories
A2AServer
Open-source project showcasing how single or multiple AI Agents interact with MCP in real-world tasks. Includes both frontend and backend implementations.
AlphaMix
强化学习进行量化金融
LangGraphA2A
LangGraph+A2A+MCP 实现的Agent RAG
MixText
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
MultiAgentPPT
MultiAgentPPT 是一个集成了 A2A（Agent2Agent）+ MCP（Model Context Protocol）+ ADK（Agent Development Kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制
NLP
NLP 相关文件
OpenNRE
An Open-Source Package for Neural Relation Extraction (NRE)
RLTrainPPT
使用强化学习训练PPT的Agent
TrainPPTAgent
模版式PPT，可以生成套用模版的PPT
WriterAgent
写综述，写教案，写文章，写小说等都可以用的Agent撰写
johnson7788's Repositories
johnson7788/livekitrealtime
实时AI
johnson7788/agents
Build real-time multimodal AI applications 🤖🎙️📹
johnson7788/ClearerVoice-Studio
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
johnson7788/CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
johnson7788/crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
johnson7788/deep-searcher
Deep Research Alternative to Reasoning About Private Data
johnson7788/freeshare
Android share file By HTTP
johnson7788/gemini2_APP
johnson7788/hallo2
Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
johnson7788/johnson7788.github.io
个人主页
johnson7788/LightRAG
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
johnson7788/LiveTalking
Real time interactive streaming digital human
johnson7788/LocalMCPManus
johnson7788/luminate
Luminate - an interactive system that enables structured generation and exploration of LLM outputs
johnson7788/mahilo
mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent systems that can each interact with humans while sharing relevant context internally.
johnson7788/MimicTalk
MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes; NeurIPS 2024; Official code
johnson7788/MiniMates
The fastest digital human algorithm, now on your desktop.
johnson7788/multimodal-live-api-web-console
A react-based starter app for using the Multimodal Live API over websockets with Gemini
johnson7788/Open-LLM-VTuber
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
johnson7788/openai-realtime-console
React app for inspecting, building and debugging with the Realtime API
johnson7788/OpenManus
No fortress, purely open ground. OpenManus is Coming.
johnson7788/openpod
johnson7788/phidata
Build AI Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.
johnson7788/pipecat
Open Source framework for voice and multimodal conversational AI
johnson7788/podcastfy
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI
johnson7788/praise-me
Praise Me everyday
johnson7788/sentimentapp
情感分析app
johnson7788/Spark-TTS
Spark-TTS Inference Code
johnson7788/TopicGPT
TopicGPT allows to integrate the benefits of LLMs into Topic Modelling
johnson7788/VideoChat
实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.