Stars
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost…
将 Qwen3-ASR 的 LLM 部分导出为 GGUF，用 llama.cpp 进行加速推理。后者支持 Vulkan 和 Cuda 加速。
An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.
A Python-based Beamforming Simulator with a PyQt5 GUI for visualizing and analyzing antenna array patterns. Adjust parameters like the number of antennas, distance, delay, and frequency to generate…
Open Data Platform for analysts, quants and AI agents.
TradingAgents: Multi-Agents LLM Financial Trading Framework
A simple screen parsing tool towards pure vision based GUI agent
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Convert PDF to markdown + JSON quickly with high accuracy
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
The open source platform for AI-native application development.
基于企微gpt知识库的bot机器人，能够自动回复企业微信中收到的消息。这个机器人能够处理私聊和群聊，还可以记住与用户的聊天内容，从而做出更加贴合上下文的回应。此外，您还可以设置白名单来控制机器人与哪些用户或群组交互。
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.
Port of OpenAI's Whisper model in C/C++
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
EchoPal 是一个创新的开源项目，旨在开发一款集成了录音、摄像头和头戴式耳机功能的智能可穿戴设备。这款设备不仅能够记录声音和图像，还能实时处理并回应用户的需求，成为您的日常生活和工作的智能伴侣。
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Noise supression using deep filtering