Most Noteworthy AI Open Source Projects in 2025

A document understanding and semantic retrieval framework based on large language models, designed for enterprise knowledge bases and RAG applications.

A tool focused on AI translation, supporting one-click automatic translation of complex long texts such as RPG games, novels, subtitles, and documents.

A powerful framework for building, running, and evaluating autonomous agents based on open-source models, supporting automatic configuration generation, multi-modal tool integration, and in-depth research capabilities.

An end-to-end speech recognition toolkit based on ModelScope, supporting various functions such as speech recognition, voice activity detection, and punctuation restoration.

An AI knowledge curation system developed by Stanford University that can automatically research topics and generate Wikipedia-style long-form reports with citations.

A multi-agent platform based on large language models, providing developer-friendly message exchange mechanisms and distributed deployment capabilities.

An open-source web application builder powered by local AI agents, enabling rapid generation and deployment of professional-grade websites through natural language.

Microsoft's open-source, cutting-edge multi-speaker conversational text-to-speech AI model, supporting the generation of expressive dialogue audio of up to 90 minutes with up to 4 different speakers.

A CLI tool for analyzing token usage and costs in local JSONL files for Claude Code.

A revolutionary AI swarm coordination development platform that enables enterprise-grade development orchestration through intelligent agent clusters and Claude Code integration.

An AI-powered task management system designed for developers collaborating with Claude AI, seamlessly integrating with IDE environments like Cursor and Windsurf.

Open-source AI search engine powered by Firecrawl, providing intelligent answer generation with real-time citations, streaming responses, and live data.

An open-source AI agent workflow builder, providing a lightweight visual interface for quickly building and deploying LLM applications that connect various tools.

A powerful family of multimodal GUI automation agents supporting end-to-end operations on mobile devices and PC platforms.

Open-source ChatGPT alternative that runs 100% offline on your computer as an AI assistant

An open-source tool that quickly clones and rebuilds any website into a modern React application through AI conversation.

GLM-4.5V and GLM-4.1V series: Open-source vision-language models for diverse multimodal reasoning, enhancing visual reasoning capabilities through reinforcement learning.

A no-code AI data processing tool to build, enrich, and transform datasets using AI models.

Enhanced MCP interactive feedback server, supporting both Web UI and desktop application interfaces, enabling human-computer interaction feedback workflows in AI development.

Open-source intelligent agent browser with local AI automation and privacy protection.

An open-source deep research assistant that uses AI agents to automatically conduct in-depth research and generate comprehensive reports.

A one-stop AI agent development tool that provides a visual interface to simplify the entire process of agent creation, debugging, and deployment.

Alibaba's most advanced open-source AI programming model, designed specifically for intelligent agent programming tasks.

A multi-agent web search engine framework based on large language models, simulating human thinking processes to achieve deep AI search.

JD.com's open-source, end-to-end, production-grade general multi-agent framework, supporting out-of-the-box intelligent agent application development.