Loading...
Explore
Discover the best AI tools in one place
28 tools found
Vanna AI is an open-source Python-based RAG (Retrieval-Augmented Generation) framework engineered to generate high-accuracy SQL queries from plain English questions. Unlike general-purpose chatbots that frequently hallucinate non-existent database columns and tables, Vanna trains specifically on your database schema, table DDL, documentation, and historical query logs. When a business user or developer asks a natural language question, Vanna retrieves relevant schema definitions and validated SQL examples to construct an accurate, executable SQL query for PostgreSQL, Snowflake, BigQuery, MySQL, SQLite, or SQL Server. With over 12,000 GitHub stars, Vanna allows organizations to deploy self-hosted text-to-SQL agents inside Slack, Streamlit dashboards, or internal REST APIs without exposing private database records to third parties.
RAGFlow is an open-source enterprise RAG (Retrieval-Augmented Generation) engine based on deep document understanding and multimodal document parsing. Unlike naive RAG systems that slice documents into arbitrary character chunks—scrambling complex tables, footnotes, and multi-column layouts—RAGFlow preserves the original semantic structure of complex documents. Powered by DeepDoc computer vision models, RAGFlow extracts clean text, recognizes complex tables across multiple pages, identifies corporate hierarchies, and visually highlights exact source citations with bounding boxes inside PDF viewers. With self-hosted Docker deployment, low-code workflow orchestration, and native support for local and cloud LLMs, RAGFlow is widely adopted by enterprise organizations requiring zero hallucination in legal, financial, and technical document analysis.
Mem0 (formerly Embedchain) is a universal, persistent memory architecture designed to solve the critical context amnesia problem in modern AI applications. While foundational LLMs forget user preferences and past interactions the moment a session ends, Mem0 maintains a continuous, self-improving memory graph across user sessions, agents, and applications. With Mem0, developers can build personalized AI assistants, customer support agents, and autonomous workflow bots that remember user preferences, past project decisions, and communication styles over months and years. Mem0 operates as both an open-source self-hostable Python/TypeScript library and a managed cloud platform, providing sub-100ms vector search, episodic memory extraction, and automated memory consolidation without manual prompt engineering.
Unstructured is the leading enterprise ETL (Extract, Transform, Load) platform engineered to prepare messy, unstructured business documents for Retrieval-Augmented Generation (RAG) and LLM fine-tuning. Over 80% of enterprise data lives in complex formats like scanned PDFs, PowerPoint decks, Word files, HTML tables, and email threads that break standard text scrapers. Unstructured utilizes specialized computer vision and vision-language models to segment documents into structural semantic elements (titles, paragraphs, headers, embedded tables, and image captions) while preserving exact spatial and hierarchical context. Available as an open-source Python library and a high-throughput serverless cloud API, Unstructured integrates directly with LangChain, LlamaIndex, and major vector databases to power mission-critical enterprise knowledge retrieval.
Intervo AI is an open-source platform for building and deploying conversational AI agents. It provides tools for creating voice-enabled AI assistants that can handle complex interactions. Developers can customize and self-host their AI agent solutions.
Suna by Kortix is an open-source AI agent designed to handle real-world tasks autonomously. It can perform complex operations across various domains, acting as a digital employee.
Openwork is a local AI agent that helps automate your knowledge work tasks directly on your machine. It processes documents, manages workflows, and assists with complex information tasks without sending data to the cloud.
Intelligent Internet Agent is an open-source AI assistant designed to handle a wide range of tasks. It provides users with a versatile and customizable AI experience for everyday productivity and automation.
clawXiv is a free preprint archive dedicated to autonomous AI agent research. It provides a platform for researchers to share and discover cutting-edge work in the field of AI agents. The archive fosters open collaboration and rapid dissemination of agent-based research findings.
InitRunner enables developers to define and deploy AI agents using simple YAML configuration files. It streamlines the process of creating automated workflows directly from the command line. This tool is ideal for developers who prefer code-first approaches to AI automation.
DeerFlow is an open-source SuperAgent framework that can research, code, and create content autonomously. It orchestrates multiple AI agents to handle complex tasks from start to finish. Developers and researchers can extend and customize the framework for their specific needs.
Pillar is an open-source app copilot that transforms natural language requests into actionable tasks within applications. It bridges the gap between user intent and app functionality.
NemoClaw is an open-source platform for building and deploying enterprise-grade autonomous AI agents at scale. It provides tools for agent orchestration, memory management, and multi-agent collaboration. Designed for developers and enterprises needing robust agent infrastructure.
PaioClaw is a secure and user-friendly AI agent platform that allows users to deploy AI agents in seconds. It focuses on security and ease of use, making it accessible for both beginners and advanced users. The platform supports a wide range of automation and agent-based workflows.
socra is an AI problem-solving platform that helps teams document, track, and resolve issues systematically. It automates workflow creation and knowledge management. The tool aims to reduce repetitive problem-solving.
This tool provides a browser-based interface to run AutoGPT, allowing users to experiment with autonomous AI agents without local setup. It simplifies access to agent-based task automation.
Hermes Agent is an autonomous AI agent designed to learn from user interactions and adapt over time, providing personalized assistance for various tasks. It combines memory, learning capabilities, and autonomous decision-making to become more effective with continued use.
Dedalus Labs provides a Model Context Protocol gateway that enables seamless integration between large language models and external MCP servers. It acts as a universal bridge, allowing developers to connect any LLM to any MCP-compatible tool or data source without custom integration work. The platform handles authentication, routing, and protocol translation automatically.
Phidata is an open-source framework for building, orchestrating, and deploying AI agents with persistent memory and tool integration. It provides abstractions for creating agents that can reason over databases, use external APIs, and maintain context across long conversations. The framework supports both single-agent and multi-agent architectures.
Langflow is a low-code visual interface for designing and deploying AI agent chains and RAG pipelines. Users drag and drop components representing LLMs, data sources, and tools to create complex agent architectures. It integrates natively with LangChain and supports deployment as APIs or standalone applications.
E2B provides secure, sandboxed cloud execution environments where AI agents can run code, access files, and interact with tools without risking host systems. It offers SDKs in Python and JavaScript for spinning up isolated compute sandboxes in milliseconds. The platform is designed specifically for agent builders who need safe code execution capabilities.
AG2 (formerly AutoGen) is an open-source framework for building AI agent systems. It enables complex multi-agent conversations and task automation.
Semantic Kernel is an open-source SDK by Microsoft for building AI agents and orchestrating complex AI workflows. It supports multiple programming languages.
AutoGen is a framework developed by Microsoft for building multi-agent conversational systems. It enables multiple agents to collaborate and solve tasks through conversation.
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 and GPT-3.5 language models. It chains together LLM thoughts to autonomously achieve user-defined goals. Users can assign tasks and let the AI work through them independently.
The most popular framework for developing applications powered by large language models, including agents and RAG.
A cloud platform for fine-tuning and running the world's leading open-source AI models at scale.
A collaborative platform for the machine learning community to share and build models, datasets, and demo apps (Spaces). It serves as the primary repository for open-source AI.