Best open source AI tools

Portfolioly is a free AI-powered tool that instantly creates stunning, professional portfolios from your LinkedIn, GitHub, or resume. It features one-click deployment, a unique interactive chat mode, and is fully open-source for complete customization.

Metrics Help is an open-source web tool for machine learning practitioners. It functions as a comprehensive guide and an interactive analyzer for ML training metrics. Users can paste training logs to get instant explanations for key metrics like accuracy, loss, and perplexity, aiding in model performance analysis and debugging.

Zimage is a free, open-source AI image generator that delivers photorealistic quality on standard consumer hardware. Its efficient 6B parameter model excels at rendering accurate bilingual text (English and Chinese). With its unique S3-DiT architecture, it offers superior prompt adherence and high-speed generation, making advanced AI art accessible to everyone.

Agenta is an open-source LLMOps platform designed for teams to build reliable LLM applications. It integrates prompt management, systematic evaluation, and observability into a single, collaborative workflow, helping developers, product managers, and domain experts move from scattered processes to structured development.

Presenton is an open-source AI presentation generator designed for developers and teams. It allows for self-hosting, API integration, and creating pixel-perfect, on-brand presentations from custom templates, ensuring complete control, privacy, and no vendor lock-in.

Dank is a JavaScript-native, open-source framework for orchestrating and deploying containerized AI agents. It enables developers to build, manage, and scale multiple AI agents as microservices across any cloud infrastructure, simplifying complex AI deployments with Docker-native architecture and real-time monitoring.

Voice AI Space is a comprehensive online hub dedicated to voice AI technology, offering a curated directory of tools, the latest news, in-depth knowledge resources, job opportunities, and industry events. It serves as a central guide for developers, entrepreneurs, and enthusiasts navigating the rapidly evolving voice tech landscape.

PolyGPT is a free and open-source desktop application that allows users to chat with multiple AI models, including ChatGPT, Gemini, and Claude, simultaneously. It eliminates tab-switching by enabling users to type a prompt once and receive side-by-side, real-time responses from various AIs for easy comparison and enhanced productivity.

Layrr is a free and open-source visual editor that allows developers and designers to create and edit real code directly. It combines the intuitive drag-and-drop interface of design tools like Figma with the flexibility and ownership of traditional coding, supporting any tech stack and leveraging AI for design-to-code conversion and natural language interface generation.

Shinkai is an open-source, no-code platform that empowers users to create, manage, and deploy powerful AI agents locally. It supports both cloud and local AI models, offers integrated crypto functionalities, and enables secure, decentralized peer-to-peer interactions, making advanced AI automation accessible to everyone.

Models by Hathora offers a curated catalog of low-latency ASR, TTS, and LLM models optimized for voice AI and real-time applications. Developers can explore, test, and deploy production-ready models quickly, featuring interactive sandboxes and direct API access for seamless integration into voice agents and other applications.

Skald is an open-source RAG API designed for developers to quickly build AI agents without the complexity of managing RAG infrastructure. It simplifies knowledge storage, context management, and semantic search, offering a powerful solution for integrating long-term memory into AI applications.

LLM Models is a comprehensive online directory and comparison platform for large language models and foundation models. It provides detailed technical specifications, benchmark performance, and feature comparisons to help developers, researchers, and businesses select the most suitable AI models for their needs.

FRAI is a comprehensive, free-forever AI compliance platform designed to simplify adherence to global AI regulations like the EU AI Act and ISO 42001. It automates website scanning for AI usage and tests chatbots for bias, safety, and compliance, providing continuous monitoring and audit-ready reports.

Skillgraph is an experimental, open-source AI agent framework designed to build robust, controllable, and cost-effective AI agents. It replaces traditional low-level tool-calling with sophisticated 'skills' that manage complex tasks, multi-turn workflows, and internal logic, offering superior control and efficiency for developers.

An open-source, self-hosted platform for discovering, deploying, and managing specialized AI agents on your own infrastructure, ensuring complete data privacy and control.

Arcade is an AI tool-calling platform for developers, enabling AI agents to securely perform actions on behalf of users. It connects AI to services like Gmail, Slack, and APIs through pre-built connectors and a custom SDK, handling complex authentication (OAuth) automatically. This allows developers to build assistants that go beyond chat to execute real-world tasks.

NocoBase is an open-source, self-hosted no-code and low-code development platform. It empowers users to build custom business applications like CRMs and internal tools with high flexibility, granular permissions, and automated workflows, ensuring data security through on-premises deployment.

Helicone is an open-source platform offering an AI Gateway and LLM Observability for developers. It helps build reliable AI applications by providing tools to route, monitor, debug, and analyze LLM usage. Key features include a unified API for 100+ models, intelligent caching, rate limiting, prompt management, and detailed performance analytics.

Mcpwhiz is a free, open-source developer tool that instantly converts API specifications like Swagger/OpenAPI, Postman Collections, and GraphQL into production-ready Model Context Protocol (MCP) servers. It automates code generation in multiple languages, including TypeScript and Python, allowing developers to build context-aware applications with ease.

Agentary is an open-source JavaScript SDK for developers to build and run autonomous AI agents directly in the browser. It leverages WebGPU and WebAssembly for on-device execution, ensuring complete data privacy, zero latency, and offline functionality. This serverless framework allows for the creation of fast, private, and intelligent web applications without cloud dependencies or API costs.

Deepgrok is an open-source search engine and knowledge base designed to help users find truthful and accurate information on any topic. It emphasizes deep inquiry and factual discovery.

Videoasprompt is an AI-powered tool by ByteDance that generates videos using a reference video or image as a prompt. It animates a source image with the same semantics (concept, style, motion, camera movement) as the reference video, enabling zero-shot, high-quality video creation.

A definitive guide and benchmarking platform for agentic automation. It provides developers with interactive market maps, performance analysis, and reports on tools for web browsing and computer control, helping them build reliable AI agents.