Discover AI agents built for Artificial Intelligence: Comprehensive directory of solutions with open-source code verified by AI agency professionals focused on the Artificial Intelligence sector.

Open-Source AI Agents for Artificial Intelligence

Cline is an open-source AI coding assistant integrated into Visual Studio Code, designed to automate various coding tasks. It features dual Plan/Act modes, allowing developers to strategize and execute coding actions efficiently. Cline can create and edit files, run terminal commands, and utilize the Model Context Protocol (MCP) to extend its capabilities. Operating directly within the IDE, it ensures a seamless coding experience, enhancing developer productivity by handling routine tasks and providing intelligent code assistance.

Cline

cline

An open-source AI coding assistant for VS Code, automating coding tasks with Plan/Act modes and terminal execution.

Codename Goose is an open-source AI agent developed by Block's Open Source Program Office, designed to automate intricate engineering tasks directly on your machine. It extends beyond mere code suggestions by autonomously building projects, writing and executing code, debugging, orchestrating workflows, and interacting with external APIs. Goose operates locally, ensuring data privacy and security, and is highly extensible, allowing integration with various large language models (LLMs) and tools through the Model Context Protocol (MCP). This flexibility enables developers to customize Goose to their specific workflows, thereby enhancing productivity and innovation.

Codename Goose

codename-goose

An open-source, on-machine AI agent automating complex engineering tasks to enhance developer productivity.

L2MAC (Large Language Model Automatic Computer) is an AI framework designed to generate extensive outputs, such as entire codebases or lengthy texts, from a single prompt. It employs a multi-agent system where each agent executes a portion of the task, effectively bypassing the fixed context window constraints of traditional LLMs. This approach allows L2MAC to produce coherent and large-scale outputs, significantly enhancing the capabilities of AI in software development and content creation.

L2MAC

l2mac

An AI framework enabling large-scale code generation by overcoming LLM context limitations.

GPTDiscord is an all-in-one, open-source GPT integration for Discord, developed by Kav-K. It enables ChatGPT-style conversations, image generation, AI-based moderation, custom knowledge bases, and YouTube summarization within Discord servers. The bot supports multi-modal interactions, allowing users to engage in rich, AI-enhanced dialogues and automate various tasks, enhancing the overall user experience on Discord.

GPTDiscord

gptdiscord

A comprehensive GPT-3 interface for Discord, offering ChatGPT-style conversations, image generation, AI moderation, and more.

DemoGPT is an open-source initiative that automates the creation of Large Language Model (LLM)-based applications. Leveraging GPT, it translates user instructions into LangChain code, which is then rendered as interactive Streamlit applications. The process involves planning, task creation, code snippet generation, and final code assembly, ensuring a seamless transition from concept to functional application. DemoGPT's flexibility allows it to utilize any LLM model meeting specific performance criteria, keeping it at the forefront of AI application development.

DemoGPT

demogpt

An open-source tool that transforms user instructions into interactive Streamlit applications using GPT.

Bolt.diy is an open-source platform that allows developers to prompt, run, edit, and deploy full-stack web applications using any Large Language Model (LLM) of their choice. It supports integration with multiple LLMs, including OpenAI, Anthropic, Ollama, OpenRouter, Gemini, LMStudio, Mistral, xAI, HuggingFace, DeepSeek, and Groq models. The platform is designed to be easily extensible, enabling users to incorporate additional models as needed. Bolt.diy provides a comprehensive environment for AI-assisted coding, facilitating the development of web applications directly in the browser.

Bolt.diy

bolt-diy

Open-source platform enabling AI-powered full-stack web development using any LLM.

LangMem is a software development kit (SDK) designed to enhance AI agents by integrating long-term memory capabilities. It allows agents to extract important information from interactions, optimize behavior through prompt refinement, and maintain knowledge over time. Compatible with various storage systems and natively integrating with LangGraph's storage layer, LangMem enables continuous improvement, personalized responses, and consistent behavior across sessions.

LangMem

langmem

An SDK enabling AI agents to learn and adapt through long-term memory integration.

assistant-ui is an open-source TypeScript/React library designed to help developers seamlessly incorporate AI chat interfaces into their applications. It offers customizable components that handle essential chat functionalities such as auto-scrolling, accessibility, and real-time updates. Inspired by libraries like shadcn/ui and cmdk, assistant-ui provides primitive components that can be fully tailored to specific needs. The library also supports integrations with popular AI tools and frameworks, including LangGraph and Vercel AI SDK, facilitating the development of stateful conversational AI agents. By leveraging assistant-ui, developers can create intuitive and interactive AI chat experiences within their React applications.

assistant-ui

An open-source TypeScript/React library enabling developers to integrate AI chat interfaces into their applications.

TensorFlow is an end-to-end open-source platform for machine learning developed by the Google Brain Team. It offers a comprehensive ecosystem of tools, libraries, and community resources that enable researchers and developers to build and deploy machine learning-powered applications efficiently. TensorFlow supports various programming languages, including Python, C++, and JavaScript, and is compatible with multiple platforms such as Linux, macOS, Windows, Android, and JavaScript. Since its initial release in 2015, TensorFlow has become one of the most widely adopted deep learning frameworks, facilitating tasks ranging from research prototyping to production deployment.

TensorFlow

tensorflow

An open-source machine learning platform developed by Google for building and deploying ML models.

ToRA, developed by researchers from Tsinghua University and Microsoft, is a series of Tool-integrated Reasoning Agents aimed at addressing challenging mathematical problems. By seamlessly combining natural language reasoning with external computational tools such as computation libraries and symbolic solvers, ToRA enhances the analytical capabilities of AI systems. This integration allows ToRA to effectively tackle complex mathematical reasoning tasks, outperforming existing open-source models on multiple datasets. Notably, ToRA-Code-34B is the first open-source model to achieve over 50% accuracy on the MATH dataset, surpassing GPT-4's Chain-of-Thought results.

ToRA

tora

A tool-integrated AI agent designed to solve complex mathematical problems by interacting with external tools.

Fleek is an open-source platform that streamlines the creation and deployment of autonomous applications and AI agents. It offers a verifiable, auto-scalable cloud environment, enabling developers to launch AI agents with minimal effort. With features like one-click deployments and pre-built templates, Fleek simplifies the process of integrating AI functionalities into various applications. The platform supports seamless interaction with on-chain environments, allowing AI agents to perform blockchain-specific tasks and respond intelligently to user requests.

Fleek

fleek

A platform for building and deploying autonomous apps and AI agents on an open-source, auto-scalable cloud.

Screenpipe is an open-source platform designed to continuously capture screen and audio activities on user devices, storing data locally to ensure privacy. Built with Rust for reliability, it provides developers with APIs to build context-aware AI applications that utilize comprehensive desktop activity data. Screenpipe supports cross-platform functionality, operating on Windows, macOS, and Linux systems. It offers a plugin system, allowing developers to create and deploy Next.js applications directly to the desktop environment, enhancing productivity and enabling the development of AI assistants with full context awareness.

Screenpipe

screenpipe

An open-source platform enabling 24/7 local recording of screen and audio activities for AI application development.

Open-Source AI Agents for "Artificial Intelligence" Industry