Programming Agents Agentic AI directory: Access intelligent solutions with open-source code verified by top AI agency partners and automation specialists.

Open-Source Agentic AI in "Programming Agents" Category

Codex CLI is an open-source, terminal-native AI coding assistant developed by OpenAI. Designed for developers who prefer working directly in the terminal, it integrates OpenAI's latest models (like o4-mini) to perform tasks such as reading, modifying, and executing code within a local environment. Codex CLI supports multimodal inputs, allowing users to pass text, screenshots, or diagrams to generate or edit code accordingly. It offers three distinct approval modes—Suggest, Auto Edit, and Full Auto—providing flexibility in how autonomous the agent operates. The tool emphasizes security by running in a sandboxed, network-disabled environment and ensures that your source code remains on your machine unless explicitly shared. With zero-setup installation and compatibility with macOS, Linux, and experimental support for Windows via WSL, Codex CLI aims to streamline the development workflow by bringing powerful AI capabilities directly to the command line.

Codex CLI

codex-cli

Open-source terminal-based AI coding assistant that reads, writes, and executes code locally with multimodal input support.

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.

OpenDevin is an open-source project that aims to replicate and enhance the capabilities of Devin, an autonomous AI software engineer. The platform enables the development of AI agents that can perform complex software engineering tasks, such as writing code, running commands, and browsing the web, by leveraging large language models (LLMs). OpenDevin provides a comprehensive suite of tools, including a chat interface, command terminal, workflow planner, code editor, and integrated browser, to facilitate seamless collaboration between human developers and AI agents. The project is community-driven, encouraging contributions from developers, researchers, and AI enthusiasts to advance the field of AI-assisted software development.

OpenDevin

opendevin

An open-source platform for developing AI-powered autonomous software engineering agents capable of executing complex tasks.

Sweep AI is an open-source tool designed to function as an AI-powered junior developer, automating the transformation of bug reports and feature requests into actionable code changes. By integrating with GitHub repositories, Sweep AI reads the codebase, plans necessary modifications, and generates pull requests with the proposed code alterations. This process enhances development efficiency by reducing manual effort in addressing issues and implementing new features. Sweep AI supports multiple programming languages, including Python, JavaScript, Rust, Go, Java, C#, and C++, and offers both hosted and self-hosted deployment options to cater to various organizational needs.

Sweep AI

sweep-ai

An AI-powered junior developer that transforms bug reports and feature requests into code changes, streamlining the software development process.

OpenHands, formerly known as OpenDevin, is an open-source platform that facilitates the creation and deployment of AI agents designed to emulate human software developers. These agents can modify code, execute commands, browse the web, and interact with APIs, thereby automating various aspects of the software development lifecycle. OpenHands aims to enhance development efficiency by allowing AI agents to perform tasks such as code generation, debugging, and testing, effectively acting as autonomous coding assistants. The platform integrates with existing development tools and workflows, providing a seamless experience for developers seeking to leverage AI in their projects.

OpenHands

openhands

An open-source platform for AI-powered software development agents capable of performing tasks akin to human developers.

Mentat is an open-source AI-powered coding assistant designed to enhance developer productivity by integrating directly with the command line interface. Leveraging models like GPT-4, Mentat assists with a range of coding tasks, including understanding new codebases, adding features, and refactoring existing code. Unlike other tools, Mentat coordinates edits across multiple locations and files, providing contextual assistance without the need for manual copy-pasting. It supports various programming languages and integrates seamlessly with version control systems like Git, streamlining the development workflow.

Mentat

mentat

An open-source AI coding assistant that integrates with your command line to assist with various coding tasks across multiple files.

ReactAgent is an experimental open-source tool that leverages the GPT-4 language model to autonomously generate and compose React components based on user-provided stories. Built with React, TailwindCSS, TypeScript, Radix UI, Shadcn UI, and the OpenAI API, it aims to streamline the development process by translating user requirements into functional React components. Adhering to atomic design principles, ReactAgent facilitates the creation of modular and reusable components, enhancing efficiency in web development projects.

ReactAgent

reactagent

An open-source autonomous agent utilizing GPT-4 to generate and compose React components from user stories.

Devika AI is an advanced open-source AI software engineer designed to interpret complex human instructions, decompose them into actionable steps, perform relevant research, and produce code to achieve defined goals. Utilizing large language models such as Claude 3, GPT-4, GPT-3.5, and local LLMs via Ollama, Devika AI offers robust planning and reasoning capabilities. It serves as a competitive alternative to Devin by Cognition AI, aiming to democratize intelligent software development tools. Key features include contextual keyword extraction, seamless web browsing for information gathering, multilingual code generation, and a conversational interface for natural language interactions.

Devika AI

devika-ai

An open-source AI software engineer capable of understanding high-level human instructions, conducting research, and generating code to accomplish specified objectives.

Bolt.new is an innovative platform that combines artificial intelligence with an in-browser development environment, allowing users to build, edit, run, and deploy full-stack web applications seamlessly. Utilizing StackBlitz’s WebContainers technology, it provides full control over the development environment, including the filesystem, Node.js server, package manager, terminal, and browser console. This integration empowers AI agents to manage the entire application lifecycle—from creation to deployment—directly within the browser. Bolt.new supports various JavaScript frameworks and libraries, such as Vite and Next.js, enabling developers, project managers, and designers to create production-grade applications without the need for local environment setup.

Bolt.new

bolt-new

An AI-powered web development agent enabling users to prompt, run, edit, and deploy full-stack applications directly from their browser without local setup.

Micro Agent is an open-source AI-driven tool developed by Builder.io, designed to automate the process of writing and refining code to meet predefined unit tests. By leveraging large language models (LLMs), Micro Agent generates code in languages such as JavaScript, TypeScript, and Python, iteratively modifying it until all test cases pass. This approach ensures that the produced code aligns with specified requirements, reducing the need for manual debugging and accelerating the development cycle. Micro Agent also integrates with design tools like Figma for visual matching, ensuring precise design-to-code conversion.

Micro Agent

micro-agent

An open-source AI tool that autonomously writes and refines code to pass specified unit tests, enhancing development efficiency.

MiniAGI is a lightweight autonomous agent that operates with GPT-3.5-Turbo or GPT-4 models. It's built around a carefully crafted prompt system and includes a basic set of tools, allowing it to perform tasks while showing its reasoning process (chain-of-thoughts).

The system features short-term memory capabilities with summarization to maintain context, and it can engage in inner monologue – meaning it can "think through" problems internally. It also has self-criticism abilities, allowing it to evaluate and potentially improve its own responses and decisions.

MiniAGI

miniagi

A lightweight AI agent designed to perform basic tasks using GPT-3.5 and GPT-4.

Codel is an open-source AI agent that executes complex tasks in a sandboxed Docker environment, suitable for developers looking for a **self-sufficient agent** that can handle technical workflows. Codel operates by detecting next steps independently, whether it’s web scraping, data processing, or editing files. Codel’s unique ability to operate within Docker allows it to handle projects end-to-end with full autonomy, making it an ideal solution for developers who need an agent to manage tasks in a secure, isolated environment.

Codel

codel

An open-source, fully autonomous AI agent designed for complex projects within a Docker environment.

Open-Source Agentic AI Category "Programming Agents"