AI coding assistants and autonomous coding agents
SWE-AF is an autonomous software engineering fleet platform using a multi-agent factory architecture. It orchestrates planner, coder, reviewer, and verifier agents to automate the full software engineering lifecycle from issue analysis to code fix, scoring 95/100 on benchmarks.
AI pair programming in your terminal. Collaborate with LLMs to edit code, manage Git, and refactor across multiple files with deep developer workflow integration.
An agentic orchestrator for parallel coding agents that plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and code reviews for complex development workflows.
gptme is a terminal-based AI agent equipped with local tools for writing code, using the terminal, and browsing the web to build persistent autonomous agents.
Fully local Manus AI alternative that autonomously browses the web, writes code, and interacts via voice, with no API costs
KiloCode is an all-in-one open-source coding agent platform for VS Code and JetBrains, integrating 200+ models with autonomous coding, debugging, and iteration capabilities.
SWE-agent takes a GitHub issue and automatically generates fixes using your LLM of choice, also applicable to cybersecurity auditing and competitive coding. NeurIPS 2024 paper.
Tabby is a self-hosted AI coding assistant supporting code completion, code generation, and enterprise-grade deployment, compatible with major IDEs.
Open-source extensible AI coding agent that goes beyond code suggestions — install, execute, edit, and test with any LLM.
Agent Skills is a curated collection of production-grade engineering skills for AI coding agents, maintained by Addy Osmani, providing battle-tested best practices and operational conventions.
Claude Code is an agentic coding tool by Anthropic that lives in your terminal, understands your codebase, and helps you code faster through natural language commands.
GPT Engineer is an AI tool that generates entire codebases based on natural language descriptions. Just describe what you want to build, the AI asks for clarification, and then builds it.
ByteRover CLI provides persistent structured memory for autonomous coding agents. It features context tree management, git-like version control, and cloud sync, compatible with Cursor, Claude Code, Windsurf, and 22+ coding agents via MCP integration.
Open-source agentic coding CLI by the Charm team, supporting multiple LLM backends for autonomous coding in the terminal
Cline is an autonomous coding agent in your IDE that can create/edit files, execute commands, use the browser, and more with your permission every step of the way.
Continue is an open-source AI code assistant extension for VS Code and JetBrains IDE. It can autocomplete code, refactor, and explain code, helping developers improve programming efficiency.
Dyad is a local AI app builder that lets users create and iterate on web applications through natural language conversations, supporting multiple LLM providers.
Python and JS/TS SDK for running AI-generated code in secure cloud sandboxes with Jupyter-style code interpretation
Agent Zero is a general-purpose AI agent framework supporting autonomous task planning, tool use, and code execution for building self-directed AI assistants.
A memory upgrade for coding agents. Provides persistent contextual memory for Claude Code, Codex, and other coding agents to improve long-task consistency.
Open-source agentic development environment (YC W26) that runs multiple coding agents in parallel with any LLM provider
Gemini CLI is a terminal-based AI agent tool from Google that supports code generation, file operations, and multi-turn conversations with a free usage tier.
Platform to experiment with AI Software Engineer — specify software in natural language, watch AI write and execute code, then iterate improvements
HumanLayer provides a human-in-the-loop layer for AI coding agents, enabling them to seek human approval and guidance when solving hard problems in complex codebases.
AI research automation agent by Andrej Karpathy that automatically runs nanochat training research experiments on a single GPU.
Claude Coder is an autonomous coding agent as a VSCode extension. It transforms mockups to code, auto-fixes lint errors, writes tests, and performs complex multi-file edits with an agent mode for autonomous task execution.
An open-source asynchronous coding agent by LangChain built on LangGraph, autonomously handling software engineering tasks including code generation, debugging, and file editing.
Context Mode is a context window optimization tool for AI coding agents that sandboxes tool output for 98% context reduction across 12 major platforms.
Multica is the open-source managed agents platform that turns coding agents into real teammates with task assignment, progress tracking, and compound skill accumulation.
Aide is a VSCode extension for AI-powered coding assistance, featuring one-click comments, code conversions, UI-to-code generation, and AI batch file processing.
An autonomous AI agent framework from NousResearch that supports multiple LLM backends and grows with user needs.
Codex CLI is OpenAI's open-source coding-agent command-line tool for code understanding, refactoring, generation, and terminal collaboration in developer workflows.
An open-source tool by OpenAI that turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
Powerful MCP toolkit for coding that provides semantic retrieval and editing capabilities, serving as an IDE for AI agents
Aider is an AI coding assistant that lets you pair program with LLMs in your terminal. It supports Git integration and can automatically commit code changes, perfect for developer pair programming.
Open source AI coding agent designed for large projects and real world tasks, providing terminal-based code generation with multi-step planning and file management.
Roo Code is an autonomous coding agent extension for VS Code and JetBrains that can create/edit files and run terminal commands directly in your editor.
Open-source web UI for Claude Code, Cursor CLI, and Codex enabling remote management of AI coding sessions and projects from mobile and web.
Skales is a local AI desktop agent for Windows, macOS, and Linux. It features an agent skills system (SKILL.md), autonomous coding (Codework), multi-agent team collaboration, and desktop automation with 15+ AI providers, requiring no Docker or terminal.
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp in a unified terminal interface
OpenCode is an open-source terminal coding agent that supports multiple LLM providers, offering AI-powered code generation and editing in the terminal.
stagewise is a purpose-built browser for developers with a coding agent integrated right in, enabling direct code interaction from the web interface.
Open-source agentic software engineer and Devin alternative with planning, reasoning, web browsing, and multi-model support
Code editor for the AI agents era that runs an army of Claude Code, Codex, and other coding agent instances in parallel
Void is an open-source AI code editor built on VS Code architecture, supporting Claude, GPT, and other models, delivering a Cursor-style intelligent coding experience.
Repomix packs your entire repository into a single AI-friendly file, perfect for feeding your codebase to LLMs like Claude, ChatGPT, and DeepSeek for analysis, review, or code generation.
Zed Agentic is Zed's open-source project for in-editor agent collaboration, focused on code understanding, editing suggestions, and enhanced developer workflows.