AI code editor with an agent, Tab completion, cloud agents and automated code review, from Anysphere in San Francisco.
Coding agents: AI tools compared (October 2026)
How results are ranked: How we review
Results
Autonomous coding agent from Cognition that delivers finished pull requests, with a desktop editor (formerly Windsurf), CLI and code review.
Agentic coding tool from Anthropic for terminal, IDE, desktop and browser that reads and edits code, runs commands and opens pull requests.
AI coding assistant from GitHub with code suggestions in many IDEs, chat, code review and a cloud agent that prepares pull requests.
Coding agent from JetBrains for the IDE, terminal, GitHub Actions and GitLab CI, with bring-your-own-key for more than ten models.
Open-source zero-code platform from OpenBMB in which several AI agents work together on software and other tasks.
Open-source MCP toolkit from Oraios AI that gives coding agents semantic code retrieval and symbol-level editing.
Benchmark that tests whether AI systems resolve real GitHub issues, with Verified, Lite, Multimodal, Multilingual and Bash Only boards.
Open source AI agent from Google for the terminal with Gemini models, Google Search grounding, file access, shell commands and MCP.
Open source terminal coding agent from Mistral AI, with Mistral models, other compatible providers or local models offline.
Open source coding agent from China's Qwen team for terminal, editor, desktop and chat, with Qwen, third-party or local models.
Princeton and Stanford paper on agent-computer interfaces that let language models fix GitHub issues autonomously.
Open source coding agent as a VS Code extension, CLI and SDK, where you pay only for model usage.
Open source coding agent from OpenAI for the terminal, usable with a ChatGPT plan or API key, plus IDE extension and cloud.
ICLR 2025 paper on OpenHands (formerly OpenDevin), an open platform for AI agents that write code, run commands and browse the web.
Last updated:














