GitHub's AI pair-programmer — inline completions, chat, and the new Agent mode that ships PRs.
CodeTool useMemory
Demo · hover to play
27 agents · capability hub
AI agents with code execution2026
Agents that write, run, and iterate on code in a sandboxed environment. Required for data work, scripting, and any task that ends in "and verify it actually works".
Want the technical definition? Read the code execution glossary entry →
The 27 agents that ship code execution
Codeium's AI editor — Cascade agent flows alongside in-line completion and chat.
CodeTool useMemoryBrowserDemo · hover to playBackground agent that drives the Cursor editor across multi-file changes.
CodeTool useMemoryDemo · hover to playVercel's generative UI agent — design and ship React components from natural language.
CodeTool useVisionDemo · hover to playAutonomous AI software engineer that ships PRs end-to-end.
CodeTool useBrowserMemoryDemo · hover to playMicrosoft's open-source multi-agent framework — orchestrate conversations between specialised agents.
Multi-agentTool useCodeMemory
Anthropic's terminal agent — composable, scriptable, and built around Claude's tool-use loop.
CodeTool useMemoryDemo · hover to playVibe-coding builder for non-engineers — prompt a full-stack app and ship it to a live URL in minutes.
CodeTool useVisionDemo · hover to playStackBlitz's in-browser AI builder — generates and deploys real Node.js apps from a single prompt.
CodeTool useVisionDemo · hover to playGeneral-purpose agent that turns a single prompt into a finished deliverable.
BrowserTool useCodeMemoryGet AGENTS20codeAGENTS20
Build and ship full applications from a single prompt — runs in the Replit cloud.
CodeTool useBrowserMemoryDemo · hover to playAI dev tool that builds entire production apps from spec — formerly GPT Pilot, open-source roots.
CodeTool useMemoryDemo · hover to playAWS's enterprise AI agent — coding assistant, business chat, and customizable Q apps grounded in your AWS data.
CodeTool useRAGMemoryDemo · hover to playAutonomous coding agent grounded in your whole codebase — multi-file edits with deep context.
CodeTool useMemoryRAG
Privacy-first AI coding assistant — runs on your own infrastructure or in a private cloud.
CodeTool useMemoryDemo · hover to playOSS terminal coding assistant — pair-programs, edits in place, commits as you go.
CodeTool use
Open-source autonomous coding agent that lives in your IDE.
CodeTool useBrowserDemo · hover to playCode intelligence agent for enterprise — answers questions about your code, navigates large monorepos.
CodeTool useRAGMemoryDemo · hover to playByteDance's AI coding IDE with autonomous Builder mode — multi-file scaffolding from a single prompt.
CodeTool useMemory
Open-source coding agent for VS Code and JetBrains — bring your own model, customize every prompt.
CodeTool useMemoryDemo · hover to playOpenAI’s open-source terminal agent for refactors, audits and migrations.
CodeTool useDemo · hover to playGitHub's natural-language micro-app builder — describe a personal app, get a deployed working version.
CodeTool useMemory
Autonomous AI engineer trained on long contexts — handles hour-long coding sessions without losing track.
CodeTool useMemory
GitHub-native agent that turns issues into reviewed pull requests.
CodeTool useMemoryDemo · hover to playAutonomous "Droid" agent for end-to-end engineering with native AGENTS.md support.
CodeTool useMemoryMulti-agent
Open-source autonomous coding agent that plans, codes, and ships across full repos.
CodeTool useBrowserMulti-agent
EU-sovereign agentic assistant on Mistral Medium 3.5 with parallel Work mode across SaaS.
CodeTool useMemoryRAG
Frequently asked
What is code execution in AI agents?+
An agent capability for writing and running code in a sandboxed environment — usually Python — to compute, transform data, or test hypotheses.
Which AI agents support code execution?+
27 agents in our index ship code execution. The list above is sorted by community interest; GitHub Copilot, Windsurf, Cursor Agent are the most-researched in 2026.
How do I evaluate code execution in an AI agent?+
Look for: (1) reliability across edge cases, not just demo videos; (2) how the agent recovers when code execution fails mid-task; (3) whether code execution is the default mode or an opt-in feature. Production-ready agents publish code execution benchmarks; demos and screenshots aren't enough.
Explore code execution further
Explore other capabilities