Ten-record public-beta audit.

Whenever aider edits a file, it commits those changes with a descriptive commit message. This makes it easy to undo or review aider’s changes.
reasonably-inferred · https://aider.chat/docs/git.html

Aider takes special care before editing files that already have uncommitted changes (dirty files). Aider will first commit any preexisting changes with a descriptive commit message.
reasonably-inferred · https://aider.chat/docs/git.html

Gaps: reads repository, edits files, runs commands, opens pull requests, comments on issues or PRs, accesses secrets or environment variables, makes network/API calls, supports sandboxing, supports permission controls, supports enterprise administration, supports human approval controls, supports production deployment

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.
explicitly-supported · https://docs.anthropic.com/en/docs/claude-code/overview

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.
explicitly-supported · https://docs.anthropic.com/en/docs/claude-code/overview

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.
explicitly-supported · https://docs.anthropic.com/en/docs/claude-code/overview

Claude Code works directly with git. It stages changes, writes commit messages, creates branches, and opens pull requests.
explicitly-supported · https://docs.anthropic.com/en/docs/claude-code/overview

Gaps: comments on issues or PRs, accesses secrets or environment variables, makes network/API calls, supports sandboxing, supports permission controls, provides audit logging, supports enterprise administration, supports branch isolation, supports human approval controls, supports production deployment

AI coding assistant in your editor. Create files, run commands, browse the web, and use tools with human-in-the-loop approval.
explicitly-supported · https://docs.cline.bot/getting-started/overview

AI coding assistant in your editor. Create files, run commands, browse the web, and use tools with human-in-the-loop approval.
explicitly-supported · https://docs.cline.bot/getting-started/overview

AI coding assistant in your editor. Create files, run commands, browse the web, and use tools with human-in-the-loop approval.
explicitly-supported · https://docs.cline.bot/getting-started/overview

AI coding assistant in your editor. Create files, run commands, browse the web, and use tools with human-in-the-loop approval.
explicitly-supported · https://docs.cline.bot/getting-started/overview

Gaps: reads repository, opens pull requests, comments on issues or PRs, accesses secrets or environment variables, supports sandboxing, supports permission controls, provides audit logging, supports enterprise administration, supports branch isolation, supports production deployment

Inspect diffs, run checks, and catch problems before you merge
reasonably-inferred · https://docs.cursor.com/background-agent

Inspect diffs, run checks, and catch problems before you merge
reasonably-inferred · https://docs.cursor.com/background-agent

Inspect diffs, run checks, and catch problems before you merge
reasonably-inferred · https://docs.cursor.com/background-agent

Inspect diffs, run checks, and catch problems before you merge
reasonably-inferred · https://docs.cursor.com/background-agent

Gaps: runs commands, opens pull requests, comments on issues or PRs, accesses secrets or environment variables, makes network/API calls, supports sandboxing, supports permission controls, provides audit logging, supports enterprise administration, supports production deployment

Devin's terminal, where you can watch commands being executed and view output logs. You can also copy the shell output for debugging purposes. To run commands directly, use the IDE's shell.
explicitly-supported · https://docs.devin.ai/get-started/devin-intro

Devin's embedded code editor equipped with all the IDE tools and shortcuts you're familiar with. Follow Devin's work in real time and take over to run commands, make direct code edits or test Devin's code.
explicitly-supported · https://docs.devin.ai/get-started/devin-intro

Auto-approves read-only tools within the current directory, and asks for permission for write/execute operations.
explicitly-supported · https://docs.devin.ai/cli/essential-commands

Auto-approves file edits within the workspace while still prompting for shell commands and other actions.
explicitly-supported · https://docs.devin.ai/cli/essential-commands

You may need to provide Devin with credentials and keys such as passwords, API keys, cookies or other for authentication.
explicitly-supported · https://docs.devin.ai/admin/security

Gaps: opens pull requests, comments on issues or PRs, makes network/API calls, supports sandboxing, provides audit logging, supports enterprise administration, supports branch isolation, supports human approval controls, supports production deployment

Gemini CLI uses tools to interact with your local environment, access information, and perform actions on your behalf. These tools extend the model's capabilities beyond text generation, letting it read files, execute commands, and search the web.
explicitly-supported · https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/tools.md

You must manually approve tools that modify files or execute shell commands (mutators). The CLI shows you a diff or the exact command before you confirm.
explicitly-supported · https://github.com/google-gemini/gemini-cli/blob/main/docs/reference/tools.md

Sandboxing isolates potentially dangerous operations (such as shell commands or file modifications) from your host system, providing a security barrier between AI operations and your environment.
explicitly-supported · https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/sandbox.md

Sandbox expansion is a dynamic permission system that lets Gemini CLI request additional permissions for a command when needed.
explicitly-supported · https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/sandbox.md

Gemini CLI core provides a suite of tools for interacting with the local file system. These tools allow the model to explore and modify your codebase.
explicitly-supported · https://github.com/google-gemini/gemini-cli/blob/main/docs/tools/file-system.md

Gaps: edits files, opens pull requests, comments on issues or PRs, accesses secrets or environment variables, makes network/API calls, provides audit logging, supports enterprise administration, supports branch isolation, supports production deployment

Hooks allow you to execute custom shell commands at key points during agent execution, enabling you to add validation, logging, security scanning, or workflow automation.
explicitly-supported · https://docs.github.com/en/copilot/concepts/coding-agent/coding-agent

Configure secrets and variables
reasonably-inferred · https://docs.github.com/en/copilot/concepts/coding-agent/coding-agent

Gaps: reads repository, edits files, opens pull requests, comments on issues or PRs, makes network/API calls, supports sandboxing, supports permission controls, provides audit logging, supports enterprise administration, supports branch isolation, supports human approval controls, supports production deployment

Jules runs in a virtual machine where it clones your code, installs dependencies, and modifies files.
explicitly-supported · https://jules.google/docs/index.md

Jules runs in a virtual machine where it clones your code, installs dependencies, and modifies files.
explicitly-supported · https://jules.google/docs/index.md

Once you submit a task, Jules will generate a plan. You can review and approve it before any code changes are made.
explicitly-supported · https://jules.google/docs/index.md

Soon, you will see Jules comment automatically on the issue. When Jules is finished with the issue, it will provide a link to the pull request where you can review its work.
explicitly-supported · https://jules.google/docs/running-tasks.md

Gaps: reads repository, runs commands, opens pull requests, accesses secrets or environment variables, makes network/API calls, supports permission controls, provides audit logging, supports enterprise administration, supports branch isolation, supports production deployment

Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.
explicitly-supported · https://developers.openai.com/codex/cli/

Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.
explicitly-supported · https://developers.openai.com/codex/cli/

Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.
explicitly-supported · https://developers.openai.com/codex/cli/

Steer the active turn, inspect commands and diffs as they appear, and keep follow-up work in the same session.
explicitly-supported · https://developers.openai.com/codex/cli/

Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.
explicitly-supported · https://developers.openai.com/codex/cloud/

Configure any dependencies, tools, environment variables, or secrets the task needs.
explicitly-supported · https://developers.openai.com/codex/cloud/

Gaps: comments on issues or PRs, makes network/API calls, supports sandboxing, supports permission controls, provides audit logging, supports enterprise administration, supports branch isolation, supports production deployment

Code mode allows Cascade to create and make modifications to your codebase
explicitly-supported · https://docs.windsurf.com/windsurf/cascade

Gaps: reads repository, runs commands, opens pull requests, comments on issues or PRs, accesses secrets or environment variables, makes network/API calls, supports sandboxing, supports permission controls, provides audit logging, supports enterprise administration, supports branch isolation, supports human approval controls, supports production deployment