agent-browser
A browser-automation CLI for shell-capable agents, using compact accessibility snapshots and element references to drive web pages.
An agent uses a model to choose and carry out steps with tools. Compare coding agents, ongoing assistants and systems you operate yourself; the tool access and supervision differ as much as the models do.
How these were chosen: documented roles and concrete uses. For community momentum, explore repository signals.
Understand what stays running, where your data goes, and what you need to operate yourself.
Selected for documented roles and useful workflows. Alphabetical, editorial selections; not an adoption or capability ranking.
A browser-automation CLI for shell-capable agents, using compact accessibility snapshots and element references to drive web pages.
A terminal pair programmer with a repository map, Git integration, linting and tests.
Python and CLI browser agents with optional hosted browser and agent services.
Anthropic's coding agent reads repositories, edits files and runs development commands from terminal, IDE, desktop or web surfaces.
A cloud agent for briefs, connected business apps and assignments that continue while you are away.
A coding agent with edits, terminal tools, planning, checkpoints and approval controls.
OpenAI's terminal coding agent inspects and edits local repositories, runs development tools and supports interactive or scripted workflows.
Integrated repository-aware coding, edits, reviews and desktop, CLI and cloud agents.
Code suggestions, codebase questions, editing, reviews and agents that can produce pull requests.
Terminal agents with subagents, permissions, skills, hooks and MCP integrations.
Persistent named agents with role context, background work and repeatable routines on a shared cloud computer.
Agent software you operate, with configurable models, execution backends, persistent memory and reusable skills.
A low-level orchestration framework for stateful agents that combine deterministic steps, model calls, durable execution and human review.
An ongoing hosted agent with a cloud computer, connected apps and context across projects in ChatGPT.
An open-source coding agent with terminal, desktop and web interfaces that can connect to hosted providers or local model runtimes.