Pick the agent, not the marketing.

Good fit

You want repo work in a terminal or editor, and can explicitly choose the approval mode and provider before it starts writing.

Good fit

You want a repo-aware coding agent for interactive work or a bounded headless script, with tool permissions chosen for the job.

Good fit

You want a local general-purpose agent with MCP tools, reusable recipes and an optional schedule whose history you can inspect.

Good fit

You want a session-led coding agent and are willing to match permission and plugin configuration to your chosen OpenCode generation.

Good fit

You want to customize a Python browser agent, give your existing agent browser controls, or hand a task to the hosted V4 agent.

Good fit

You want task-led coding in a local CLI, with explicit sandbox settings for scripts or CI.

Good fit

You want reusable skills and memory across chat surfaces, plus scheduled work whose tools, outputs and failures you own.

Good fit

You want an open coding agent in the editor, terminal, or desktop, model-agnostic.

Good fit

You need an always-on operator agent on your own machine, with a real owner when it fails.

Good fit

You want Claude operating in the browser with enterprise transcript controls.

Good fit

You want the agent inside the editor, with optional cloud/self-hosted machines.

Good fit

You want Anthropic to host the agent session and permission policy.

Good fit

You are building an agent on OpenAI’s Agents API, not buying a packaged runtime.

Good fit

You want Anthropic’s hosted computer-use path, not a local Browser Use install.

Good fit

You are building a voice/multimodal agent and will own the pipeline.

Good fit

You want a local coding session with confirm, yolo and human modes, plus a saved trajectory you can inspect.

Good fit

You already run Claude Team or Enterprise and want a shared Slack agent with scoped access, routines, and an organization spend limit.

Good fit

You want a hosted agent to hold a standing role, retain work across shifts, and return decisions for approval rather than wait for the next prompt.

Good fit

You are standing up computer-use infrastructure yourself.

Good fit

You want user-directed task work in Zoom, with optional event- or schedule-triggered workflows and deliberately configured approval steps.

Good fit

You want a terminal coding partner with a repo map, reviewable git changes and editor-comment triggers.

Good fit

You want a small Hugging Face code-agent library to embed.

Good fit

You want reports and business-tool actions with per-operation Auto, Ask or Off controls, rather than a fixed approval rule for every write.

Good fit

You want a persistent operations assistant that can work through your existing email and calendar, including recurring follow-up and scheduling. You also want vendor-documented phone access to connected tools or scheduled briefing calls with follow-up questions and an emailed rundown if missed.

Good fit

You can configure integration-wide write rules for shared Slack work and separately review private-surface actions, connected-account authority and routine delivery.

Good fit

You want to shape work in an attended thread, then add a bounded trigger and deliberately widen its tool, account and knowledge access.

Good fit

You want coding and research in one Docker/Web UI workspace, with project memory and an optional bridge to your host files.

Good fit

You want an interactive coding agent with explicit command policy, plus a read-only-by-default task runner you can opt into edits and CI writes.

Good fit

You want reviewable branch/PR work, or configured automations that start new sessions or feed events into an existing one, with activity logs and optional failure email.

Good fit

You need to find the teammate session working on a repo or branch and send it context or a small text file without replacing its agent runtime.

Good fit

You want human-assigned coding or ops work with persistent agents, channels and delegation, and accept the preview's full local access. Check the noncommercial license and provider terms before choosing it for business or shared use.

Good fit

You want a runnable starting point you can customize, and can own the stack. Replace the single-user example with real sign-in and proper secrets before anyone else can reach it. MIT governs repository code; required CopilotKit Intelligence service/licensing and model access are separate. Exact costs and entitlements remain unassessed.

Good fit

You want persistent conversations plus browser, terminal and file work, with optional voice. Use Team Computers only for mutually trusted work; use separate computers when workloads need isolation. Treat trusted local-computer mode as host access, not a sandbox.