agentlist

The AI agent index

Find the right agent.

Explore, filter, and compare AI agents for the way you work.

Explore the indexCompare agents

Before you choose

All guides

The agent index

118 of 118 active entries

120 cataloged · 2 retired entries excluded from this index. Verification dates are listed on each agent’s spec sheet.

Select two agents to compare

Compare agents
  • Cursor

    Cursor is a VS Code–based AI-native editor with repo-aware chat, multi-file edits, Composer/agent modes, and cloud background agents.

    AI IDEEditorAPI
    View details
  • Google Antigravity

    Google Antigravity is Google's agent-first IDE and CLI, the successor surface to Gemini Code Assist for individuals and Gemini CLI.

    AI IDEEditorCLI
    View details
  • Kiro

    Kiro is AWS's agent-first IDE: spec-driven development (requirements → design → tasks), agent hooks, and an Auto agent, with a CLI.

    AI IDEEditorCLI
    View details
  • Trae

    Trae is ByteDance's AI-native VS Code fork with Builder chat and SOLO, an autonomous mode that plans and builds whole apps from a brief.

    AI IDEEditor
    View details
  • Windsurf / Devin Desktop

    Windsurf is Cognition's AI IDE (ex-Codeium) built around Cascade multi-step agent flows, sold on the same Free / Pro / Max / Teams sheet as Devin.

    AI IDEEditor
    View details
  • Zed

    Zed is a fast native editor (Rust, GPU-rendered) with a built-in agent panel, edit predictions, and hosted or BYOK models.

    AI IDEEditor
    View details
  • Amazon Q Developer

    Amazon Q Developer (formerly CodeWhisperer) is AWS's coding assistant with IDE and CLI agents plus Java/.NET transformation.

    IDE extensionEditorCLI
    View details
  • Augment Code

    Augment Code is a context-engine coding agent for large codebases, available in VS Code, JetBrains, and a CLI (Auggie), priced as one flat team plan.

    IDE extensionEditorCLI
    View details
  • Cline

    Cline is an open-source VS Code agent that plans, edits, and runs tools with BYOK models and approval controls.

    IDE extensionEditorCLI
    View details
  • Gemini Code Assist

    Gemini Code Assist is Google's per-seat coding assistant for IDEs and Google Cloud workflows, now sold only as Standard and Enterprise.

    IDE extensionEditor
    View details
  • GitHub Copilot

    GitHub Copilot is the GitHub-native coding assistant: completions, chat, agent mode, and PR coding agents across many IDEs.

    IDE extensionEditorAPI
    View details
  • Junie

    Junie is JetBrains' coding agent — inside JetBrains IDEs (Junie Local in AI Chat) and as a terminal CLI. GA since June 2026, with agentic debugging that drives the IDE's real debugger, breakpoints included.

    IDE extensionEditorCLI
    View details

Showing 12 of 118 matching agents

Guides & comparisons

A closer look.

Head-to-head spec diffs and practical guidance to help you narrow 118 active systems down to the one you will actually use.

  • 01

    Cursor vs Windsurf / Devin Desktop

    The two flagship AI IDEs. Cursor is a VS Code fork with the largest third-party model pool; Windsurf (now under Cognition, alongside Devin) is the ex-Codeium editor built around Cascade agent flows.

  • 02

    Claude Code vs Codex CLI

    The two terminal-native agents bundled with the frontier subscriptions — Claude Pro/Max vs ChatGPT Plus/Pro. Both plan, run commands, and commit against your local checkout.

  • 03

    Build your own shortlist

    Filter the index by category, interface, and hosting, then put any two entries side by side on the same spec fields.

Our approach

Clear specs. Better decisions.

Agentlist is an independent index built to make the agent ecosystem more transparent, comparable, and useful. 120 cataloged systems: 118 active and 2 retired, from 97 vendors across 15 categories. Each spec sheet includes its verification date.

  • Source-linked information

    Every entry cites the vendor pages it was compiled from, so you can verify a claim instead of trusting ours.

  • Side-by-side comparisons

    The same spec fields on every entry — category, interfaces, hosting, access, status — so differences are visible at a glance.

  • A growing, open index

    The catalog is seeded by hand and re-verified on each refresh. New agents and corrections are welcome.

Common questions

What is agentlist.io?
agentlist.io is a catalog of AI agents — AI IDEs, IDE extensions, terminal (CLI) agents, cloud agents, platforms, model routers, bridges, personal agents, digital employees, ops agents, computer-use agents, research agents, and voice agents — normalized to the same spec fields (category, interfaces, hosting, pricing, status) so they can be compared side by side.
What counts as an agent here?
Anything that takes work on with an LLM in the loop: editors and terminals that write code, cloud agents that return pull requests, employees that hold a business role, agents that drive a browser, hold a pager, research a question, or answer the phone — plus the routers and protocols that connect them to models and tools.
How do I choose between an AI IDE, a CLI agent, and a cloud agent?
Pick by where you want the work to happen. An AI IDE or extension keeps you in the editor with the agent as a collaborator. A CLI agent runs against your local checkout in the terminal for interactive, supervised sessions. A cloud agent runs remotely on its own and hands back a PR — best when you want to delegate a whole task rather than pair on it.
Is the pricing on agentlist.io accurate?
Pricing and status are recorded from public vendor pages and marked approximate with a seed date. Vendors change plans often; confirm on the vendor's own pricing page before deciding.
Are listings paid or sponsored?
No. Entries are editorial records compiled from public documentation. A listing is a catalog record, not an endorsement or a paid placement.