Taxonomy — 19 categories · 159 systems

AI agents and agent tools

Agentlist groups agents and supporting tools into 19 categories. Coding agents include agentic development environments, IDE extensions, CLI agents, and cloud agents. Tools around them include platforms, model routing and configuration, bridges, agent communication, agent services, agent workspaces, terminal session managers, orchestration systems, and remote access. Other categories cover personal agents, digital employees, operations, computer use, research, and voice.

Each category page defines the term, explains who it's for, lists tradeoffs, and links every cataloged system in it.

01

Agentic development environments

An agentic development environment is the place you run coding agents from: an editor or desktop app where agents plan, edit and test across a repo, several can run at once, and you review the result there. Some are editors (Cursor, Zed, Kiro), some sit on top of your editor (VS Code with Copilot), and some manage agents from other vendors (Warp, JetBrains Air).

Cursor · Windsurf / Devin Desktop · Kiro · Google Antigravity · Zed · Trae

06 systems →
02

IDE extensions & copilots

IDE extensions add completion, chat, and agent modes to an existing editor — VS Code, JetBrains, Neovim — through the editor's plugin system. They range from vendor copilots to open-source, bring-your-own-key agents.

GitHub Copilot · Cline · Amazon Q Developer · Gemini Code Assist · Sourcegraph Cody · Augment Code · Continue · Roo Code · Kilo Code · Junie

10 systems →
03

CLI & terminal agents

CLI agents run in the shell against a local checkout. They read the repository, plan changes, edit files, execute commands and tests, and often commit — usually with tool protocols like MCP for extension.

Claude Code · Codex CLI · Aider · Amp · OpenCode · OpenHands · Goose · Gemini CLI · Warp · Muse Code · Grok Build · Kimi Code · Qwen Code · Mistral Vibe · Crush

15 systems →
04

Cloud & autonomous agents

Cloud agents run in a vendor-hosted sandbox rather than on your machine. You hand them a task — an issue, a ticket, a prompt — and they return a pull request or a deployed change for human review.

Devin · Factory Droids · Jules · Replit Agent · Roomote

05 systems →
05

Platforms & harness multiplexers

Platforms sit above individual agents: multi-agent IDEs that run Claude Code, Codex, and Cursor side by side in Git worktrees, or managed APIs that deploy coding agents across harnesses with sandboxes and credentials.

Glean Agents · n8n · Salesforce Agentforce · Cursor Origin

04 systems →
06

Model routing & configuration

Model gateways route requests through compatible APIs. Configuration utilities manage provider profiles, credentials, and tool settings. Both help connect coding agents to model providers, but a configuration switcher is not necessarily a request proxy.

OpenRouter · LiteLLM · Magpie · CC Switch · Claude Code Router · CLIProxyAPI · 9Router · Together Link

08 systems →
07

Bridges, brokers & protocols

Bridges attach agents to tools, data, and channels — tool protocols (MCP), memory servers, and transport bindings that expose an agent through chat or voice. For agents talking to agents, see agent communication.

Model Context Protocol · instinct-mcp · coding memory

02 systems →
08

Agent communication & collaboration

Bridges connect agents to tools; this category connects agents to each other. It splits into open protocols for cross-vendor discovery and messaging (A2A, AGNTCY, ANP, NANDA) and multi-agent frameworks where a supervisor delegates work to specialists through handoffs (CrewAI, Microsoft Agent Framework, LangGraph, MetaGPT, CAMEL).

OpenScout / Scout · A2A Protocol · AGNTCY · Agent Network Protocol · NANDA · BeeAI · CrewAI · Microsoft Agent Framework · LangGraph · MetaGPT · CAMEL · Agency Swarm · OpenAI Agents SDK · Reason Network · Agent Relay · hcom · Claude Peers MCP · MCP Agent Mail

18 systems →
09

Agent services

Agent services are purpose-built primitives whose customer is the agent (or its builder): ways to pay (x402, AP2, AgentCard, Skyfire), ways to authenticate (Keycard, Arcade, Scalekit), places to exist (AgentMail inboxes, E2B sandboxes, Browserbase browsers), and senses (Exa search, Mem0 memory). Where bridges give agents protocols, services give them accounts — metered, billable capabilities the agent can't synthesize.

AgentMail · x402 · Agent Payments Protocol · Skyfire · Payman · Nevermined · AgentCard · Keycard · Arcade · Scalekit · Composio · E2B · Browserbase · Exa · Mem0 · OpenMail · Nylas · Resend · Postmark

19 systems →
10

Personal & always-on agents

Personal agents are self-hosted assistant runtimes: one gateway or process that holds sessions, memory, tools, and skills, and meets you in the channels you already use — Telegram, WhatsApp, Discord, Slack, Signal, iMessage — alongside CLIs, TUIs, and web dashboards. They run on your hardware or your VPS, keep state on your machine, and delegate to repo-native coding agents when the task is code.

Muse · Grok Bot · OpenClaw · Hermes Agent · NanoClaw · ZeroClaw · PicoClaw · nanobot

08 systems →
11

AI employees & digital coworkers

AI employees are agents packaged as a job function — an SDR that prospects, a support rep that resolves tickets, a recruiter that screens candidates. They arrive with an identity, a role, and integrations into the systems that role touches (CRM, helpdesk, ATS, email, phone), and they're sold on seats or outcomes rather than editor features.

Alice · Ava · Piper · Sierra · Decagon · Fin · Harvey · Lindy · Juicebox (PeopleGPT) · Mercor

10 systems →
12

On-call & ops agents

Ops agents sit inside the incident and security loop: they watch alerts, correlate telemetry, investigate pages, draft root-cause analyses, and propose or apply remediations. AI SREs handle production incidents; AI SOC analysts (Dropzone, Simbian) handle security queues.

Cleric · Resolve · incident.io · Rootly · Bits AI · Dropzone AI · Simbian

07 systems →
13

Browser & computer-use agents

Computer-use agents operate software through its interface — a browser, a desktop, a remote session — by reading the screen or DOM and acting with clicks, keystrokes, and navigation. Some are hosted products that take a goal and return a result (ChatGPT Agent, Manus); others are open frameworks and APIs for building your own (Browser Use, Skyvern, Stagehand, Claude Computer Use).

Browser Use · Skyvern · ChatGPT Agent · Claude Computer Use · Manus · Stagehand

06 systems →
14

Research & analyst agents

Research agents take a question and return a structured, cited report — searching, reading, and synthesizing dozens of sources over minutes-long runs. Consumer 'deep research' modes live inside chat products (ChatGPT, Gemini, Perplexity); enterprise analysts work over licensed or internal corpora (Hebbia, AlphaSense); academic tools ground in the literature (Elicit).

ChatGPT Deep Research · Gemini Deep Research · Perplexity · Genspark · Hebbia (Matrix) · Elicit · AlphaSense

07 systems →
15

Voice & phone agents

Voice agents handle real-time spoken conversations: inbound reception and support, outbound reminders and qualification, scheduling, intake, and surveys. The category is mostly developer platforms (Vapi, Retell, Bland, Deepgram, ElevenLabs Agents) that orchestrate speech-to-text, a model, and text-to-speech over telephony — plus no-code products (Synthflow) that ship a ready receptionist.

Vapi · Bland AI · Retell AI · Synthflow · ElevenLabs Agents · Deepgram Voice Agent · Grok Voice Agent API

07 systems →
16

Agent workspaces

Agent workspaces organize existing coding agents into sessions, projects, and review surfaces. Many use Git worktrees to separate concurrent tasks.

Conductor · Paradev (formerly Superset) · Emdash Classic · Agentastic.dev · Schaltwerk · Nimbalyst · Vibe Kanban · cmux · T3 Code · Orca

10 systems →
17

Terminal session managers

Terminal session managers organize coding-agent processes, terminal panes, and project sessions. Some also create Git worktrees and help with branch workflows.

Claude Squad · Agent Deck · Agent of Empires · CCManager · dmux · Named Tmux Manager (NTM) · Herdr · Rex

08 systems →
18

Agent orchestration systems

Agent orchestration systems assign and coordinate work across coding agents, track workflows, and organize their outputs. These listings focus on tools around existing coding harnesses.

Gas Town · Agent Orchestrator · CLI Agent Orchestrator · Ruflo · Maestro

05 systems →
19

Remote access & continuity

Remote agent access tools expose existing coding-agent sessions through mobile, browser, or desktop clients so users can monitor and direct work away from the host.

Happy · HAPI · Paseo · Omnara

04 systems →
FAQ

Frequently asked

What are the main types of AI agents?

Agentlist groups agents and supporting tools into 19 categories. Coding agents include agentic development environments, IDE extensions, CLI agents, and cloud agents. Tools around them include platforms, model routing and configuration, bridges, agent communication, agent services, agent workspaces, terminal session managers, orchestration systems, and remote access. Other categories cover personal agents, digital employees, operations, computer use, research, and voice.

What is the difference between an agentic development environment and an IDE extension?

An agentic development environment is an editor or desktop app built around agents, such as Cursor, Zed or Kiro, so the vendor controls the whole interface. An IDE extension installs into the editor you already use (VS Code, JetBrains, Neovim) and adds agent features without replacing it. Extensions are lower-commitment; a full environment can integrate more deeply.

What is the difference between a CLI agent and a cloud agent?

A CLI agent runs on your machine, in your terminal, against your local checkout — you watch and steer it in real time. A cloud agent runs on the vendor's infrastructure in its own sandbox, typically takes a ticket or prompt, and returns a pull request. CLI agents favour interactive work; cloud agents favour delegating whole tasks.

Do I need a model router or a bridge to use a coding agent?

No. Most agents work out of the box with their default model provider. A model router (like OpenRouter or LiteLLM) is useful when you want to swap providers, control cost, or use one API key across many models. A bridge (like the Model Context Protocol) is useful when you want an agent to reach tools, databases, or internal services in a standard way.