LIST-OF-AI-AGENTS · 112 systems · 89 vendors · 15 categories

The list of AI agentsevery agent, one spec sheet

Every cataloged agent, grouped by what it actually does — coding tools first, then the agents that hold a role: employees, on-call responders, browser drivers, analysts, and voices on the phone. Each entry links to a spec sheet recording category, interfaces, hosting, pricing, and status. Want facets instead of a scroll? Use the filterable index.

01

AI IDEs · 06

An AI IDE is a forked or purpose-built code editor whose primary interface is an AI agent: repo-aware chat, multi-file edits, and agent modes are first-class, not a plugin. Most are VS Code forks; some are native editors that add agent panels. Category guide →

02

IDE extensions & copilots · 10

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. Category guide →

03

CLI & terminal agents · 15

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. Category guide →

Claude Code

Anthropic · cli-agent

cli/editor/api · local · Included in Claude Pro $20/mo and Max ($100/$200); API pay-per-token

Codex CLI

OpenAI · cli-agent

cli/editor/api · local/cloud · Included in ChatGPT Free/Go/Plus/Pro/Business/Enterprise; credits for extra usage

Aider

Community / OSS · cli-agent

caution
cli · local · Free (OSS) + your model API costs

Amp

Amp Inc. · cli-agent

cli/editor · local · Hobby free (BYOK / own runners); Megawatt $20/mo; Gigawatt $200

OpenCode

Community / OSS · cli-agent

cli · local · Free (OSS) + BYOK; Zen PAYG; Go $10/mo

OpenHands

Community / OSS · cli-agent

cli/api/editor · local/cloud · Free OSS self-host; Cloud free tier + $20/mo

Goose

Block · cli-agent

cli · local · Free (OSS) + model costs

Gemini CLI

Google · cli-agent

caution
cli · local · Consumer/free tiers ended Jun 18, 2026; API key or Code Assist Standard/Enterprise only

Warp

Warp · cli-agent

cli · local/cloud · Free; Pro $20/mo; Team $45–50/user; Max $200

Muse Code

Meta · cli-agent

cli/api · local · Contributor free (5h token windows); subs rolling out; API $1.25/M in · $4.25/M out

Grok Build

xAI · cli-agent

cli/editor/api · local · Free to try; SuperGrok $30/mo or X Premium+ $40/mo; API grok-4.6 $2/M in · $6/M out

Kimi Code

Moonshot AI · cli-agent

cli/editor/api · local · Free OSS; Kimi Code managed service or Moonshot API keys (multi-provider)

Qwen Code

Alibaba Cloud · cli-agent

cli/editor/api · local · Free OSS (Apache-2.0); Alibaba Cloud Coding Plan or any compatible provider

Mistral Vibe

Mistral AI · cli-agent

cli/editor · local · CLI open source; models via Mistral API / Le Chat; Devstral Small self-deployable

Crush

Charm · cli-agent

cli · local · Free OSS (FSL-1.1-MIT); BYO provider keys
04

Cloud & autonomous agents · 05

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. Category guide →

05

Platforms & harness multiplexers · 01

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. Category guide →

06

Model routers & gateways · 02

Model routers expose a single, usually OpenAI-compatible API and route requests across providers with fallbacks, spend controls, and usage billing. Most BYOK coding agents can point at one. Category guide →

07

Bridges, brokers & protocols · 02

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. Category guide →

08

Agent communication & collaboration · 13

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). Category guide →

09

Agent services · 15

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. Category guide →

10

Personal & always-on agents · 06

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. Category guide →

11

AI employees & digital coworkers · 10

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. Category guide →

12

On-call & ops agents · 07

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. Category guide →

13

Browser & computer-use agents · 06

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). Category guide →

14

Research & analyst agents · 07

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). Category guide →

15

Voice & phone agents · 07

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. Category guide →

FAQ

Frequently asked

How many AI agents are on this list?

112 systems from 89 vendors, grouped into 15 categories — verified 2026-09-25. The count grows on each catalog pass; see the changelog for additions, repricings, and retirements.

What kinds of AI agents are included?

Developer-facing agents (AI IDEs, IDE extensions, CLI agents, cloud agents, platforms, model routers, bridges), always-on assistants (personal agents), and agents that hold a job: digital employees, ops agents on the incident/security loop, computer-use agents driving GUIs, research agents producing cited reports, and voice agents on the phone.

What is the best AI agent on the list?

It depends on the job, not the league table. Pick a category first — an IDE or CLI agent for supervised coding, a cloud agent for delegated tickets, an employee or ops agent for business roles — then compare entries on interfaces, hosting, and pricing. Every entry links a spec sheet; curated head-to-heads live on the compare page.

Is this list of AI agents free and kept up to date?

Yes. Entries are editorial records compiled from public vendor pages — no paid placement. Each refresh re-verifies pricing and status; the changelog and RSS feed record every change.

Can I filter or sort this list?

This page is the full read-through. For filtering, use the systems index — search plus category, interface (editor, CLI, API, chat, browser, voice), and hosting facets — and select any two entries for a side-by-side spec diff.

Records verified 2026-09-25. Vendors: Anysphere · Cognition · Anthropic · OpenAI · GitHub · Community / OSS · Amazon Web Services · Google · Sourcegraph · Amp Inc. · Block · Factory AI · Replit · OpenRouter · OpenScout · Zed Industries · ByteDance · Warp · Augment Code · Roo Code Inc. · Meta · xAI · Moonshot AI · Alibaba Cloud · Mistral AI · Charm · Kilo · JetBrains · OpenClaw Foundation · Nous Research · Qwibit AI · ZeroClaw Labs · Sipeed · HKUDS · 11x · Artisan · Qualified · Sierra · Decagon · Intercom · Harvey · Lindy · Juicebox · Mercor · Cleric · Resolve · incident.io · Rootly · Datadog · Dropzone AI · Simbian · Browser Use · Skyvern · Manus · Browserbase · Perplexity · Genspark · Hebbia · Elicit · AlphaSense · Vapi · Bland AI · Retell AI · Synthflow · ElevenLabs · Deepgram · A2A Project · AGNTCY · NANDA (MIT Media Lab) · IBM · CrewAI · Microsoft · LangChain · DeepWisdom · CAMEL-AI · VRSEN · AgentMail · Coinbase · Skyfire · Payman · Nevermined · AgentCard · Keycard · Arcade · Scalekit · Composio · E2B · Exa · Mem0.