---
title: "The AI agent catalogue · every agent, classified and sourced · Agent Fieldbook"
url: https://agentfieldbook.org/catalog/all/
description: "The full Agent Fieldbook catalogue: every AI agent classified by the agency lens, specced against primary sources, and drawn as a specimen card whose shape reflects its topology. Frontier assistants, coding copilots, platforms, vertical SaaS, security, legal, health, science and finance."
section: "Catalogue · All"
source: Agent Fieldbook — generated from the published page
---

# Every agent in the corpus

**A field guide to the systems reshaping how work gets done.** Explore the agents and open-source harnesses in the Fieldbook, each classified by deployment mode, inferred topology, home country and build approach. Every specimen card makes the operating model behind the product visible.

## 103 agents Live data · click a specimen for its anatomy

## Field notes

The full catalogue: classified, specced and sourced

**The catalogue is built to show what an agent is, not just what it promises.** Each entry is classified, specified and sourced from available evidence. Its topology is inferred from product descriptions, technical documentation and how the system is configured in practice.

Vertical SaaS is the leading deployment path at 31 of 103 agents, with security, fraud and finance advancing behind it. In tightly governed enterprise settings co-pilot patterns remain common: they keep information within the business, preserve approval controls and can orchestrate across multiple models. In banking and finance that often means pairing frontier models with custom-trained systems. Filter by modality and classification, then open a card for the full spec sheet.

- [Brandon Chaplin](https://www.linkedin.com/in/brandon-chaplin-digital-marketing-strategist)

## Common questions

### What are the main types of AI agent?

Broadly five. Frontier assistants from the large labs, copilots built into a tool you already use, platforms for building your own, open-source frameworks you host yourself, and vertical agents made for one industry such as law or healthcare.

### What is the difference between an AI agent and an AI assistant?

How much happens without you. An assistant replies to what you ask. An agent takes a goal, plans the steps and uses tools until the task is done. The labels are used loosely in marketing, so check what a product actually does on its own.

### How do I choose an AI agent for my business?

Start with the job, not the model. Check what tools and data it can reach, whether it sits inside software your team already uses, what it costs per user or per task, and who approves its actions. Tool access increasingly runs through MCP, an open standard worth checking support for [(Model Context Protocol)](https://modelcontextprotocol.io/).

### What model do most AI agents run on?

Usually a foundation model from one of the big labs rather than one trained in-house. The agent is everything around it: the tools, the memory, the workflow and the guardrails. That is why two agents can behave very differently while sharing the same model.

### Can multiple AI agents work together?

Yes. Multi-agent setups split a job across specialised agents, often with one coordinating the rest. It adds capability, and also adds cost, latency and new ways to fail, so most production systems keep the number of agents small.

## Next in the learning path

- [Agent vs operator The lens every entry is classified by](https://agentfieldbook.org/catalog/agency/)

- [Frontier agents The general-purpose flagships](https://agentfieldbook.org/catalog/frontier/)

- [Open-source agents The community and framework-native builds](https://agentfieldbook.org/catalog/oss/)

- [Reference architectures Real systems assembled from these agents](https://agentfieldbook.org/design/architectures/)

- [Deployment modalities Where each of these agents runs](https://agentfieldbook.org/catalog/modalities/)

## Entries

_103 entries listed on this page._

| name | description | subjectOf |
| --- | --- | --- |
| ChatGPT Agent | Distribution is the moat, destination product and launch surface for new OpenAI agent capabilities. | https://openai.com/index/march-funding-updates/ |
| Claude Agent | Not only a model destination, Anthropic shaped the agent tooling layer through MCP. | https://www.anthropic.com/system-cards |
| Gemini Agent | Combines product distribution, model ownership, and a standards play through A2A. | https://blog.google/innovation-and-ai/sundar-pichai-io-2026/ |
| GitHub Copilot | Agnostic coding surface increasingly governed by usage-based economics. | https://github.com/features/copilot |
| GitHub Copilot Cloud Agent | Cloud execution makes Copilot more agentic and more compute-intensive. | https://github.com/features/copilot |
| Microsoft 365 Copilot | Grounding (Microsoft Graph) and enterprise distribution are the moat. | https://www.microsoft.com/microsoft-365-copilot |
| M365 Copilot Chat | Free included chat is a distribution wedge into paid Copilot. | https://www.microsoft.com/microsoft-365-copilot |
| Cursor | The model router disguised as an IDE, model choice is a feature, not a backend detail. | https://docs.cursor.com/models |
| Sourcegraph Cody | Owns code context and enterprise controls, not the frontier model. | https://sourcegraph.com/cody |
| Devin | Model provenance now disclosed, Devin runs on Anthropic Claude and OpenAI models (confirmed Jun 2026). | https://devin.ai/blog/claude-fable-5-available-in-devin/ |
| Salesforce Agentforce | A governed enterprise runtime wrapped around CRM, actions, and flexible model supply. | https://www.salesforce.com/news/press-releases/2026/05/27/fy27-q1-earnings/ |
| Intercom Fin | Rebranded from Intercom to Fin; agreed to be acquired by Salesforce (~$3.6B, Jun 2026). Flagship Fin now runs on proprietary Apex models, not Claude. Strong compliance signalling (ISO 42001). | https://venturebeat.com/technology/intercoms-new-post-trained-fin-apex-1-0-beats-gpt-5-4-and-claude-sonnet-4-6 |
| HubSpot Breeze | Outcome pricing by resolution is strategically notable. | https://www.hubspot.com/company-news/hubspots-customer-agent-and-prospecting-agent-now-you-pay-when-the-task-is-complete |
| Zendesk AI | Category presence strong; model stack needs a deeper documentation crawl. | https://support.zendesk.com/hc/en-us/articles/5352026794010-About-automated-resolutions-for-AI-agents |
| Freshworks Freddy | Promising operational automation; exact model stack not public. | https://www.freshworks.com/freddy-ai/ |
| Ada | Product strength exceeds public proof of model sourcing. | https://www.ada.cx |
| Notion Enterprise Search | Strong citation-first enterprise search pattern. | https://www.notion.com/product/enterprise-search |
| Slack AI | Search and permissioning are central to Slack's AI moat. | https://slack.com/features/ai |
| Lindy | Inbox-first delegation agent with explicit multi-model billing under the hood. | https://docs.lindy.ai/pricing |
| Relevance AI | Built for ops teams running agents, not only engineers building them. | https://relevanceai.com/ |
| Zapier Agents | The connector moat is doing the heavy lifting. | https://zapier.com/agents |
| Deepgram Voice Agent | Voice stack vendor with unusually clear pricing surfaces. | https://deepgram.com/product/voice-agent-api |
| ElevenLabs Agents | Latency leadership is clear; agent reasoning stack is less public. | https://elevenlabs.io/conversational-ai |
| Gemini Enterprise Platform | A2A gives Google a standards wedge inside enterprise agents. | https://docs.cloud.google.com/gemini/enterprise/docs/register-and-manage-an-a2a-agent |
| Harvey AI | Market-leading enterprise legal agent, expanded 6→60+ jurisdictions with autonomous agents; table stakes at $50M+/yr firms. | https://www.harvey.ai |
| Mistral Vibe | Rebranded from Le Chat to Vibe (Jun 2026); EU-sovereign frontier assistant now runs Mistral Large 3 / Medium 3.5. |  |
| CrowdStrike Charlotte AI | Agentic SOC at the endpoint, Charlotte moved past copilot to autonomous detection, triage and response; AgentWorks lets teams build custom security agents. | https://www.crowdstrike.com/en-us/press-releases/crowdstrike-launches-charlotte-ai-agentworks-ecosystem-for-building-secure-agents/ |
| Microsoft Security Copilot | Investigates incidents and executes security workflows; Agent 365 is the enterprise control plane with shadow-AI discovery and network-level prompt-injection blocking. | https://techcommunity.microsoft.com/blog/securitycopilotblog/from-alert-overload-to-decisive-action-how-security-copilot-agents-are-transform/4504213 |
| Dropzone AI | Autonomously investigates every security alert end-to-end, producing analyst-grade conclusions without playbooks. | https://www.dropzone.ai |
| Prophet Security | Agentic AI SOC analyst that triages and investigates alerts at machine speed, cutting alert overload. | https://www.prophetsecurity.ai/blog/top-5-ai-soc-analyst-platforms |
| Simbian | Autonomous AI security agents that automate SOC workflows from detection to response. | https://www.simbian.ai |
| Apate.ai | Deploys swarms of conversational decoy "victims" that engage scammers in real time: wasting their resources and harvesting live threat intelligence. A Macquarie University Cyber Security Hub spin-out. | https://www.apate.ai/ |
| Sardine | Fraud, compliance and AML platform deploying risk agents that investigate and decision transactions in real time. | https://www.sardine.ai |
| XBOW | First non-human to top HackerOne's US leaderboard. Autonomous pen-tester founded by Oege de Moor (creator of GitHub Copilot / CodeQL); Pentest On-Demand turns 35–100-day engagements into clicks. | https://xbow.com/blog/top-1-how-xbow-did-it |
| Horizon3.ai NodeZero | Autonomous penetration-testing agent that continuously finds and chains exploitable attack paths across an environment, then verifies real impact. | https://www.horizon3.ai |
| ZeroPath | Agentic application-security scanner that finds and triages exploitable code vulnerabilities with low false positives. | https://zeropath.com |
| Legora | Collaborative legal AI calling 2026 "the year of agents in legal": agents completing end-to-end legal work with human oversight. | https://news.crunchbase.com/venture/unicorn-legal-tech-ai-startup-legora-triples-valuation/ |
| Spellbook | Word-native contract drafting and review agents for transactional lawyers. | https://www.businesswire.com/news/home/20251009110230/en/ |
| Hippocratic AI | Patient-facing healthcare agents for scheduling, intake, outreach and chronic-care: built safety-first for non-diagnostic tasks. | https://www.hippocraticai.com |
| OpenEvidence | Evidence-based clinical question-answering for physicians: one of the most valuable healthcare AI companies. | https://www.openevidence.com |
| Abridge | Ambient clinical documentation, listens to the visit and drafts the note inside the EHR. | https://www.abridge.com |
| Ambience Healthcare | Ambient documentation + Chart Chat copilot embedded directly in Epic for context-aware clinical insight. | https://www.ambiencehealthcare.com |
| Nabla | Ambient clinical documentation with fast deployment and a clean workflow, used widely outside the US-only market. | https://www.nabla.com |
| Rogo | Finance-native agentic platform; its Felix agent runs IB workflows end-to-end: deal screening, CIM generation, comps, data-room diligence. | https://rogo.ai |
| Hebbia Matrix | Research-and-reasoning agents that execute end-to-end workflows from discovery to deliverable across finance, law and consulting. | https://www.hebbia.com/product |
| AlphaSense Assistant | Market-intelligence agents over broker research, expert calls, SEC filings and news: scheduled to deliver insights automatically. | https://www.alpha-sense.com/resources/research-articles/ai-tools-for-financial-research/ |
| FutureHouse (Robin / Kosmos) | Multi-agent AI scientists that generate hypotheses, design experiments and analyze data: Robin identified ripasudil as a candidate therapy autonomously. | https://www.futurehouse.org/about |
| Sakana AI Scientist | Automates the research lifecycle via agentic tree search: produces workshop-level papers end-to-end. | https://github.com/SakanaAI/AI-Scientist-v2 |
| Lila Sciences | Building AI that performs the scientific method autonomously at superhuman speed: "scientific superintelligence". | https://www.lila.ai/ |
| Make Agents | Visual scenario builder now with AI agents as first-class nodes: automations + agents in one canvas. | https://www.make.com/en/ai-automation |
| n8n AI Agents | Open-source workflow automation with native AI Agent nodes, LangChain-under-the-hood, self-hostable. | https://n8n.io/features/ |
| Retool Agents | Retool's agent builder, same low-code canvas as their internal-tool platform, now agents as workflow primitives. | https://retool.com/products/agents |
| Airtable AI | AI baked into every field, summarise, extract, categorise, generate, at the row level. | https://www.airtable.com/platform/ai |
| Coda AI | AI assistant baked into Coda docs, writes, summarises, and automates against the doc as its state. | https://coda.io/product/ai |
| Bardeen | Browser-native agent that reads and acts across web apps: no code, chained playbooks. | https://www.bardeen.ai/ |
| Aider | Open-source CLI coding agent, you keep the repo, it writes commits alongside you. | https://aider.chat/ |
| OpenHands | Open-source Devin-alternative from All Hands AI: autonomous coding agent with sandbox execution. | https://github.com/All-Hands-AI/OpenHands |
| SWE-agent | Princeton/Stanford research agent that solves SWE-bench tasks via an agent-computer interface. | https://swe-agent.com/ |
| Continue.dev | Open-source IDE copilot, bring-your-own-model, extensible autocomplete + chat + agent modes. | https://www.continue.dev/ |
| Zed AI | Rust-built editor with first-class AI agent panel: Anthropic-partnered, fast native UI. | https://zed.dev/ai |
| Warp AI | Terminal reimagined as an agent surface: natural language commands, multi-step workflows. | https://www.warp.dev/warp-ai |
| Bolt.new | StackBlitz's in-browser AI agent, full-stack apps built end-to-end from a prompt, deploys instantly. | https://bolt.new/ |
| v0 | Vercel's design-to-code agent, chat produces production Next.js components in real time. | https://v0.dev/ |
| Lovable | Swedish full-stack app builder, chat gives you a deployed React + Supabase app, edit-by-prompt. | https://lovable.dev/ |
| 11x (Alice) | AI SDR "Alice", books meetings 24/7 from cold outbound, marketed as a headcount replacement. | https://www.11x.ai/ |
| AiSDR | AI SDR that runs full outbound sequences: replies, follow-ups, meeting booking end-to-end. | https://aisdr.com/ |
| Regie.ai | Autonomous sales-development agent, sequences that self-adapt, hand off qualified leads to reps. | https://www.regie.ai/ |
| Claygent | Enrichment + outbound platform, chained data providers + LLM waterfalls to build hyper-targeted lists. | https://www.clay.com/ |
| Apollo AI | AI layer on top of Apollo's 260M+ contact DB: chat with pipeline, agentic outbound built in. | https://www.apollo.io/product/ai |
| Gong AI | Call intelligence + deal insights + coaching agent: Gong's bet that the rep is just the physical layer. | https://www.gong.io/product/ |
| Jasper | Enterprise marketing content platform, brand-voice-trained agents that write campaigns end-to-end. | https://www.jasper.ai/ |
| Copy.ai | GTM-workflow-focused agent platform, outbound, RFP, deal desk automations. | https://www.copy.ai/ |
| HeyGen | Avatar video generation, clone voice, generate multi-lingual video from a script. | https://www.heygen.com/ |
| Synthesia | UK-based enterprise avatar-video platform: 200+ languages, 150+ AI avatars. | https://www.synthesia.io/ |
| Runway | Gen-3 video generation + editing agent: Hollywood-adopted for film production workflows. | https://runwayml.com/ |
| Vapi | Developer platform for building voice AI agents: end-to-end pipeline, sub-second latency. | https://vapi.ai/ |
| Retell AI | Voice-agent building blocks, real-time conversational agents for customer support + sales calls. | https://www.retellai.com/ |
| Bland AI | Enterprise phone-agent platform, self-hosted voice models, human-indistinguishable calls at scale. | https://www.bland.ai/ |
| Sierra | Bret Taylor + Clay Bavor's conversational-AI company: enterprise customer-support agents. | https://sierra.ai/ |
| Decagon | AI customer-service agents for enterprise: outcome-based pricing, deep CS-tool integrations. | https://decagon.ai/ |
| Cresta | Real-time coaching + AI-agent platform for contact centres: assists humans, replaces routine calls. | https://cresta.com/ |
| Ironclad AI | CLM leader's AI agent layer, Jurist AI drafts, reviews, redlines contracts. | https://ironcladapp.com/product/ai/ |
| Robin AI | UK contract-review AI, Claude-integrated, in-line redlines, natural-language edits. | https://www.robinai.com/ |
| Suki AI | Voice-first clinical assistant, ambient documentation, EHR integration, physician co-pilot. | https://www.suki.ai/ |
| Notable Health | Autonomous agents across the care journey: intake, scheduling, follow-ups, chart prep. | https://www.notablehealth.com/ |
| Glass Health | Clinical-decision-support AI for clinicians: differential diagnosis + evidence-based reasoning. | https://glass.health/ |
| Auquan | Agentic research for asset management, surfaces material risks + insights from unstructured data. | https://www.auquan.com/ |
| Kensho | S&P-owned financial AI, NLP + entity extraction + LLM agents across S&P Capital IQ. | https://kensho.com/ |
| Julius AI | Chat with your data, natural-language data-analysis agent, sandboxed Python + charts. | https://julius.ai/ |
| Hex Magic | Hex's AI baked into notebooks, SQL + Python + viz generation from natural language. | https://hex.tech/product/magic-ai/ |
| Databricks Assistant | Databricks AI assistant, SQL/PySpark generation + notebook copilot for lakehouse work. | https://www.databricks.com/product/databricks-assistant |
| Snowflake Cortex | AI functions in-warehouse, LLM calls as SQL, agents built on top of Snowflake's corpus. | https://www.snowflake.com/en/data-cloud/cortex/ |
| Datadog Bits AI | Datadog's incident-response AI, investigates alerts, correlates signals, drafts postmortems. | https://www.datadoghq.com/product/platform/bits-ai/ |
| RunWhen | Agentic ops platform, auto-diagnose infra + Kubernetes issues via runbook agents. | https://www.runwhen.com/ |
| Elicit | AI research assistant, semantic search + summarisation across 125M+ academic papers. | https://elicit.com/ |
| Consensus AI | AI-powered search engine over 200M+ research papers: evidence-based answers with citations. | https://consensus.app/ |
| OpenAI Deep Research | ChatGPT mode that plans + browses + synthesises multi-source research reports over 5-30 minutes. | https://openai.com/index/introducing-deep-research/ |
| Gemini Deep Research | Gemini Advanced's multi-step research agent: plans, browses, and synthesises long-form reports. | https://blog.google/products/gemini/google-gemini-deep-research/ |
| Perplexity Deep Research | Perplexity's deep-research mode, plans, browses, and synthesises reports with citation trail. | https://www.perplexity.ai/hub/blog/introducing-perplexity-deep-research |
| Glean | Enterprise search + Work AI, indexes every app you work in, agents built on top. | https://www.glean.com/ |
| Paradox Olivia | Conversational recruiting assistant, screens candidates, schedules interviews at scale for enterprises. | https://www.paradox.ai/ |
| Eightfold AI | AI talent-intelligence platform, matches, screens, and manages talent at enterprise scale. | https://eightfold.ai/ |
| Nous Hermes Agent | The self-improving open-source agent from Nous Research: a built-in learning loop that creates skills from experience, remembers across sessions and runs on any model. MIT-licensed, a CLI plus a messaging gateway into Telegram, Discord, Slack and more. | https://github.com/NousResearch/hermes-agent |