# Agentic.ai Directory — Full Reference

> This is the extended version of llms.txt. For the concise version, see: https://agentic.ai/llms.txt
>
> Independent buying verdicts ("which of these should I use for <job>?") are published as public
> sample decision reports — each ranks a category on our 9-dimension /36 rubric plus hands-on deep
> research and names one pick with its trade-offs. Vendor payments cannot influence the ranking
> (code-enforced firewall: https://agentic.ai/methodology). Live sample URLs are listed in https://agentic.ai/llms.txt.
> For programmatic access, see the agent manifest: https://agentic.ai/.well-known/agent.json
> For a human-readable explainer of agentic AI itself (definition, examples, FAQ), see: https://agentic.ai/what-is-agentic-ai
> For inbox-automation tools specifically (top 6 picks ranked by agenticness), see: https://agentic.ai/best/inbox-automation
> For agentic AI platforms for business (ranked by agenticness), see: https://agentic.ai/best/agentic-ai-platforms
> For agentic AI personal assistants (ranked by agenticness), see: https://agentic.ai/best/personal-assistants
> For how we score and why no vendor pays for placement (the code-enforced independence firewall), see: https://agentic.ai/methodology
> To verify a "Certified Agentic AI Product Evaluator" credential (public registry, per-holder verification pages), see: https://agentic.ai/certified

## What is Agentic.ai?

Agentic.ai is a curated directory of AI tools that take autonomous action. We evaluate every tool on a 36-point agenticness scale across 9 dimensions:

1. **Action Capability** (0-4): Can it execute real actions via APIs, tools, or systems?
2. **Autonomy** (0-4): Can it decide next steps dynamically based on context?
3. **Planning & Reasoning** (0-4): Can it decompose goals into multi-step plans?
4. **Adaptation & Recovery** (0-4): Does it adjust based on results and handle errors?
5. **State & Continuity** (0-4): Does it maintain context across interactions?
6. **Reliability** (0-4): Does it produce consistent, predictable results?
7. **Interoperability** (0-4): Can it work with external tools, APIs, and protocols?
8. **Safety & Observability** (0-4): Does it operate within defined guardrails with audit trails?
9. **Operator Sovereignty** (0-4): Is it open-source, BYOK, auditable, with transparent costs?

## Agenticness Levels

- **Reactive Tool** (0-5 pts): Responds to prompts but takes no autonomous action
- **Guided Assistant** (6-12 pts): Executes tasks you assign, one step at a time
- **Adaptive Collaborator** (13-18 pts): Proposes and executes multi-step plans with approval
- **Domain Specialist** (19-25 pts): Handles domain-specific workflows independently
- **Autonomous Operator** (26-31 pts): Manages complex cross-domain workflows with self-correction
- **Strategic Agent** (32-36 pts): Fully self-directed — sets own goals, operates continuously

## Categories — For People (Personal & Consumer)

### General-Purpose AI Agents
URL: https://agentic.ai/c/general-purpose-agents
AI agents that can browse the web, manage files, run code, and take autonomous action on your behalf. From OpenClaw to ChatGPT Agent, these tools go beyond chat to actually do things for you.

### Coding Agents
URL: https://agentic.ai/c/coding-agents
AI that writes, reviews, and ships code. From IDE-integrated copilots like Cursor to autonomous engineers like Devin, these agents are transforming how software gets built.

### Personal Assistants
URL: https://agentic.ai/c/personal-assistants
General-purpose AI assistants for everyday tasks, scheduling, and personal productivity. Examples: Lindy, Reclaim AI, Motion. NOT for domain-specific assistants (use health-wellness, finance-planning, etc. for those).

### Writing & Creativity
URL: https://agentic.ai/c/writing-creativity
AI tools where the PRIMARY purpose is writing, content creation, or creative work. Examples: Sudowrite, Jasper, Copy.ai, Midjourney. NOT for tools that happen to generate text as a secondary feature.

### Browser & Computer Use
URL: https://agentic.ai/c/browser-computer-use
AI agents that control your browser and desktop to complete tasks. From Claude Computer Use to Chrome Auto Browse, these tools interact with existing software on your behalf.

### Research & Deep Analysis
URL: https://agentic.ai/c/research-deep-analysis
AI agents for deep research, fact-finding, and synthesis. These tools go beyond search to analyze multiple sources, produce structured reports, and surface insights you'd miss on your own.

### Learning & Education
URL: https://agentic.ai/c/learning-education
AI tutors, study assistants, and learning companions where EDUCATION is the primary purpose. Examples: Learny AI, Duolingo Max, Khanmigo. NOT for tools that have educational content but serve another primary purpose.

### Health & Wellness
URL: https://agentic.ai/c/health-wellness
AI for fitness, mental health, nutrition, medical guidance, and wellbeing. Examples: Ada Health, Fitbit AI, Wysa. This is the category for health-focused tools even if they have automation or learning features.

### Finance & Planning
URL: https://agentic.ai/c/finance-planning
Personal finance AI, budgeting, investing, and financial planning tools. Examples: Wealthfront, YNAB, Trim, Cleo. This is the category for finance-focused tools even if they automate financial tasks.

### Home & Automation
URL: https://agentic.ai/c/home-automation
Smart home AI, IoT automation, and household management. Examples: Home Assistant, SmartThings. For consumer home/life automation, NOT business workflow automation.

### Music & Audio Generation
URL: https://agentic.ai/c/music-generation
AI tools for composing music, generating soundtracks, and producing audio. From text-to-song generators to cinematic soundtrack composers, these tools help you create music without traditional instruments.

### Video & Media Production
URL: https://agentic.ai/c/video-media-production
AI for creating, editing, and producing video content. From text-to-video generation to AI-powered podcast editing and real-time video translation, these tools transform media production.

### Design & Visual Creation
URL: https://agentic.ai/c/design-ai
AI tools for graphic design, UI/UX, presentations, and visual content. Generate layouts, create brand-consistent designs, and build polished visuals from natural language prompts.

### Translation & Localization
URL: https://agentic.ai/c/translation-localization
AI-powered translation and localization tools for documents, websites, and software. Go beyond word-for-word translation with context-aware AI that handles technical terminology and brand voice.


## Categories — For Teams (Business & Builders)

### Sales & Marketing
URL: https://agentic.ai/c/sales-marketing
AI agents for lead generation, sales outreach, content marketing, and campaign automation. Examples: Reply.io, Conversica, Regie.ai, Drift. Primary purpose must be sales/marketing.

### Customer Support
URL: https://agentic.ai/c/customer-support
AI-powered support agents, help desk automation, and customer service. Examples: Forethought, Ultimate.ai, Intercom Fin, Zendesk AI. For tools where PRIMARY purpose is customer support.

### Engineering & DevTools
URL: https://agentic.ai/c/engineering-devtools
AI coding assistants, code review tools, and developer productivity solutions for teams. Write code faster, catch bugs earlier, and automate the tedious parts of software development.

### Data & Analytics
URL: https://agentic.ai/c/data-analytics
AI for data analysis, business intelligence, visualization, and reporting. Examples: ThoughtSpot, Julius, Powerdrill. Primary purpose must be working with data/analytics.

### Workflow Automation
URL: https://agentic.ai/c/workflow-automation
GENERAL-PURPOSE workflow automation platforms that connect multiple apps/services. Examples: Zapier, Make, n8n, Relay. NOT for domain-specific tools - use their domain category instead (finance-planning for financial automation, sales-marketing for sales automation, etc.).

### Agent Frameworks & Orchestration
URL: https://agentic.ai/c/agent-frameworks
Open-source frameworks and SDKs for building custom AI agents. From LangChain to CrewAI, these tools let developers create, orchestrate, and deploy multi-agent systems.

### Agent Infrastructure
URL: https://agentic.ai/c/agent-infrastructure
The plumbing layer for AI agents: memory systems, tool integrations, observability, sandboxing, and identity management. Essential building blocks for production agent deployments.

### Enterprise Agent Platforms
URL: https://agentic.ai/c/enterprise-agent-platforms
Full-stack platforms for deploying AI agents at organizational scale. Built-in governance, compliance, audit trails, and admin controls for enterprises that need agents they can trust.

### Research & Intelligence
URL: https://agentic.ai/c/research-intelligence
AI for market research, competitive intelligence, deep analysis, and knowledge synthesis. Examples: Perplexity Pro, Elicit. Primary purpose must be research/analysis.

### HR & Operations
URL: https://agentic.ai/c/hr-operations
AI for recruiting, HR processes, expense management, and operational efficiency. Examples: Fyle, Moveworks. For tools where HR/ops is the primary domain.

### Legal AI
URL: https://agentic.ai/c/legal-ai
AI for contract review, legal research, compliance, and document analysis. These tools help legal teams draft, review, and manage contracts faster while reducing risk.

### Cybersecurity AI
URL: https://agentic.ai/c/cybersecurity-ai
AI-powered threat detection, security operations, and vulnerability management. Autonomous security agents that detect, investigate, and respond to threats in real time.

### Supply Chain & Logistics
URL: https://agentic.ai/c/supply-chain-logistics
AI for demand forecasting, supply chain optimization, and logistics management. Predict demand, optimize inventory, and gain real-time visibility across your supply chain.

### Architecture & Building Design
URL: https://agentic.ai/c/architecture-building-ai
AI for architectural design, building configuration, and construction planning. Generate floor plans, optimize building layouts, and analyze environmental impact with generative AI.

### Event Planning & Management
URL: https://agentic.ai/c/event-planning-ai
AI for event management, attendee matchmaking, and conference coordination. Automate scheduling, personalize attendee experiences, and optimize event logistics.

### Voice & Phone Agents
URL: https://agentic.ai/c/voice-phone-agents
AI agents for voice interactions, phone calls, and conversational interfaces. Build and deploy voice bots, automate phone outreach, and create natural speech-to-speech experiences with ultra-low latency.

### Browser Automation Agents
URL: https://agentic.ai/c/browser-automation
AI agents that autonomously browse the web, interact with websites, fill forms, extract data, and complete multi-step browser tasks. From headless automation to visual browsing agents.

### Multi-Agent Orchestration
URL: https://agentic.ai/c/multi-agent-orchestration
Frameworks and platforms for coordinating multiple AI agents working together. Build agent teams, manage inter-agent communication, and orchestrate parallel workflows with shared memory and tool access.


## Top Listings (by Agenticness Score)

- **CorvinOS** — Score: 24/36 (Domain Specialist)
  CorvinOS is an open-source AI operating system for teams that need pluggable engines, audited workflows, and compliance controls. It combines browser-based chat, voice and messaging bridges, data connectors, and multi-step orchestration in one platform.
  Categories: Enterprise Agent Platforms
  URL: https://agentic.ai/t/corvinos
- **Bernstein** — Score: 23/36 (Domain Specialist)
  Bernstein runs multiple CLI coding agents in isolated git worktrees, then verifies and merges only the diffs that pass checks. It is designed for reproducible, on-prem agent workflows with signed audit logs and offline review.
  Categories: Multi-Agent Orchestration
  URL: https://agentic.ai/t/bernstein-multi-agent-orchestration
- **Gobii** — Score: 21/36 (Domain Specialist)
  Gobii is an AI agent platform for automating web-based work through browser actions, email, SMS, and APIs. It’s built for individuals, teams, and developers who need repeatable workflows handled without manual effort.
  Categories: Enterprise Agent Platforms
  URL: https://agentic.ai/t/gobii
- **Claude Code** — Score: 20/36 (Domain Specialist)
  Claude Code is Anthropic's agentic coding tool that lives in your terminal. It understands your entire codebase, makes multi-file edits, runs commands, manages git workflows, and uses MCP for tool integration. Built with a Unix philosophy — it reads, plans, edits, and verifies in a loop. The fastest-growing product in the coding agent category.
  Categories: Coding Agents
  URL: https://agentic.ai/t/claude-code
- **OpenClaw** — Score: 20/36 (Domain Specialist)
  OpenClaw is a personal AI assistant that goes beyond chat and can run tasks, remember context, and act across connected tools. It is aimed at people who want an agent they can message like a coworker and let keep working in the background.
  Categories: General-Purpose AI Agents
  URL: https://agentic.ai/t/openclaw
- **Yutori API** — Score: 19/36 (Domain Specialist)
  Yutori provides APIs for browser automation, research, and recurring scouting tasks. It is built for teams and developers who want agents that can take web actions, monitor changes, and return results through APIs and logs.
  Categories: Browser Automation Agents
  URL: https://agentic.ai/t/yutori-delegate
- **Goose** — Score: 19/36 (Domain Specialist)
  Goose is an on-machine AI agent that can automate development tasks from start to finish. It runs locally, works with any LLM, and connects to MCP servers or APIs for broader tool access.
  Categories: Engineering & DevTools
  URL: https://agentic.ai/t/goose
- **Factory AI** — Score: 19/36 (Domain Specialist)
  Factory provides Droid, an AI agent you can use in coding workflows and IDE integrations like Zed. It connects through login or API key setup and charges usage with Standard Tokens across multiple models.
  Categories: Agent Infrastructure, Coding Agents
  URL: https://agentic.ai/t/factory-ai
- **KaroX** — Score: 19/36 (Domain Specialist)
  KaroX turns a local Git repository into a controlled workspace for AI coding clients. It is aimed at developers who want AI to inspect code, run checks, and make approved changes without giving it unrestricted access.
  Categories: Agent Infrastructure
  URL: https://agentic.ai/t/karox
- **Perplexity Computer** — Score: 19/36 (Domain Specialist)
  Perplexity Computer orchestrates 19 different AI models simultaneously — routing each subtask to the optimal model (Claude for reasoning, Gemini for deep research, GPT for long context). Tasks run in isolated Firecracker microVMs with 400+ app integrations and can persist for hours, days, or months. Requires Perplexity Max ($200/month).
  Categories: Browser & Computer Use, General-Purpose AI Agents
  URL: https://agentic.ai/t/perplexity-computer
- **OpenHands** — Score: 18/36 (Adaptive Collaborator)
  OpenHands (formerly OpenDevin) is a fully autonomous open-source AI coding agent. MIT-licensed core, plans + executes Python actions via CodeAct, uses browser + terminal + files. ~72% on SWE-bench Verified with Sonnet 4.5 via the OpenHands Software Agent SDK (arXiv:2511.03690).
  Categories: Coding Agents
  URL: https://agentic.ai/t/openhands
- **Cline** — Score: 18/36 (Adaptive Collaborator)
  Cline is an AI coding assistant for VS Code that can inspect your project, edit files, run terminal commands, and use a browser while asking for permission at each step. It is aimed at developers working on real codebases who want more than code completion.
  Categories: Coding Agents
  URL: https://agentic.ai/t/cline
- **Cursor** — Score: 18/36 (Adaptive Collaborator)
  Cursor is a developer-focused AI environment that adds agents, context, and automation around your repositories. It combines an editor-like interface, a CLI, and a cloud agent API to automate code review, bug fixing, CI hygiene, and more. Designed for individual developers and engineering teams who want AI to take real actions in their code and infrastructure, not just chat.
  Categories: Coding Agents
  URL: https://agentic.ai/t/cursor-ai
- **Google ADK** — Score: 17/36 (Adaptive Collaborator)
  Agent Development Kit (ADK) is a framework for developers building AI agents and multi-agent workflows. It supports Python, TypeScript, Go, and Java, and is designed to run across different models and deployment setups.
  Categories: Agent Frameworks & Orchestration
  URL: https://agentic.ai/t/google-adk
- **Hermes Agent** — Score: 17/36 (Adaptive Collaborator)
  Hermes Agent is an open-source autonomous agent from Nous Research that runs on your server and keeps context over time. It can work across chat apps, the CLI, and the browser to handle multi-step tasks and scheduled automations.
  Categories: General-Purpose AI Agents
  URL: https://agentic.ai/t/hermes-agent
- **Devin** — Score: 17/36 (Adaptive Collaborator)
  Devin is Cognition's cloud agent — distinct from Devin Desktop, the IDE formerly called Windsurf. It helps engineering teams delegate coding tasks like migrations, refactors, and bug fixes, working with Slack, Teams, Linear, and Jira, then planning, testing, and opening PRs for human review.
  Categories: Coding Agents
  URL: https://agentic.ai/t/devin
- **Claude** — Score: 17/36 (Adaptive Collaborator)
  Claude is Anthropic's flagship AI assistant, known for thoughtful reasoning, strong safety practices, and extensive capabilities. Claude Computer Use controls your desktop, Claude Cowork manages background tasks, and Dispatch lets you assign work from your phone. Available as web app, API, and mobile.
  Categories: Browser & Computer Use, General-Purpose AI Agents
  URL: https://agentic.ai/t/claude
- **Stagehand** — Score: 17/36 (Adaptive Collaborator)
  Stagehand is an open-source browser automation SDK built for developers and LLM-powered agents. It combines code-based browser control with natural-language actions so you can build web workflows that are more resilient to page changes.
  Categories: Browser Automation Agents
  URL: https://agentic.ai/t/stagehand
- **Devin Desktop** — Score: 17/36 (Adaptive Collaborator)
  Devin Desktop (formerly Windsurf, and distinct from Cognition's cloud agent Devin) is an AI-native desktop app for developers. It keeps the full IDE — editor, syntax highlighting, autocomplete, debugging — and adds a command centre for running and coordinating multiple coding agents in one place. Available for Mac, Windows, and Linux.
  Categories: Coding Agents
  URL: https://agentic.ai/t/devin-desktop
- **AICode** — Score: 17/36 (Adaptive Collaborator)
  AICode is a VS Code extension for enterprise teams working in large legacy codebases. It maps dependencies and architecture, audits specifications before coding, and keeps changes reviewable inside your infrastructure.
  Categories: Coding Agents
  URL: https://agentic.ai/t/aicode
- **GitHub Copilot** — Score: 17/36 (Adaptive Collaborator)
  GitHub Copilot helps you write, review, and adapt code directly in GitHub, your IDE, and the terminal. It supports everything from inline suggestions to agentic coding workflows with broader model choices and enterprise controls.
  Categories: Coding Agents
  URL: https://agentic.ai/t/github-copilot
- **Zencoder** — Score: 16/36 (Adaptive Collaborator)
  Zencoder links with 20+ developer tools so you can turn issues, alerts, and tasks into code changes faster. It’s built for teams that want to reduce context switching across Jira, GitHub, Sentry, CI/CD, and observability tools.
  Categories: Engineering & DevTools, Coding Agents
  URL: https://agentic.ai/t/zencoder
- **Intercom Fin** — Score: 16/36 (Adaptive Collaborator)
  Fin is Intercom’s AI agent for customer support teams. It answers questions, takes action in connected systems, and escalates to human agents when needed.
  Categories: Customer Support
  URL: https://agentic.ai/t/intercom-fin
- **Decomposer** — Score: 16/36 (Guided Assistant)
  Decomposer turns an idea into a structured execution plan in about a minute. It labels each step as yours, AI’s, or an expert’s, then helps you work through the plan one task at a time.
  Categories: Personal Assistants
  URL: https://agentic.ai/t/decomposer
- **ThumbGate** — Score: 16/36 (Guided Assistant)
  ThumbGate sits in front of coding-agent tool calls and blocks risky repeats before they run. It turns thumbs-up and thumbs-down feedback into reusable rules, with local use for individuals and paid options for dashboards, sync, and team visibility.
  Categories: Agent Infrastructure
  URL: https://agentic.ai/t/thumbgate
- **ChatGPT** — Score: 16/36 (Adaptive Collaborator)
  ChatGPT is OpenAI's flagship AI product used by 900 million people weekly. It handles conversation, code generation, data analysis, image creation, web browsing, and file processing. Agent mode lets it execute multi-step tasks with tool use. Available as web app, mobile app, desktop app, and API.
  Categories: General-Purpose AI Agents
  URL: https://agentic.ai/t/chatgpt
- **Browser Use** — Score: 16/36 (Adaptive Collaborator)
  browser-use helps you build agents that interact with websites, fill forms, and complete web tasks. It supports both a self-hosted open-source library and a cloud option for faster setup and scaling.
  Categories: Browser Automation Agents, Browser & Computer Use
  URL: https://agentic.ai/t/browser-use
- **Driftless** — Score: 15/36 (Adaptive Collaborator)
  driftless turns paired PRDs and tech specs into tracked, gated delivery work. It uses persistent agents to write, test, and verify software instead of just tracking tasks.
  Categories: Coding Agents
  URL: https://agentic.ai/t/driftless
- **LocalTry** — Score: 15/36 (Adaptive Collaborator)
  LocalTry combines CRM, scheduling, sales, marketing, reputation management, and automation in one business workspace. It is designed for small service teams that want AI to help carry work forward, not just answer questions.
  Categories: Sales & Marketing
  URL: https://agentic.ai/t/localtry
- **11x Alice** — Score: 15/36 (Adaptive Collaborator)
  11x Alice is an AI outbound sales worker for teams that want to scale prospecting without hiring more SDRs. It handles multi-channel outreach, lead enrichment, CRM sync, and deliverability setup from one platform.
  Categories: Sales & Marketing
  URL: https://agentic.ai/t/11x
- **Runloop AI** — Score: 15/36 (Adaptive Collaborator)
  Runloop AI provides sandboxed devboxes for agent workflows, including turn-based interaction through GitHub pull requests. It’s aimed at developers building coding agents that need to execute commands, keep state across turns, and respond to reviewer comments.
  Categories: Agent Infrastructure
  URL: https://agentic.ai/t/runloop
- **ChatGPT Deep Research** — Score: 15/36 (Adaptive Collaborator)
  An agent inside ChatGPT that independently searches, analyzes, and synthesizes large amounts of online information. It’s built for research-heavy tasks where you need a documented answer, not just a quick summary.
  Categories: Research & Deep Analysis
  URL: https://agentic.ai/t/chatgpt-deep-research
- **Notion AI** — Score: 15/36 (Adaptive Collaborator)
  Notion AI helps teams search, generate, analyze, and chat directly inside Notion. It also includes agents that can complete multi-step work using context from your workspace and connected apps.
  Categories: Enterprise Agent Platforms
  URL: https://agentic.ai/t/notion-ai
- **Wingman by Emergent** — Score: 14/36 (Adaptive Collaborator)
  Wingman is a messaging-first autonomous AI agent by Emergent. It connects to your email, calendar, Slack, CRM, and GitHub, then handles scheduling, research, sales support, and admin tasks through WhatsApp and Telegram conversations.
  Categories: Personal Assistants
  URL: https://agentic.ai/t/wingman-by-emergent
- **Kilo Code** — Score: 14/36 (Adaptive Collaborator)
  Kilo Code is the v5.x community fork of Roo Code (which was archived May 15, 2026). Open-source VS Code extension for agentic coding — Apache 2.0 licensed, BYOK across many providers, runs locally as an IDE extension.
  Categories: Coding Agents
  URL: https://agentic.ai/t/kilo-code
- **HouseWhisper** — Score: 14/36 (Adaptive Collaborator)
  HouseWhisper follows up with real estate leads, nurtures them over time, and routes ready prospects to the right agent. It connects to existing CRMs, dialers, and calendars so teams can work from their current stack.
  Categories: Sales & Marketing
  URL: https://agentic.ai/t/housewhisper
- **BrowserAct** — Score: 14/36 (Adaptive Collaborator)
  BrowserAct provides a managed browser environment for AI agents to browse the web, extract data, and handle blocked pages. It also offers proxy, fingerprint, and human hand-off infrastructure for multi-step web workflows.
  Categories: Browser Automation Agents
  URL: https://agentic.ai/t/browseract
- **Jules** — Score: 14/36 (Adaptive Collaborator)
  Jules helps you offload coding chores like bug fixes, test work, and version bumps. It works with GitHub, runs code in a cloud VM, and asks for approval before it turns changes into a PR.
  Categories: Coding Agents
  URL: https://agentic.ai/t/google-jules
- **Augment Code** — Score: 14/36 (Adaptive Collaborator)
  Augment Code is an enterprise-focused AI coding agent built around a 200K-token Context Engine. Closed-source SaaS with strong SWE-bench Verified results (70.6% self-reported) and the highest accuracy on the only public benchmark for AI-assisted code review.
  Categories: Coding Agents
  URL: https://agentic.ai/t/augment-code
- **Decagon** — Score: 14/36 (Adaptive Collaborator)
  Decagon is a customer support AI platform with voice and guardrails built for enterprise use. It helps teams deploy agents across support workflows with authentication, encryption, audit logs, and resiliency controls.
  Categories: Voice & Phone Agents, Agent Infrastructure
  URL: https://agentic.ai/t/decagon
- **Agentic News** — Score: 14/36 (Guided Assistant)
  Agentic News monitors thousands of sources for topics you choose, then turns the results into deduplicated briefings and AI answers. It is aimed at people who need ongoing monitoring for competitors, markets, regulations, or niche interests. 
  Categories: Research & Intelligence, Research & Deep Analysis, Learning & Education
  URL: https://agentic.ai/t/agentic-news
- **SentinelOne Purple AI** — Score: 14/36 (Adaptive Collaborator)
  Purple AI helps security teams investigate alerts, hunt threats, and trigger response workflows inside SentinelOne’s Singularity Platform. It turns natural-language questions into security queries and can synthesize evidence into explainable AI verdicts.
  Categories: Cybersecurity AI
  URL: https://agentic.ai/t/sentinelone-purple-ai
- **Zapier** — Score: 14/36 (Adaptive Collaborator)
  Zapier helps you connect apps, move data, and build multi-step automations without code. It now bundles Zaps, Tables, Forms, and Zapier MCP into unified plans for individuals, teams, and enterprises.
  Categories: Workflow Automation
  URL: https://agentic.ai/t/zapier
- **LocalAI** — Score: 14/36 (Adaptive Collaborator)
  LocalAI’s Realtime API lets you build voice and text experiences over WebSocket or WebRTC using an OpenAI-compatible protocol. It is aimed at developers who want a self-hosted, configurable realtime layer with their own VAD, STT, LLM, and TTS components.
  Categories: Agent Infrastructure
  URL: https://agentic.ai/t/localai
- **Prismor** — Score: 14/36 (Adaptive Collaborator)
  Prismor helps you control what coding agents can do before commands run. It combines a CLI, GitHub App, CI/build scanning, and MCP support for scanning dependencies, code, secrets, and agent actions.
  Categories: Agent Infrastructure, Cybersecurity AI
  URL: https://agentic.ai/t/prismor
- **StackAI** — Score: 14/36 (Adaptive Collaborator)
  StackAI is an enterprise platform for building and deploying AI agents through a visual interface. It is aimed at teams that need secure integrations, access controls, and compliance-focused deployment.
  Categories: Enterprise Agent Platforms
  URL: https://agentic.ai/t/stackai
- **Sierra AI** — Score: 14/36 (Adaptive Collaborator)
  Sierra Voice brings conversational AI to phone support, with agents that can talk naturally, handle interruptions, and act inside your internal systems. It’s built for customer experience teams that want to replace or augment traditional call flows with a more adaptive voice agent.
  Categories: Voice & Phone Agents, Customer Support
  URL: https://agentic.ai/t/sierra-ai
- **Ultimate (Zendesk)** — Score: 13/36 (Adaptive Collaborator)
  Zendesk AI Agents helps customer support teams automate conversations across channels and resolve common issues with AI. It connects to your existing customer emails, apps, and team workflows, with setup positioned as quick for non-technical teams.
  Categories: Customer Support
  URL: https://agentic.ai/t/ultimate
- **Relay** — Score: 13/36 (Adaptive Collaborator)
  Relay.app helps you build AI-driven workflows that connect tools like Gmail, Notion, HubSpot, and other apps. It is aimed at teams that want agents to take actions across systems without writing code.
  Categories: Enterprise Agent Platforms, Multi-Agent Orchestration, Workflow Automation
  URL: https://agentic.ai/t/relay
- **Tradehand** — Score: 13/36 (Adaptive Collaborator)
  Tradehand is an AI-powered office system for trade businesses that handles enquiries, quotes, bookings, job updates, and invoice chasing. It charges no monthly fee and takes 5% of invoice payments it collects.
  Categories: Sales & Marketing
  URL: https://agentic.ai/t/tradehand

## All Tags

- Copilot (Human-in-Loop) (copilot-mode) [autonomy]
- Fully Autonomous (fully-autonomous) [autonomy]
- Semi-Autonomous (semi-autonomous) [autonomy]
- A2A Support (a2a-support) [capability]
- Code Execution (code-execution) [capability]
- Computer Use (computer-use) [capability]
- File Access (file-access) [capability]
- Integrations (integrations) [capability]
- MCP Support (mcp-support) [capability]
- Memory (memory) [capability]
- Multi-Agent (multi-agent) [capability]
- RAG (rag) [capability]
- Vision (vision) [capability]
- Voice (voice) [capability]
- Web Browsing (web-browsing) [capability]
- Cloud Hosted (cloud-hosted) [deployment]
- Hybrid (hybrid-deployment) [deployment]
- On-Device / Edge (on-device) [deployment]
- Self-Hosted (self-hosted) [deployment]
- Model Agnostic (model-agnostic) [model]
- Supports Local Models (supports-local-models) [model]
- API (api) [platform]
- Android (android) [platform]
- CLI (cli) [platform]
- Chrome Extension (chrome-extension) [platform]
- Desktop (desktop) [platform]
- Discord (discord) [platform]
- IDE Extension (ide-extension) [platform]
- Slack (slack) [platform]
- Web (web) [platform]
- iOS (ios) [platform]
- Enterprise (enterprise) [pricing]
- Free Tier (free-tier) [pricing]
- Freemium (freemium) [pricing]
- Open Source (open-source) [pricing]
- Paid (paid) [pricing]
- Usage-Based (usage-based) [pricing]
- B2B (b2b) [use-case]
- B2C (b2c) [use-case]
- For Developers (developer) [use-case]
- For Teams (for-teams) [use-case]
- No-Code (no-code) [use-case]

## Structured Fields

Each listing includes structured attributes for filtering and comparison:
- deploymentModel: CLOUD | SELF_HOSTED | HYBRID | ON_DEVICE
- autonomyLevel: COPILOT | SEMI_AUTONOMOUS | FULLY_AUTONOMOUS
- modelAgnosticism: SINGLE_MODEL | MULTI_MODEL | SUPPORTS_LOCAL
- teamSupport: INDIVIDUAL_ONLY | SMALL_TEAM | ENTERPRISE
- pricingModel: FREE_OSS | FREEMIUM | SUBSCRIPTION | PER_SEAT | USAGE_BASED | HYBRID
- mcpSupport: boolean (Model Context Protocol)
- openSource: boolean
- primaryInterface: chat, gui, cli, voice, browser, ide, api

## Tool Comparison

Compare any two tools side-by-side:
- Web: https://agentic.ai/compare/{slug1}-vs-{slug2}
- API: GET https://agentic.ai/api/v1/compare?tools={slug1},{slug2}
- MCP: compare_listings tool

## Public API Quick Start

Base URL: https://agentic.ai/api/v1

```bash
# List all categories
curl https://agentic.ai/api/v1/categories

# Search for tools
curl "https://agentic.ai/api/v1/search?q=code+review"

# Get a specific listing with all structured fields
curl https://agentic.ai/api/v1/listings/cursor

# Browse open-source coding agents
curl "https://agentic.ai/api/v1/listings?category=coding-agents&openSource=true&sort=score"

# Filter by deployment model and MCP support
curl "https://agentic.ai/api/v1/listings?deployment=SELF_HOSTED&mcpSupport=true"

# Compare two tools
curl "https://agentic.ai/api/v1/compare?tools=cursor,claude-code"
```

Full OpenAPI spec: https://agentic.ai/openapi.json

## MCP (Model Context Protocol) Server

Endpoint: https://agentic.ai/mcp (streamable HTTP, stateless)

10 tools: search_listings, semantic_search, get_listing, compare_listings, get_agenticness_details, recommend_tools, list_categories, get_category, list_tags, list_recent

## Dataset Downloads

- JSON: https://agentic.ai/data/directory.json (includes all structured fields)
- CSV: https://agentic.ai/data/directory.csv
- License: CC BY 4.0 (attribution required)
- Policy: https://agentic.ai/api-policy

## Contact

hello@agentic.ai

Generated: 2026-08-13