Agentforce
Salesforce's platform for building agents that work on CRM data for service, sales and marketing teams inside Salesforce.
Microsoft Copilot Studio
Low-code tool for building agents that run in Microsoft 365, Teams and websites, with connectors to Microsoft and outside systems.
Relevance AI
No-code platform for building teams of business agents with tools, triggers and approval steps, often used for sales and ops work.
Cassidy
Workplace assistant and workflow builder that answers from company documents and runs multi-step tasks for teams.
Beam AI
Platform for building agents that run back-office processes such as order handling and invoice work, with human review steps.
Vertex AI Agent Builder
Google Cloud's set of tools for building, deploying and grounding agents on company data inside a Google Cloud project.
- Developer API
Amazon Bedrock Agents
AWS feature for building agents that call your APIs and knowledge bases, using foundation models hosted in Amazon Bedrock.
- Developer API
Writer
Enterprise AI platform with its own models and tools for building agents that follow company style, data and review rules.
LangGraph
Library for building agents as graphs of steps with saved state, pauses for human review and streaming, in Python and JavaScript.
- Open source
- Can run on your own servers
CrewAI
Python framework for multi-agent work where each agent has a role and goal and a crew of agents shares a list of tasks.
- Open source
- Can run on your own servers
AutoGen
Microsoft's open-source framework for multi-agent conversations, with a Python API and a low-code studio for testing agent teams.
- Open source
- Can run on your own servers
LlamaIndex
Framework for agents that work over your documents, with data loaders, indexing, retrieval and event-driven workflows.
- Open source
OpenAI Agents SDK
Lightweight SDK for agents with tools, handoffs between agents, guardrails and built-in tracing, available for Python and TypeScript.
- Open source
- Works with MCP
Pydantic AI
Python agent framework from the Pydantic team that uses type hints to validate tool inputs and structured model outputs.
- Open source
- Works with MCP
Semantic Kernel
Microsoft SDK for adding models, plugins and agents to apps written in C#, Python and Java.
- Open source
smolagents
Small Python library from Hugging Face for agents that write and run code as their actions, with any model you choose.
- Open source
Mastra
TypeScript framework for agents, workflows, memory and evals, aimed at web developers working in Node.js.
- Open source
- Works with MCP
Agent Development Kit
Google's open-source kit for building and testing single and multi-agent systems, with a local web UI for debugging runs.
- Open source
Letta
Platform and open-source server for stateful agents that keep long-term memory across sessions, from the MemGPT research team.
- Open source
- Developer API
Haystack
Python framework from deepset for building retrieval pipelines and agents from swappable components.
- Open source
Devin
Autonomous coding agent that works in its own cloud environment and opens pull requests for your team to review.
OpenHands
Open-source coding agent that edits code, runs commands and browses in a sandbox, with a hosted cloud version.
- Open source
- Can run on your own servers
Replit Agent
Agent inside Replit that builds and changes apps from a plain-language request, then runs and deploys them on Replit.
goose
Open-source agent from Block that runs on your machine, edits code, runs commands and connects to tools through MCP.
- Open source
- Can run on your own servers
- Works with MCP
Gemini Deep Research
Feature in the Gemini app that plans a search, reads many web pages and writes a cited report on your question.
ChatGPT deep research
ChatGPT mode that browses and reads sources for several minutes, then returns a long report with citations.
Undermind
Research agent for scientific literature that searches papers step by step and explains which ones match your question.
Exa
Search engine API built for AI apps, returning links and page contents that agents can read directly.
- Developer API
Tavily
Web search and extraction API made for agents, returning short cleaned results instead of a page of links.
- Developer API
11x
Digital sales workers that research accounts, send outreach and answer inbound calls for sales teams.
Qualified
Inbound sales agent for B2B websites that talks with visitors, qualifies them and books meetings with reps.
Conversica
Email and chat agents that follow up with leads and past customers until they are ready to talk to a person.
Sierra
Customer service agents for large brands that answer, take actions in back-office systems and hand off to staff.
Decagon
Support agents for chat, email and voice that follow written procedures and report on what customers ask about.
Crescendo
Customer experience service that pairs AI agents with its own human support staff across chat, email and voice.
Maven AGI
Support agent platform that answers customers from help content and connected systems, with copilots for human agents.
Zowie
Customer service agent for ecommerce and consumer brands that handles order questions and actions in store systems.
Vapi
Developer platform for phone and web voice agents where you choose the speech, language and voice models.
- Developer API
Retell AI
Platform for building phone agents that answer and place calls, with call flows, transfers and post-call analysis.
- Developer API
Bland
Phone agent platform for enterprises that handles inbound and outbound calls through scripted pathways and an API.
- Developer API
Synthflow
No-code builder for voice agents that answer calls, book appointments and connect to CRMs and calendars.
ElevenLabs Agents
ElevenLabs platform for voice agents that use its speech models, with tools, knowledge bases and phone integration.
- Developer API
Parloa
Voice agent platform for large contact centers, built to handle customer calls and route them to staff.
LiveKit Agents
Open-source framework for real-time voice and video agents on LiveKit's media servers, with phone support.
- Open source
- Developer API
Manus
General agent that works in its own cloud computer to browse, write code and produce files from a single request.
Simular
Desktop agent that operates apps on your computer by reading the screen and using the mouse and keyboard.
UI-TARS Desktop
Open-source desktop app from ByteDance that controls a computer through a vision model reading screenshots.
- Open source
- Can run on your own servers
Open Interpreter
Open-source tool that lets a model run code on your own computer to complete tasks you describe in a terminal.
- Open source
- Can run on your own servers
UFO
Open-source Microsoft research agent that completes tasks across Windows apps using the screen and app controls.
- Open source
- Can run on your own servers
E2B
Cloud sandboxes where agents can run generated code and use a file system without touching your servers.
- Open source
- Developer API
Composio
Library of ready tool integrations for agents, with managed login for each user's apps and MCP support.
- Developer API
- Works with MCP
Arcade
Tool-calling platform that lets agents act in apps such as email and calendars on behalf of a signed-in user.
- Developer API
Smithery
Registry for finding, installing and hosting MCP servers that give agents access to outside tools and data.
- Works with MCP
Mem0
Memory layer that stores facts from past conversations so agents can recall user preferences later.
- Open source
- Developer API
Zep
Memory and context service that builds a knowledge graph from chats and business data for agents to query.
- Developer API
Model Context Protocol
Open protocol for connecting AI apps to tools and data through small servers that any compatible client can use.
- Open source
- Works with MCP
Daytona
Secure sandboxes for running AI-generated code, with SDKs to start, control and snapshot each environment.
- Open source
- Developer API
LangSmith
Tracing, evaluation and monitoring platform for agents and LLM apps, usable with or without LangChain.
- Developer API
Langfuse
Open-source platform for tracing, prompt management and evaluation of LLM apps, self-hosted or as a cloud service.
- Open source
- Can run on your own servers
- Developer API
Arize Phoenix
Open-source tool for tracing and evaluating LLM apps, built on OpenTelemetry and runnable on a laptop or server.
- Open source
- Can run on your own servers
Braintrust
Evaluation and logging platform where teams compare prompt and model versions against test sets before shipping.
W&B Weave
Weights & Biases toolkit for tracing LLM and agent calls and running evaluations, tied to its experiment tracking.
- Open source
Helicone
Open-source proxy and dashboard that logs model requests, cost and latency with a one-line change to your API base URL.
- Open source
- Can run on your own servers
AgentOps
Monitoring for agent runs that records sessions, tool calls and costs, with SDK integrations for common frameworks.
Galileo
Evaluation and monitoring platform for agents with metrics for tool selection, task completion and safety checks.
Opik
Open-source tool from Comet for logging traces, running evaluations and testing prompts for LLM apps and agents.
- Open source
- Can run on your own servers
promptfoo
Open-source command-line tool for testing prompts and agents against test cases and probing them for security issues.
- Open source
- Can run on your own servers
Guardrails AI
Open-source framework for checking model inputs and outputs against validators before an app acts on them.
- Open source
Nothing matches. Try a shorter word, or browse the categories.