AI Agent Directory

Graph-based orchestration framework for stateful agents with explicit control flow and durable execution.

Minimal agent framework built around agents, handoffs, guardrails, and built-in run tracing.

Role-based multi-agent framework where specialized agents collaborate on tasks as a crew.

Managed headless browser infrastructure that gives agents reliable, observable, scalable web sessions.

Open-source library that lets an LLM drive a real browser to complete tasks on live websites.

Terminal-native coding agent from Anthropic that reads, edits, and runs code directly inside your repository.

Agent mode inside the Cursor editor, planning and applying multi-file changes without leaving the IDE.

Open-source terminal pair programmer that maps your repository and commits every change to git.

Cloud software engineering agent from Cognition that works asynchronously in its own sandboxed environment.

Customer support agent that resolves tickets from your own help content and hands off cleanly when it cannot.

Multi-step research agent that runs dozens of searches and returns a cited report instead of an answer.

Google's planning-first research agent that drafts a search plan you approve before it starts working.

Source-available workflow automation platform with AI agent nodes and self-hosting as a first-class option.

No-code AI agents that act across thousands of connected business apps on triggers you define.