Multistep Agents

Mobile agent that auto-queries, follows links, and composes step-by-step answer pages.

Dev-first open-source autonomous agent framework for building and running multi-step agents.

Open-source platform for autonomous software development agents that execute multi-step work.

Agentic browser that plans multi-step web tasks and generates source-linked research reports.

Chrome agent that searches, summarizes, extracts data, and automates multi-step web actions.

All-in-one assistant/extension with real-time web access for on-page research and actions.

Successor to AutoGen/Semantic Kernel for building and orchestrating multi-agent workflows.

No-code, cross-app agents that monitor triggers, act on the web, and handle multi-step workflows.

Multi-step agentic orchestration to chain steps, add loops, and run parallel paths over data.

Realtime assistant with native tool use and search; designed for deep work and multi-step tasks.

Multi-agent framework that simulates an AI software company with role-structured workflows.

Low-level orchestration for long-running, stateful agents—loops, branches, and retries.

AI software engineer that plans multi-step tasks, runs tests, and creates pull requests.

Autonomous mode that searches widely, reads sources, and synthesizes multi-source findings.

Framework for collaborative multi-agent crews with roles, memory, tools, and guardrails.