AI agents

Open-source AI pair programmer for the terminal. Edit your codebase by chatting in a CLI, with Git-native diffs and commits for every change.

Open-source Python framework for orchestrating multiple AI agents as a "crew" — each agent has a role, goal, and tools, and they collaborate to complete tasks.

Autonomous software engineer that takes a task, plans the work, writes the code, runs the tests, and reports back with a pull request — without supervision in between.

Google's autonomous research agent that plans a multi-step investigation across the web, gathers sources, and produces a structured report with citations.

Visual workflow automation platform with deep AI integration. Build agents that connect 2,000+ apps through a drag-and-drop canvas, no code required.

Browser automation agent that performs tasks on websites for you — booking, ordering, filling forms, gathering data — through a Chrome extension or API.

Google's research agent that ingests your sources — PDFs, articles, transcripts, links — and produces grounded summaries, study guides, and surprisingly good audio overviews.

OpenAI's agentic mode that controls a virtual browser to complete tasks on the open web — booking, ordering, researching, filling forms — under live user supervision.

Web-based agent that scaffolds, builds, and deploys full-stack applications from a natural language prompt. Runs in Replit's browser IDE with no local setup.

Voice agent platform that handles inbound and outbound calls with low-latency conversational AI. Build the agent in a dashboard, deploy to a phone number in minutes.

VS Code fork built around an AI-first editing model. Tab to autocomplete multi-line edits, Cmd-K to refactor, Composer to rewrite across files.

Enterprise customer support agent that handles tier-1 tickets autonomously across email, chat, and voice. Trained on your help center, ticket history, and policies.

Conversational data analyst that runs Python and SQL on your spreadsheets, CSVs, and databases. Ask in plain English; get charts, tables, and statistical results back.

AI writing tool built specifically for fiction. Continues your prose in your voice, brainstorms scene options, and edits chapter-length passages with surgical control.

Developer platform for building voice AI agents that make and answer phone calls. Bring your own LLM, TTS, and STT; Vapi handles the real-time orchestration.

Open-source Python framework that lets any LLM control a real browser — navigate, click, fill forms, scrape, log in, and stay logged in.

Anthropic's terminal-native coding agent. Reads your codebase, writes patches, runs commands, and iterates until tests pass.

LangChain's graph-based framework for building stateful, multi-actor AI agents — control flow, memory, human-in-the-loop, and durable execution as first-class concepts.

A node-based workflow agent platform — drag-and-drop AI automations across 400+ integrations, with an AI Agent node that plans and executes multi-step tasks.

A search-first research agent that reads, synthesizes, and cites every claim — replacing "Google then read 8 tabs" with one structured answer.