Agents

Free coding agents for terminal, desktop, web and GitHub repositories, supported by text ads.

Open-source AI operating system where agents work in cloud sandboxes and land changes through approved change requests

Self-hostable deep research agent that plans searches, reads sources and returns a report where every citation can be checked.

Self-hostable personal AI app that answers from the web and your documents, runs custom agents and scheduled research automations.

Autonomous research agent that reads papers, runs experiments and compiles a LaTeX report with no human in the loop

Open-source AI agent for building apps and sites, doing research, and producing documents and slides, runnable locally with your own keys.

Open-source agent harness from MindsHub that runs as the default agent in its Cowork app and standalone in a terminal.

Iterative search agent that keeps searching, reading web pages and reasoning until it finds an answer or runs out of budget.

Open-source Devin alternative that runs Claude Code, Codex, OpenCode or Pi in isolated workspaces you can self-host.

Open-source agentic language model (30.5B parameters, 3.3B active per token) trained for long, multi-step web information seeking.

Open-source deep research agent for multi-step web research, with models published on Hugging Face.

General-purpose biomedical AI agent that autonomously runs research tasks by combining LLM reasoning with code execution.

Personal research assistant for scientific work, built on LangChain DeepAgents with an isolated Docker sandbox.

Multi-agent LLM framework for web search that runs several queries at once, with React, Gradio or Streamlit front ends.

Research system that searches the web, writes an outline and drafts a Wikipedia-style article with citations; Co-STORM adds human collaboration.

AI research assistant that searches academic papers and clinical trials and produces cited reports, tables and systematic reviews.

AI workspace for analyzing data files and databases and building charts, reports, presentations, websites, images and video.

Platform that researches a market problem, builds web and mobile apps from a prompt, and monitors competitors.

Literature search agent that reads hundreds of papers, follows citation trails and notifies you when new relevant papers appear.

Gemini agentic research feature that plans, searches the web and writes multi-page reports.

OpenAI's agent mode for multi-step tasks in ChatGPT, now replaced by ChatGPT Work

ChatGPT research mode that builds reports from sources you approve, with a plan you can edit and redirect while it runs.