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

Open-source desktop app for running a multi-agent workforce on local or cloud models, with MCP and skill integration.

Open-source workspace for named AI agents with memory, delegation, routines and approval controls.

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.

Chrome side-panel agent that works in your logged-in browser, reads data behind logins and delivers finished files or drafts.

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 browser agent that drives a real browser through a page to finish a task and returns the answer

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.

Open-source self-evolving general AI agent with a Docker sandbox that can run fully local on Ollama or vLLM models.

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

General-purpose agent that builds apps, writes reports, creates presentations and connects to your other systems.

Clay's AI research agent that does web research on accounts and contacts and returns structured data with a reasoning trace for each run.

AI scientist for R&D that reads literature, analyzes data and generates hypotheses for drug development teams.

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