1,572 listed
Agents
Agents that do a job for you: coding agents in your terminal or IDE, research and browser agents, and support, sales and legal agents. Each page says how autonomous it is, where you use it, who hosts it and what it costs, with sources.
Showing 1–24 of 30
- 0.744score
Browser Use
Browser Use
Open-source browser agent in Python, plus a hosted cloud with stealth browsers and an agent API
AgentAFreshness: A★ 119K↓ 1.5M/wk - 0.728score
Goose
Agentic AI Foundation (Linux Foundation)
Open-source general-purpose agent with a desktop app, CLI and API that works with many LLM providers and MCP extensions
AgentAFreshness: A★ 55.6K - 0.718score
PentAGI
VXControl
Self-hosted multi-agent system that runs penetration tests with common security tools inside a Docker sandbox
AgentAFreshness: A★ 32.3K - 0.717score
invisible_dots
feder-cr
Self-hosted agent that gives each assistant its own virtual machine and a patched Firefox browser for web tasks
AgentAFreshness: A★ 32.2K - 0.702score
WrenAI
Canner
Open-source generative BI engine that gives AI agents a governed semantic layer for correct SQL and shareable dashboards.
AgentAFreshness: A★ 18K - 0.689score
GPT Researcher
GPT Researcher
Open-source research agent that plans questions, searches the web or your documents in parallel and writes a cited report with any LLM.
AgentAFreshness: A★ 30.3K↓ 8.5K/wk - 0.689score
Octop
TencentCloud
Self-hosted AI assistant for multiple users and agents, reachable from a web dashboard and chat apps.
AgentAFreshness: A★ 10.9K - 0.681score
yao
YaoApp
Self-hosted workspace and task board for running your agents across the devices you own.
AgentAFreshness: A★ 8.2K - 0.668score
Skyvern
Skyvern
Automates browser workflows on any website with vision-based LLM agents, via no-code app, SDK or API
AgentAFreshness: A★ 23.3K↓ 1.1K/wk - 0.656score
atomic-agent
AtomicBot-ai
Open-source local-first agent that runs browser and file tasks on local or cloud models.
AgentAFreshness: A★ 3.4K - 0.653score
OpenHands
OpenHands
Open-source platform for running coding agents, with a browser control center, CLI, SDK and self-hosted or cloud backends
AgentAFreshness: A★ 91.7K↓ 34.5K/wk - 0.650score
compozy
compozy
Open-source local daemon that runs Claude Code, Codex and Cursor CLIs on cron, webhooks and approvals.
AgentAFreshness: A★ 2.8K - 0.644score
PaperQA2
FutureHouse
Retrieval augmented generation package that answers questions from scientific papers and documents with citations.
AgentBFreshness: B★ 9.5K↓ 30.7K/wk - 0.635score
OpenAdapt
OpenAdapt.AI
Open-source layer that turns a recorded task into a replayable program for computer-use agents, with read-back checks on every save
AgentAFreshness: A★ 1.8K - 0.606score
scout
outcrawlai
Open-source browser agent that drives a real browser through a page to finish a task and returns the answer
AgentAFreshness: A★ 937 - 0.588score
shai
ovh
Terminal coding agent written in Rust with a TUI, headless mode, an HTTP server and a shell assistant.
AgentAFreshness: A★ 630 - 0.579score
Jina DeepResearch
Jina AI
Iterative search agent that keeps searching, reading web pages and reasoning until it finds an answer or runs out of budget.
AgentCFreshness: C★ 5.2K - 0.558score
useagent
useagenthq
Open-source Devin alternative that runs Claude Code, Codex, OpenCode or Pi in isolated workspaces you can self-host.
AgentAFreshness: A★ 365 - 0.541score
n8n-claw
freddy-schuetz
Self-hosted AI agent built on n8n, PostgreSQL and Claude that runs over Telegram or a webhook API.
AgentBFreshness: B★ 560 - 0.536score
openvibe
vitalops
Python port of the opencode coding agent with a CLI, a FastAPI server and MCP client support.
AgentCFreshness: C★ 1.5K - 0.507score
Biomni
Stanford SNAP
General-purpose biomedical AI agent that autonomously runs research tasks by combining LLM reasoning with code execution.
AgentDFreshness: D★ 4K - 0.482score
MindSearch
Shanghai AI Lab
Multi-agent LLM framework for web search that runs several queries at once, with React, Gradio or Streamlit front ends.
AgentFFreshness: F★ 6.9K - 0.481score
openclaw-trading-agent
netzpirat
LLM-driven trading agent for Hyperliquid that reads technical indicators and places trades with take-profit and stop-loss rules.
AgentCFreshness: C★ 447 - 0.450score
Devin
Cognition
Cloud-based autonomous software engineer that takes tickets, writes and tests code in its own browser, and opens pull requests
AgentCFreshness: C