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 29
- 0.721score
DeepSeek-Reasonix
esengine
Open-source coding agent for terminal, desktop, browser and editor that edits files and runs commands and tests
AgentAFreshness: A★ 36K - 0.719score
AionUi
iOfficeAI
Open-source desktop app for running a built-in agent and CLI agents, with scheduled tasks and remote access from chat apps
AgentAFreshness: A★ 33.7K - 0.706score
Suna
Kortix
Open-source AI operating system where agents work in cloud sandboxes and land changes through approved change requests
AgentAFreshness: A★ 20.3K - 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 - 0.680score
CyberStrikeAI
AIPentest
Self-hosted Go workspace where AI agents run security tools through MCP for authorized testing.
AgentAFreshness: A★ 8K - 0.666score
youtube-automation-agent
darkzOGx
Self-hosted open-source agent that produces and schedules YouTube videos after user approval.
AgentAFreshness: A★ 4.6K - 0.663score
openscience
synthetic-sciences
Open-source AI workbench for scientific research that runs analyses and experiments with visible steps.
AgentAFreshness: A★ 4.2K - 0.657score
mercury-agent
cosmicstack-labs
Open-source background agent with local memory, permission rules and chat access from many apps.
AgentAFreshness: A★ 3.5K - 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 - 0.647score
nanoMuse
nano-muse
Open-source personal agent for phones, computers and the browser that does tasks and asks before anything irreversible.
AgentAFreshness: A★ 2.5K - 0.638score
happier
happier-dev
Open-source web, desktop and mobile control room for running coding agents such as Claude Code and Codex on your own machines.
AgentAFreshness: A★ 2K - 0.633score
agtx
fynnfluegge
Terminal kanban board that assigns tasks to several coding agents and hands work between them by phase.
AgentAFreshness: A★ 1.7K - 0.617score
okou
okou-ai
Agent that takes a job in chat or Slack, picks its own tools, and leaves outbound work as drafts for a person to approve
AgentAFreshness: A★ 1.2K - 0.612score
thinkrail
JetBrains
Agentic IDE built around the pi coding agent, with isolated git-worktree workspaces, living specs and MCP support
AgentAFreshness: A★ 1.1K - 0.609score
kandev
kdlbs
Kanban workspace for running several coding agents in parallel, reviewing their changes and opening pull requests
AgentAFreshness: A★ 1K - 0.598score
juggler
juggler-ai
Visual workbench for AI coding agents that shows every model call, with sessions run locally or on a server
AgentAFreshness: A★ 804 - 0.597score
Magentic-UI
Microsoft Research
Microsoft AI Frontiers experimental agent for browser and local file tasks, built to run on small models.
AgentCFreshness: C★ 10.1K - 0.592score
Minke
lencx
Local-first desktop agent workspace for DeepSeek Harness, with conversations, files, terminals and a shared browser.
AgentAFreshness: A★ 692 - 0.591score
oneshot-gtm
oneshot-agent
Outbound sales agent for early founders: finds prospects, drafts messages for your approval, then sends them.
AgentAFreshness: A★ 672 - 0.584score
openteams
openteams-lab
Open-source, local-first desktop app where a team of AI coding agents shares one session, a visible plan and an issue list.
AgentAFreshness: A★ 580 - 0.577score
pizza-bot
pizza-bot-app
Local-first inbox for long-running AI agent work, built on DeepAgents and LangGraph with approvals and scheduled runs.
AgentAFreshness: A★ 520 - 0.574score
OpenInstinct
Merit-Systems
Self-hosted personal assistant you text over iMessage; it can drive a cloud browser for tasks such as bookings and purchases.
AgentAFreshness: A★ 472 - 0.564score
clay
chadbyte
Self-hosted workspace where people and coding agents share projects, live sessions and persistent Mates across providers.
AgentAFreshness: A★ 405 - 0.561score
WrongStack
WrongStack
MIT-licensed AI coding agent with terminal, TUI and browser interfaces, durable project memory and specialist subagents.
AgentAFreshness: A★ 392