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 73–96 of 106
- 0.582score
hunter-community
agentpit-io
Self-hosted AI investment research assistant for A-shares, Hong Kong and US stocks, with data and chats kept on your own machine.
AgentAFreshness: A★ 570 - 0.579score
zhikuncode
zhikunqingtao
Self-hosted open-source AI coding assistant with a CLI and web UI, multi-agent collaboration and Docker deployment.
AgentAFreshness: A★ 528 - 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 - 0.578score
AutoCVE
larlarua
Multi-agent platform that audits source code for vulnerabilities, verifies findings and drafts CVE reports
AgentBFreshness: B★ 1.2K - 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 - 0.570score
aurora
Arvo-AI
Open-source AI agent that investigates cloud and Kubernetes incidents, writes root-cause analyses and drafts fix pull requests.
AgentAFreshness: A★ 443 - 0.570score
agentgg
agentgg-dev
Open-source agentic SAST scanner: AI agents follow imports and call graphs to confirm findings in a repo or PR diff.
AgentAFreshness: A★ 441 - 0.564score
clay
chadbyte
Self-hosted workspace where people and coding agents share projects, live sessions and persistent Mates across providers.
AgentAFreshness: A★ 405 - 0.564score
pocketpaw
pocketpaw
Self-hosted personal AI agent with a desktop app and web dashboard that talks over Telegram, Slack, Discord, WhatsApp or the browser
AgentBFreshness: B★ 894 - 0.561score
WrongStack
WrongStack
MIT-licensed AI coding agent with terminal, TUI and browser interfaces, durable project memory and specialist subagents.
AgentAFreshness: A★ 392 - 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 - 0.554score
dash
agno-agi
Self-learning data agent that answers English questions with read-only SQL over a database, grounded in six context layers.
AgentCFreshness: C★ 2.3K - 0.551score
Tongyi DeepResearch
Alibaba Tongyi Lab
Open-source agentic language model (30.5B parameters, 3.3B active per token) trained for long, multi-step web information seeking.
AgentDFreshness: D★ 20.1K - 0.550score
gini-agent
Open-Curiosity
Personal agent with a Bun gateway that keeps memory, skills and run history, with approval-gated tools and web, CLI and mobile clients.
AgentCFreshness: C★ 2.1K - 0.544score
solo
solo-agent
Open-source, local-first workspace where humans and AI coding agents coordinate through channels, tasks and persistent memory.
AgentBFreshness: B★ 594 - 0.539score
VibeAround
jazzenchen
Hub that launches Claude Code, Codex CLI, Gemini CLI and other agents with third-party APIs and reaches them from web, mobile and chat apps.
AgentBFreshness: B★ 527 - 0.535score
pr-cockpit
taovc
Local desktop and web workbench that reviews a repo's pull requests with Claude or Codex in isolated worktrees and posts only approved comments.
AgentBFreshness: B★ 485 - 0.532score
bux
browser-use
Claude Code agent on a VPS you own, with a real Chromium browser and a Telegram bot to message it.
AgentBFreshness: B★ 459 - 0.528score
pentest-harness
S1N6H
Self-hosted AI agent harness for authorized penetration tests and security labs, using your own model API keys.
AgentBFreshness: B★ 430 - 0.527score
MiroThinker
MiroMindAI
Open-source deep research agent for multi-step web research, with models published on Hugging Face.
AgentDFreshness: D★ 8.4K - 0.515score
MiniCPM5-2B WebGPU Pi
victor
Coding agent that runs fully in the browser on WebGPU, with a local MiniCPM5-2B model and a virtual shell workspace.
AgentBFreshness: B - 0.511score
Chef
Convex
AI app builder from Convex that generates full-stack web apps with a built-in database, auth and background workflows.
AgentDFreshness: D★ 4.6K - 0.509score
Devika
Stition AI
Open-source agentic software engineer that plans, researches the web and writes code from a high-level task
AgentFFreshness: F★ 19.6K