General-purpose AI agents
Agents that take an open-ended goal, such as research, a report or a booking, and carry it out across tools on their own.
By weekly package downloads, the leaders are OpenClaw (4.5M), Hermes Agent (50.2K). By GitHub stars, the leaders are OpenClaw (391K), Hermes Agent (251K), AutoGPT (188K). The fastest grower over the last 30 days is OpenClaw, with downloads up 28%. As of Oct 6, 2026.
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 |
OpenClawOpenClaw Foundation (nonprofit); created by Peter Steinberger |
80 | 4.5M | up 34.8% | up 28.5% | — | 391K+162/day | 2026.9.83d ago | Free (OSS) | ||
| 27 |
Hermes AgentNous Research |
54 | 50.2K | up 37.3% | down 39.8% | — | 251K+259/day | 2026.9.2412d ago | Free (OSS) | ||
| 37 |
ManusButterfly Effect Pte. Ltd. (Manus AI), Singapore |
51 | — | — | — | — | — | — | Free + $20/mo | ||
| 62 |
GensparkGenspark Inc. (MainFunc) |
42 | — | — | — | — | — | — | Free + $24.99/mo | ||
| 74 |
AutoGPTSignificant Gravitas |
38 | — | — | — | — | 188K+22/day | 0.6.448mo ago | Free + $50/mo | ||
| 83 |
KortixKortix AI |
35 | — | — | — | — | 20.2K+3/day | 0.13.502d ago | Free + $40/mo | ||
| 105 |
DeerFlowByteDance |
27 | — | — | — | — | 83.4K+42/day | 2.1.012d ago | Free (OSS) | ||
| 114 |
Claude CoworkAnthropic |
20 | — | — | — | — | — | — | $20/mo | ||
| 117 |
ChatGPT WorkOpenAI |
19 | — | — | — | — | — | — | Free + $8/mo | ||
| 120 |
FlowithFlowith Technologies Pte. Ltd. |
19 | — | — | — | — | — | — | Free + $19.90/mo | — | |
| 143 |
Gemini SparkGoogle |
0 | — | — | — | — | — | — | $19.99/mo | ||
| 146 |
Perplexity ComputerPerplexity AI |
0 | — | — | — | — | — | — | — | ||
| 154 |
MiniMax AgentMiniMax |
— | — | — | — | — | — | — | Free + $22/mo | ||
| No agents match that filter. | |||||||||||
Ranks are overall positions by Pulse Score. Click a column to sort by what matters to you. Methodology.
What they do
A general agent gets a goal instead of a prompt: "compare these five vendors and put the result in a spreadsheet". It plans the steps, browses, runs code, writes files and reports back, usually inside a cloud sandbox.
What to compare
- Where it runs. In the vendor's cloud, in your browser or on your own machine. This decides what it can reach and what you are trusting it with.
- Pricing. Most charge by credits tied to how much work a task takes, so the cost of a long task is hard to predict up front.
- Oversight. Whether you can watch, pause and correct the agent while it works, and what it asks permission for.
Most products in this group are closed services, so we rank them on site traffic rank, attention and, for open-source projects, repository and package activity.
Head-to-head comparisons
Related guides
AI Agent vs Chatbot vs Agentic AI: What Is the Difference?
Plain-language definitions of AI agents, chatbots, agentic AI, LLMs, workflows and skills, how they relate, and how to tell which one you are looking at, with real examples.
Best AI Agents in 2026: Live Rankings by Category
The leading AI agents for coding, automation, research, browsing, app building, customer support, voice and sales, ranked by public usage data that refreshes daily, with prices and free options.
What Is an AI Agent? A Practical Explanation With Real Examples
What makes software an AI agent, how agents differ from chatbots and plain language models, the main types in use today and how to judge one.
AI Agent Statistics 2026: Live Usage, Growth and Activity Data
Current statistics on AI agents from public data: package downloads, editor installs, GitHub stars, pull requests opened by coding agents, release pace and benchmark results. Updated daily.
Questions about general-purpose AI agents
Are general-purpose agents safe to give access to my accounts?
Treat access the way you would for a new contractor: grant the minimum, prefer agents that ask before consequential actions such as purchases or sending messages, and avoid handing over credentials for accounts where a mistake would be costly.