Curated agent list
The best autonomous AI agents in 2026
Beyond coding, a separate class of agents is emerging: long-running autonomous systems with persistent memory, multi-LLM routing, and self-improving loops. OpenClaw and Hermes Agent crossed 60K+ stars each within months of release.
Manus
MonicaGeneral-purpose autonomous agent that decomposes a goal into parallel sub-agents and executes browser, code, and analysis tasks end-to-end.
Computer Use
AnthropicAnthropic's screen-control capability — Claude clicks, types, and scrolls through any GUI app via screenshots and keyboard/mouse primitives.
Operator
OpenAIOpenAI's browser-using agent. Books flights, fills forms, runs research tasks autonomously inside a sandboxed browser.
Comet
PerplexityPerplexity's agentic web browser — search, summarize, take actions across tabs, all powered by their answer engine.
OpenClaw
Erik SteinbergerOpen-source autonomous AI agent (formerly Clawdbot, Moltbot — lobster theme). Self-hosted; supports Claude, GPT, KIMI, MiMo, Qwen 3, Llama 4, Mistral, plus local models via Ollama. ~347K GitHub stars.
open sourceHermes Agent
Nous ResearchOpen-source AI agent from Nous Research with a built-in learning loop — creates skills from experience, persists knowledge, builds a model of its user across sessions. ~60K stars in two months.
open sourceWant the rest? Browse the full agent directory, or build a side-by-side comparison.