AI Agents on OpenRouter
Real-world adoption ranked by token volume on OpenRouter — the neutral marketplace for LLM inference. Because vendors don't benefit from gaming OpenRouter numbers (it's pay-per-token), this is one of the few adoption signals that's resistant to benchmark-style gaming.
| # | Agent | Daily | Cumulative | Updated |
|---|---|---|---|---|
| 01 | Hermes Agent Nous ResearchOSS | 224B | 6.47T | May 10, 2026 |
| 02 | OpenClaw Erik SteinbergerOSS | 186B | 9.17T | May 10, 2026 |
| 03 | Claude Code Anthropic | — | 3.05T | May 10, 2026 |
14other tracked agents don't use OpenRouter (most route directly to their own provider — Claude Code → Anthropic, Codex → OpenAI, Cursor → multi-provider via own infra) so they're excluded from this ranking.
Why two metrics?
Daily tokensanswers "what's being used right now." A surge can mean a viral release, a launch, or just attention.
Cumulative tokensanswers "total reach over the agent's lifetime." Older agents accumulate more — newer entrants like Hermes Agent climb fast on daily but take time to catch up on cumulative.
Both numbers come from OpenRouter's public app rankings. See the methodology page for ingestion details.
Other leaderboards
- gpt.buzz Composite Agent Index — cross-benchmark capability ranking