Nick Trenkler
last time we compared openclaw and hermes agents it was april 7th. but the recent conflict between these projects made us compare it again, and here's what we've found out
growth from april 7 → june 23 (% change):
• stars: openclaw 350k → 380k (+9%), hermes 28k → 201k (+618%)
• forks: openclaw 70k → 79.6k (+14%), hermes 3.6k → 35.8k (+894%)
• contributors: openclaw 1,500 → 2,476 (+65%), hermes 300 → 1,532 (+411%)
• messaging platforms: openclaw 25+ → 23 (~−8%), hermes 14 → 22 (+57%)
• skills: openclaw 44k → 65.2k (+48%), hermes 70 → 86.5k (~+123,000% – so big it didn't fit the graph below)
observations:
1. hermes grew faster on every github metric in percentage terms, but it's growing off a much smaller base. the big percentages are catch-up, not overtaking
2. openclaw still leads in absolute terms on stars (380k vs 201k), forks (79.6k vs 35.8k), contributors (2,476 vs 1,532), and messaging platforms (50+ vs 22)
3. skills flipped. in april openclaw led by a wide margin (~44k vs ~70). by june hermes pulled ahead (86.5k vs 65.2k), consistent with its self-creating skill loop rather than manual additions
4. on token throughput hermes is clearly ahead: 1.03t daily vs openclaw's 148b, and 17t+ all-time vs 5.16t
5. openclaw's own growth was steady but unremarkable, with platform count the only metric to roughly double
conclusion:
openclaw remains larger by community and ecosystem size, but hermes is closing the gap fast and already leads on skills and token volume. the next 2.5 months will show whether hermes' growth rate holds or flattens as its base gets bigger
Addy Crezee
