shellbench
The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based scoring, reliability metrics, configuration diagnostics.
openclaw/shellbench
View on GitHub ↗The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based scoring, reliability metrics, configuration diagnostics.
shellbench grew +1.4% in the last 30 days, ranks 519th of 738 in Evaluation & Guardrails, actively maintained, last commit today.
Star trajectory
97 days tracked+1.4% in 30d, above the Evaluation & Guardrails median of +1.2%.
Last commit today, fresher than the median of 15d.
How it compares in Evaluation & Guardrails
Ranked 519th of 738 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 12
- Forks
- 32
- Watchers
- 2
- Open issues
- 9
- Releases
- 0
- Created
- 2026-04-07
- Stars this week
- +0
You've seen where shellbench stands today.
Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.