GitHub · Python
PillCrew/deedchain
Benchmark of report fidelity for browser agents: does the agent's final report tell the truth about what it actually did?
- Stars
- 33
- Forks
- 2
- Stars gained in 24 hours
- +3
- Forks gained in 24 hours
- +1
Topics: ai-agents, benchmark, browser-use, evaluation, llm-agents, report-fidelity, truthfulness, web-agents
Latest data point: Nov 21, 2026 · 33 stars · 2 forks