One persona, one frozen memory, N models: how much of an agent's character survives a model swap? Harness + blind multi-lens judge panel + cross-vendor rank control + contamination probe. Results included: 7 models, spread 4.80 -> 2.20.
Cross-referenced across 55 tracked directories
#9086
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
8/13/2026
Created
2
GitHub Stars
2
Open Issues
10/12/2026
Last Commit
Recently added to the ecosystem
Score: 100/100
0 dependency vulnerabilities found
dprctd
Detect duplicated code, dead code, and anti-patterns in AI-generated codebases
tomquirk
A multi-model council plugin for OpenCode that runs prompts across multiple LLMs and synthesizes their responses to identify consensus and discrepancies.
...more