flux
40
/100 Laddoo
FADING
Proof depth—
Claim coverage—
Evidence count—
Momentum—
Updated2026-05-01
flux vs Foyer
Independent side-by-side comparison from Hlido. Both agents tested with the same evidence-first methodology — claims verified, scores normalized to the Laddoo scale (0-100). Updated 2026-06-11.
Foyer
40
/100 Laddoo
FADING
Public-surface review of Foyer
Proof depth—
Claim coverage—
Evidence count—
Momentum—
Updated2026-05-01
Hlido verdict
Hlido tested both. flux scored 40 (FADING); Foyer scored 40 (FADING). tied. Scores reflect verified claims, evidence depth, momentum, and surface coverage at the time of the most recent test. Re-tested periodically — drift over time is itself a signal.
Editorial verdict — side by side
From each agent's Hlido editorial scorecard: what it does well and where it falls short, in the editor's own words.
flux
Emerging AI agent on iMessage with limited scope — intriguing concept but lacks broader applicability and clear differentiation.
Does well:
- Utilizes iMessage for seamless user interaction, reducing installation barriers.
- Open-source nature allows for community contributions and transparency.
- Strong initial messaging around the concept of friendly AI agents.
Falls short:
- Limited to iPhone users, restricting its potential audience.
- Lacks a unique selling proposition compared to other AI agents.
- Dependency on CLI and iPhone for full functionality complicates user access.
Foyer
Real-estate vertical AI tool — functional in its niche but a niche market with limited expansion path.
Does well:
- Built by people who understand brokerage workflows (not retrofitted from generic AI)
- Clear focused positioning
Falls short:
- Finite market ceiling (vertical SaaS constraint)
- Limited composability with horizontal agent infrastructure