# diri

Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. The same evidence rules apply to Podium and its competitors, but they do not remove this conflict of interest.

Page: https://adecomparison.com/ade/diri/
Website: https://github.com/cristicretu/diri
Research: not-researched

## Measured by ADEMark

Source: https://ademark.dev/ (CC BY 4.0; credit ADEMark). diri 0.11.2, measured up to 12 November 2026 on Mac mini M4, 16 GB, macOS 27 · Claude Opus 5.5, effort high. Third-party measurements, not findings; no overall score. Place counts only apps with a value.

- Cold start: 2.26 s (6th of 12), median of 6 runs
- New thread, ready to type: 663 ms (10th of 10), median of 10 runs
- First word on screen: 256 ms (1st of 11), median of 9 runs
- Typing lag, 5 agents streaming: 72 ms (9th of 11), 1 run
- Open a 2,000-message thread: 88 ms (2nd of 11), median of 5 runs
- Memory at rest, 5 threads: Not measured. ADEMark: it starts its agents detached, so we cannot yet tell them from other Claude processes
- Idle CPU: 0.55% (2nd of 13), 1 run
- Memory under load: Not measured. ADEMark: it starts its agents detached, so we cannot yet tell them from other Claude processes
- Tokens to answer “hi”: 39.5K tokens (6th of 13), median of 3 runs
- Tokens for one real question: 175.8K tokens (10th of 13), 1 run
- Team build: hidden tests passed: Not measured
