retroassemblyvsTransformer Lab
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| retroassembly | Transformer Lab | |
|---|---|---|
| Score | 56/100 | 61/100 |
| Rank in category | #5 of 5 in Emulation | #12 of 25 in LLM Inference |
| GitHub stars | 1 153 | 5 199 |
| Stars, last 30 days | +72 | +2 |
| Stable releases, 12 months | 3 | 9 |
| Latest release | v7.260719.1051 · 19 Jul 2026 | v0.40.1 · 19 Jun 2026 |
| Setup | Easy | Moderate |
| Official Docker image | Yes | No |
| License | MIT | AGPL-3.0 |
| Main language | Typescript | Python |
Which one should you pick?
Transformer Lab scores 61/100 against 56/100 for retroassembly, so it is the safer default.
Transformer Lab ships more often: 9 stable releases in the past year, against 3 for retroassembly.
If you want the quickest setup, retroassembly is easier to run; Transformer Lab needs more configuration.
retroassembly is growing faster right now (+72 stars in 30 days).
retroassembly details →Transformer Lab details →