Head to head
IWE vs Maginary
Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.
No reviews yet
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
Full listing
No reviews yet
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
Full listingThe short version
Neither has been reviewed yet, so the comparison rests on the scan and the public usage numbers. The safety scan favours IWE (94/100 against 83). Maginary is hosted and callable through the gateway; IWE runs on your own machine. IWE has noticeably more public adoption.
| IWE | Maginary | |
|---|---|---|
| User rating | No reviews yet | No reviews yet |
| Safety grade | A94/100 | B83/100 |
| Adoption | Established | Growing |
| GitHub stars | 1.7k | 1 |
| Downloads / week | 136 | 1.2k |
| Runs where | Your machine (local) | Hosted (remote) |
| Gateway-ready | No | Yes |
| Tools | — | 16 |
| Write actions | — | 6 |
| Price per call | Free | Free |
| Licence | Apache-2.0 | MIT |
| Last release | 2026-09-19 | 2026-09-15 |
| Category | AI and agents | AI and agents |