A
llama-gpt
72.7
10,923 stars · MIT
Self-Hosted
serviette leads by 24.7 · decisive
A
72.7
10,923 stars · MIT
B · leads
97.4
58,707 stars · MIT
llama-gpt versus serviette is a Self-Hosted comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. llama-gpt is written mainly in TypeScript; serviette is written mainly in Python. The composite score is 72.7 for llama-gpt and 97.4 for serviette.
serviette has 58,707 GitHub stars to llama-gpt's 10,923, a gap of 47,784 (5.37×). Forks are 701 for llama-gpt and 1,551 for serviette. On the log scale used inside this pair, adoption is 85 versus 100, and the fork community is 89 versus 100.
Push history: llama-gpt was last pushed on 23 April 2024 (938 days ago), and serviette was last pushed on 10 November 2026 (7 days ago). Open issues stand at 98 for llama-gpt (0.009 per star) and 6 for serviette (0.000 per star). Issue-health scores are 84 and 96; activity scores are 16 and 92.
Both llama-gpt and serviette are listed as MIT. A permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. The license score is therefore level at 96 versus 96, and the decision moves to adoption, activity, and hosting. This is a procurement signal, not legal advice.
In Self-Hosted, both llama-gpt (10,923 stars) and serviette (58,707 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: llama-gpt is open source, serviette is open source.
serviette is ahead on every scored dimension that is not level. Level dimensions: license flexibility, self-hosting. The widest gap is recent activity at 76 points (16 vs 92), and the tightest is self-hosting at 0 points (100 vs 100).
serviette finishes ahead at 97.4 against llama-gpt at 72.7, a 24.7 point decisive margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | llama-gpt | serviette |
|---|---|---|
| GitHub stars | 10,923 | 58,707 |
| Forks | 701 | 1,551 |
| Open issues | 98 | 6 |
| Adoption | 85 | 100 |
| Activity | 16 | 92 |
| Community | 89 | 100 |
| Issue health | 84 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 72.7 | 97.4 |
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.
serviette has more GitHub stars: 58,707 versus 10,923 for llama-gpt. The gap is 47,784 stars.
serviette was pushed more recently: 10 November 2026 versus 23 April 2024 for llama-gpt. That is 931 days apart.
Yes. This catalog marks both llama-gpt and serviette as self-hostable. Confirm each project's deploy docs before you plan a migration.
llama-gpt is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. serviette is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
serviette scores 97.4 and llama-gpt scores 72.7. This page calls that a decisive lead for serviette.