mozilla-ai/otari
Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest today, with 44 contributors on GitHub.
Use Cases & Benefits
- Provides an OpenAI-compatible gateway to route requests to over 40 LLM providers with unified API access, virtual keys, budget enforcement, and usage tracking.
- Enables centralized management of multiple LLM providers with secure credential handling, cost control, and flexible routing policies through a single self-hosted endpoint.
- Use for consolidating access to diverse LLM APIs in a single interface to simplify integration and reduce credential exposure in multi-provider AI applications.
- Use for enforcing API key scopes, user budgets, and usage limits in organizations managing multiple teams and projects consuming LLM services.
- Use for implementing failover and weighted routing policies to optimize cost and reliability when querying different LLM providers in production AI systems.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
Apache 2.0
Permissive: commercial use, modification and redistribution are allowed with attribution; includes an explicit patent grant from contributors.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
An OpenAI-compatible LLM gateway you own and run.
Route one endpoint to 40+ providers, issue virtual keys, enforce budgets, and track usage.
Otari sits between your applications and model providers. It authenticates requests, resolves provider credentials, enforces budgets before dispatch, and records usage afterwards. Provider calls go through any-llm.
Run Otari standalone with your own database and provider keys, or connect a data plane to otari.ai.
Run an ephemeral standalone gateway with Docker:
On the first empty database, Otari creates an API key and prints it once:
OpenAI clients work by setting
base_urltohttp://localhost:8000/api/v1.This container uses SQLite inside the container and is deleted when it stops. Use the Compose setup below for persistent data.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
Forks
101+18
Open issues
286-31
Compared with peers in AI
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| thedotmack/claude-mem | 113.6K | +8.8K | 35 | today |
| D4Vinci/Scrapling | 98.1K | +6.9K | 65 | 1 day ago |
| Leonxlnx/taste-skill | 110.7K | +5.2K | 55 | 1 day ago |
| calesthio/OpenMontage | 77.2K | +4.2K | 40 | — |
| heygen-com/hyperframes | 79.6K | +4.1K | 45 | today |
| mozilla-ai/otari | 785 | — | 45 | today |
| Category median | 98.1K | +5.2K | 45 | — |
Also by mozilla-ai
Other repositories from this maintainer that GStars tracks
Discover Repositories
Search across tracked repositories by name or description