# mozilla-ai/otari

> A self-hosted OpenAI-compatible gateway to 40+ LLM providers: one endpoint, virtual keys, budgets, and usage tracking. It sits between apps and providers, checks budgets before dispatch, and records usage afterwards.

- Magnitude: 4.0 out of 10 — Early signal
- Stars: 640 total · +3 stars measured 2026-10-18, 11:45–13:49 UTC, ≈ 13 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-04-02 · Last push: 2026-10-18
- GitHub: https://github.com/mozilla-ai/otari · Homepage: https://otari.ai/docs/gateway · Page: https://gitnova.dev/en/r/mozilla-ai/otari

## Useful for

- Run a self-hosted gateway with Docker and point OpenAI clients to one endpoint
- Issue virtual keys with budget limits for teams and workspaces
- Configure failover and weighting across providers via local routing policies

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 11:45–13:49: 637 → 640 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +13 stars, using observed gains and the previous day.
- Before this, the repository barely got any stars — about 2 per day.
- Elevated gains were measured on the last 2 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #12, +46 stars.
- About 9 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 83
- Issues and pull requests: 2,372
- Watchers: 6
- Average over the last week: 18 per day
- Usual pace: 2 per day
- Stars in the last hour (measured): 2
- Latest release: v0.28.0 (2026-10-16)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-19 … 2026-10-18: 2, 2, 4, 2, 3, 3, 1, 0, 1, 1, 3, 2, 1, 4, 0, 1, 3, 4, 2, 1, 1, 1, 1, 2, 0, 2, 3, 59, 50, 3

## Spotted in now

- GitHub Trending Python today: #12, +46 stars

## Similar by description

1. **tbphp/gpt-load** — 1.2 · Steady · DevOps & infrastructure · Go · +2 stars measured 2026-10-18, 00:26–13:55 UTC, ≈ 4 by evening
   Self-hosted AI gateway that unifies multiple channels and credentials (API keys and subscriptions) behind a single entry point with scheduling, failover, and request logs.
   Full card: https://gitnova.dev/en/r/tbphp/gpt-load.md
2. **maximhq/bifrost** — 2.4 · Steady · Language models · Go · +16 stars measured 2026-10-18, 00:25–13:52 UTC, ≈ 28 by evening
   High-performance Go AI gateway that unifies 23+ LLM providers (OpenAI, Anthropic, Bedrock, etc.) behind a single OpenAI-compatible API with fallbacks, load balancing, and semantic caching.
   Full card: https://gitnova.dev/en/r/maximhq/bifrost.md
3. **QuantumNous/new-api** — 2.9 · Steady · Language models · Go · +26 stars measured 2026-10-18, 00:24–13:51 UTC, ≈ 47 by evening
   Self-hosted AI gateway that aggregates multiple LLM providers behind a unified OpenAI-, Claude-, or Gemini-compatible API with routing, access, and cost management.
   Full card: https://gitnova.dev/en/r/QuantumNous/new-api.md
4. **BerriAI/litellm** — 2.9 · Cooling · Language models · Python · +32 stars measured 2026-10-18, 00:23–13:51 UTC, ≈ 55 by evening
   Open-source AI gateway and Python SDK that calls 100+ LLM providers (OpenAI, Anthropic, Bedrock, Azure, VertexAI, etc.) through a single OpenAI-compatible interface with cost tracking, guardrails, load balancing, and logging.
   Full card: https://gitnova.dev/en/r/BerriAI/litellm.md
5. **diegosouzapw/OmniRoute** — 4.1 · Steady · AI agents · TypeScript · +45 stars measured 2026-10-18, 11:46–13:50 UTC, ≈ 134 by evening
   Gateway to 359 AI providers (150+ free) and 1200+ models through one OpenAI-compatible endpoint with quota-aware auto-fallback and token compression.
   Full card: https://gitnova.dev/en/r/diegosouzapw/OmniRoute.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-18 13:59 UTC, updated every 30 minutes.