otari vs respan-gateway
Mozilla.ai's self-hosted AI gateway: one OpenAI/Anthropic-compatible endpoint over 40+ providers via any-llm, with virtual keys, pre-dispatch budgets, routing policies and a usage dashboard. — versus — Rust LLM gateway in one binary: any OpenAI/Anthropic/Gemini client to any model, cross-vendor realtime voice, MCP tools inside chat calls, hedged requests and a live cost log.
Both self-hosted multi-provider gateways; Otari centres on virtual keys and budgets for teams, Respan on protocol translation, MCP tooling and raw performance.
| otari | respan-gateway | |
|---|---|---|
| Stars | 953 | 954 |
| Forks | 138 | 145 |
| Language | Python | Rust |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | today | today |
| Topics | gateway | gateway |
| Curated connections | 3 | 4 |
otari — the curator's take
Pick it when a team needs to hand out revocable, scoped model keys and enforce spend limits before requests go out — Docker-run with zero config, Postgres when you outgrow SQLite, plus Claude Code hooks for per-developer tracking. It's young (1.0) next to LiteLLM's provider breadth and ecosystem; for a solo dev just pointing a coding CLI at free tiers, a lighter local router is less to operate.
respan-gateway — the curator's take
Pick it when gateway overhead matters (sub-0.1ms, tiny memory) or you need protocol translation beyond chat — realtime voice across vendors, MCP tools usable by any model, a plugin trait for custom guardrails. Young and tied to the Respan tracing product for deep observability; if you need team keys, budgets and a mature provider list today, LiteLLM or Otari are safer.