A proxy between AI clients and model backends. Requests translate once to a canonical form, route to the cheapest capable tier (local, direct, fleet, cloud, frontier), and escalate on failure with circuit breakers and mid-stream failover. A post-turn Curator bounds long agent sessions (97.7% context reduction vs naive resend at 50+ turns, production-measured). Provider adapters are separate lex-llm-* gems.
Required Ruby Version
>= 3.4
Authors
Esity
Versions
- 0.15.0 July 25, 2026 (447 KB)
- 0.14.20 July 24, 2026 (446 KB)
- 0.14.18 July 24, 2026 (445 KB)
- 0.14.17 July 23, 2026 (443 KB)
- 0.14.16 July 15, 2026 (442 KB)
