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
- 0.16.9 August 26, 2026 (516 KB)
- 0.16.8 August 19, 2026 (492 KB)
- 0.16.3 August 18, 2026 (489 KB)
- 0.15.2 August 04, 2026 (452 KB)
- 0.15.1 August 03, 2026 (450 KB)
