Skip to content

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Rust

Commits on main

70aeb1f
fix: Cleanup FallThrough sessions (#313)
Graham King committed 3 months ago
dcce01a
fix(translation): stop streams after in-band errors (#305)
Elyas Mehtabuddin committed 3 months ago
a6aa645
fix(server): render Anthropic error envelopes (#315)
nachiketb-nvidia committed 3 months ago
e1895c7
chore: Remove libsy/examples (#306)
Graham King committed 3 months ago
54d4b66
fix(docs): explain removed setup commands (#297)
Elyas Mehtabuddin committed 3 months ago
016a511
feat(routing): add probability capability policy (#296)
Ayush Agarwal committed 3 months ago
5c25651
fix(server): handle graceful process shutdown (#294)
nachiketb-nvidia committed 3 months ago
c1c1b41
build: Check in some dev server files (#289)
Graham King committed 3 months ago
5fad270
fix(server): compact the startup banner (#293)
nachiketb-nvidia committed 3 months ago
a3283c9
ffca4e8
fix(translation): reject malformed request fields (#287)
nachiketb-nvidia committed 3 months ago
eea4e01
chore(docs): llm classifier reasoning note (#286)
Ayush Agarwal committed 3 months ago
6e63ad9
fix(translation): preserve buffered Responses output (#284)
nachiketb-nvidia committed 3 months ago
0e99eb4
fix(translation): reduce Anthropic token fallback (#282)
nachiketb-nvidia committed 3 months ago
a5fefa7
17b0e17
fix(server): warn on duplicate target model ids (#180)
Elyas Mehtabuddin committed 3 months ago
8928163
refactor: Reduce copying of HTTP headers (#269)
Graham King committed 3 months ago
5ad7c0e
a9c04b3