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

7a40d51
chore: getting started cleanup (#218)
Ayush Agarwal committed 3 months ago
74324f1
d495386
docs: minimal working readme (#214)
Ayush Agarwal committed 3 months ago
cdb893b
ace80c8
feat(switchyard-server): `/v1/stats/reset` (#213)
Graham King committed 3 months ago
a6a4dce
50e8d74
88a9fd3
doc(AGENTS.md): Allow panic in tests (#209)
Graham King committed 3 months ago
e4e5f47
fix(libsy): preserve classifier system instruction (#195)
Bryan Bednarski committed 3 months ago
f3ff7ff
feat(llm-client): add bounded upstream retries (#173)
nachiketb-nvidia committed 3 months ago
ef646cd
build: Import most of graham-code-review (#191)
Graham King committed 3 months ago
96a5516
c8ca731
b0c9ac5
1f5d173
36b9636
feat: switchyard rust server image (#181)
Bhuvan Agrawal committed 3 months ago
11d3648
e4632e3
2faf5f1
refactor(libsy): generalize fall-through state (#158)
nachiketb-nvidia committed 3 months ago
61f41ff