stuntd
bladedevoff
Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.
- License
- Apache-2.0
- GitHub Stars
- 33
- Source reviewed
- —
Where Jev makes a decision
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
What this project offers
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Review scope
Author and repository text is preserved where clear; missing languages are enriched automatically. Checks establish source-level Jev integration, not runtime, safety, or performance validation.
Sources and implementation
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/README.md
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/proxy/jev.py
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/decisions/__init__.py
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/decisions/schema.py
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/decisions/site.py
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/jev/__init__.py
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/jev/answer.py
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/jev/schema.py
- bladedevoff/stuntd/blob/ee218f52eda33d9f9afda6b9cf4924fb52862b69/stuntd/jev/state.py
Related projects
jev-codex-router
0xNatoshi · Model Routing
Uses Jev to classify each Codex turn, then applies local rules to choose the model, reasoning effort, and speed mode.
jev-research
sherajdev · Model Routing
A Jev and Herdr integration guide with a prototype for routing tasks to different Agents.
jev-demo
minghanminghan · Model Routing
A customer-service routing demo that batches Jev questions before following the resulting route.
jev-router-playground
hugo-alves · Model Routing
A model-routing playground where Jev picks a candidate and users compare the resulting answers.