Real Jev Agent Implementations
Live demonstrations, open-source repositories, and sourced benchmarks where developers put Jev into production loops. Filter by architecture pattern or explore video breakdowns below.
Showing 5 sourced implementations (official)
Clear filters ×
DEMO
Agent Trace Observability
A TypeSafe workflow that triages completed agent runs for review, bugs, or on-call escalation.
TypeSafe Agent Skills
Official skills that teach coding agents how to design and compose TypeSafe decision workflows.
@typesafeai
DEMO
Wikiracing Fast Navigation
An official benchmark demonstrating Jev selecting optimal Wikipedia links in real time to reach target concepts.
Hop Latency: <50ms / stepBenchmark: WikiracingAction Space: 140+ links
@0xidanlevin
DEMO
Jev on WebMCP Benchmark
Solved 49 of 49 benchmark tasks at 112× lower model cost by combining Jev tool selection with fast LLMs.
Tasks solved: 49/49Model cost: ~112× lower
@latentspacepod
DEMO
Why I Couldn't Build Jev at OpenAI: Diogo Almeida
TypeSafe Co-founder & CEO Diogo Almeida explains why post-training on generative LLMs fails on agent loops and how RLCD trains System 1.
Speaker: Diogo AlmeidaDuration: 58 minsTopic: RLCD & System 1