Jev project radar

Playable board games driven by Jev decisions.

→Open the project link to review its source material and implementation.

Local Telegram channel JSON analyzer for intent, quality, sentiment, and speaker tone.

→Open the project link to review its source material and implementation.

Jev Gamecast: replay-first React app that asks Jev typed questions about live sports data.

→Open the project link to review its source material and implementation.

Local tactics shrink 225 moves to about 40 candidates, then Jev picks among tiered options.

→Open the project link to review its source material and implementation.

Short video explainer of how Jev's typed-decision loop works.

→Open the project link to review its source material and implementation.

Desktop writing app using Jev for fast structured writing judgments.

→Open the project link to review its source material and implementation.

Talk nicely or nastily over time; structured state tracks the mood.

→Open the project link to review its source material and implementation.

Hosted typesafe-ai/jev for AI SDK evaluate calls, no TypeSafe waitlist required.

→Open the project link to review its source material and implementation.

The maze as JSON; Jev picks the turn at each junction in real time.

→Open the project link to review its source material and implementation.

Work-in-progress demo of Jev driving Minecraft, including fleeing zombies at night.

→Open the project link to review its source material and implementation.

One sentence becomes six room settings. Jev chooses, the app renders.

→Open the project link to review its source material and implementation.

Jev picks rotation and column from holes, stack height, and bumpiness.

→Open the project link to review its source material and implementation.

Steve Krouse's playable 16-judgment demo and video.

→Open the project link to review its source material and implementation.

Head-to-head test at validating local event listings, with cost and latency.

→Open the project link to review its source material and implementation.

Video comparison against a structured-output LLM baseline.

→Open the project link to review its source material and implementation.

Jev vs Jev gomoku with source and timing logs.

→Open the project link to review its source material and implementation.

Local A-share technical analysis using Jev Choice and Noul questions to assess direction and volatility across two horizons, with evidence for Buy/Hold/Sell assessments and no order execution.

→Open the project link to review its source material and implementation.

Typesafe/Jev public X demo

→Open the project link to review its source material and implementation.

Does Jev predict stock returns from news? It reads the news well; there is no tradeable alpha. Three arms separate reading from recall.

→Open the project link to review its source material and implementation.

Jev (TypeSafe) vs. Gemini 3.8 Flash vs. GPT-5.6 Luna na anotação estruturada de sentenças do TJSP: qualidade, tempo e custo

→Open the project link to review its source material and implementation.

Wikipedia link race pathfinder guided by Jev: assesses outbound links to navigate between two articles in real time.

→Combines classic graph traversal with probabilistic judgments to prune the Wikipedia multi-hop search space.

Interactive explorer and Jev question workspace for Jev Board datasets.

→Open the project link to review its source material and implementation.

Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.

→Open the project link to review its source material and implementation.

Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.

→Open the project link to review its source material and implementation.