AntonioCoppeAntonioCoppe/jev-harnessJev Harness
A TypeScript decision harness for TypeSafe Jev: confidence gates, shadow mode, recipes, and offline eval CLI. Unofficial, requires a TypeSafe API key.
1001MIT
OPEN SOURCE · CURATED REPOSITORIES
Jev GitHub Projects.
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
750 projects
Most popular
Ranked by GitHub Stars
Fastest rising
Ranked by recent Star growth and update activity
12 projects
AntonioCoppeAntonioCoppe/jev-harness
choxoschoxos/jevchessJev Chess
Jev, TypeSafe's System One model, plays chess against any OpenRouter LLM or Stockfish in a one-page web app with live moves, move probabilities, saved games and win rates.
510MIT
CrowdLinkerCrowdLinker/JevPromptCoachJevPromptCoach
Claude Code plugin that scores coding-agent prompts with TypeSafe's Jev model and tracks whether your prompting improves. Default mode adds zero latency.
201MIT
lhvietlhviet/jev-bridgejev-bridge: TypeSafe Jev MCP server
A zero-dependency MCP server that connects Claude Code to TypeSafe's Jev, providing calibrated probability judgments with local caching and cost tracking.
100MIT
westaicommercewestaicommerce/westai-openclaw-jevWestAI OpenClaw Jev: TypeSafe Jev integration for OpenClaw
An OpenClaw skill that integrates TypeSafe AI's System One decision model Jev, providing a dependency-free CLI wrapper for calibrated yes/no, choice, and score judgments. Includes examples, budget checks, and documented limitations.
000MIT
OmarAlaaeldeinOmarAlaaeldein/jev-verifier-skillJev Verifier Skill
OpenCode skill providing LLM agents with fast typed probabilistic judgments from TypeSafe AI's Jev via System One API, including PII redaction.
000MIT
aliaihubaliaihub/awesome-jev-usecasesAwesome Jev Use Cases
An evidence-backed curated list of use cases and patterns for TypeSafe AI's Jev / System One model, with labeled sources, plus guides, examples, and evaluation methods.
1831
khordookhordoo/jev-reflex-autonomy-labJev Reflex Autonomy Lab
Multi-drone autonomy lab demonstrating TypeSafe Jev reflex decisions with optional System 2 strategy guidance.
1720
JacquesGariepyJacquesGariepy/ORIGIN-CIVILIZATIONORIGIN-CIVILIZATION: AI simulation using TypeSafe Jev
An AI life-and-civilization simulation where every decision is made by TypeSafe Jev. LLMs plan but never decide; all decisions are typed, probabilistic, and auditable.
300
ogamircsogamircs/jev-demoJev Demo: Typed Decisions vs OpenAI
Independent demo of TypeSafe AI's Jev model for typed decisions with probabilities, measured against OpenAI on support-ticket triage. Includes a live local app and a replay page.
000
choxoschoxos/jev-reviewerJev Reviewer: Systematic Review Data Extraction
Uses TypeSafe AI's Jev/System One model (jev-1.13.0) to locate verbatim evidence in trial reports and supplements, supporting RoB 2, ROBINS-I, QUADAS-2 templates; files are processed locally in the browser.
3261MIT
y0usafy0usaf/pi-jevpi-jev: TypeSafe Jev decision layer for the Pi coding agent
A Pi coding agent extension that uses TypeSafe Jev to gate tool calls and judge outputs. Includes a shadow/enforce tool-call gate, output leak/failure detection, and a jev_ask tool for typed answers. Calibration results are documented.
14091MIT