quaeastquaeast/vllm2jevvllm2jev
A lightweight script that adapts vLLM services to a Jev-style interface, enabling Choice, Score, and Noul decisions via logprobs.
100
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
Sponsors
These products pay for the directory. Want yours up here?
Most popular
Ranked by GitHub Stars
Fastest rising
Ranked by recent Star growth and update activity
16 projects
quaeastquaeast/vllm2jev
jiangkoumojiangkoumo/ego-jevego-jev: Jev-driven browser automation
Uses TypeSafe AI's Jev (System One) model to drive the ego lite browser: one indexed element table in, one operation and target out per request. Includes comparative benchmarks showing ~2x faster than per-step LLM loops.
400MIT
zlZaynzlZayn/AI-decision-makerSignalChain: AI Data Cleaning Framework with Jev Probability Engine
Open-source Python framework integrating TypeSafe AI's Jev/System One probabilistic engine with LLM dual pipelines for CSV field type recognition and data cleaning; tests show Jev and LLM classification conclusions align.
100MIT
PerryLinkPerryLink/jevcorejevcore: TypeSafe Jev Integration for DSH/MCP
TypeSafe Jev integration providing a core decision library, DeepSeek Harness plugin, and MCP server; offline by default, with tests and real API verification.
1300Apache-2.0
ARCJ137442ARCJ137442/jev-2048Jev 2048 Lab
A 2048 web lab where every move is driven by TypeSafe AI's Jev decision model, showing probability, confidence, latency, and cost, with no heuristic fallback.
510MIT
One card in the feed, every sixteen, on every page of it. $50 a week, cancel any week.
glud123glud123/jev-assistjev-assist: TypeSafe Jev skill
jev-assist is a coding-agent skill that uses TypeSafe Jev/System One to rank repository files by task relevance, detect convention drift, and flag risky diffs before commit. It includes setup, validation, and pre-commit hook wiring.
300MIT
yzbcsyzbcs/Should-I-JevShould-I-Jev
Scans LLM logs and code for decision-shaped calls, estimates savings from migrating to JEV, calibrates decision models, and generates migration PRs. Optionally calls the JEV API for a self-audit.
100MIT
Renwang-HuangRenwang-Huang/arbitypeArbitype: Typed Decision Tools for AI Agents Powered by TypeSafe Jev
Arbitype is an MCP-native typed decision layer powered by TypeSafe Jev, offering classify, score, verify, gate, route, and review tools for AI agents.
000MIT
formulahendryformulahendry/jev-acpJev ACP adapter
An ACP decision agent that calls TypeSafe AI's Jev for Choice, Score, and Noul evaluations. It provides guided templates, JSON output, and can run via npx without building.
000MIT
ziqi-jinziqi-jin/agent-to-trustAgent-to-Trust: Jev Cross-check
A2T integrates TypeSafe AI's Jev (System One) as an independent judge to cross-check its deterministic graders; methodology and results are in docs/jev.md. The repo benchmarks, simulates, and scores agent trustworthiness via evidence-based credit scores.
710MIT
KiritoKingKiritoKing/midscene-jev-runnerMidscene JEV Runner
Community-maintained JEV runner integration for Midscene Test. It calls TypeSafe AI's JEV via OpenRouter ~typesafe/jev-latest by default and provides Playwright direct use plus strict jevAct nodes for Midscene.
300MIT
qddegtyaqddegtya/qualmqualm - Typed decisions from TypeSafe Jev
A TypeScript library for TypeSafe Jev/System One, providing typed ask/decide APIs with a required unsure branch and Cloudflare/TypeSafe providers.
104MIT