Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
JEV-27B-VL
Modelsimage text to text model by autotrust · transformers
autotrust/JEV-27B-VL -
AutoTrust-Decider-Pro-35B
Modelstext classification model by autotrust · transformers
autotrust/AutoTrust-Decider-Pro-35B -
JEV-35B
Modelstext classification model by autotrust · transformers
autotrust/JEV-35B -
image text to text model by autotrust · transformers
autotrust/AutoTrust-Decider-Pro-Vision-27B -
GEV-26B-Decide
Modelstext classification model by autotrust · transformers
autotrust/GEV-26B-Decide -
openjev
Modelszero shot classification model by openjev
openjev/openjev -
JEV-35B-NVFP4
Modelstext classification model by autotrust · transformers
autotrust/JEV-35B-NVFP4 -
drex-v1.5
Modelsmodel by nace-ai
nace-ai/drex-v1.5 -
THX-02
Modelszero shot classification model by HAL-X-AI · thx02
HAL-X-AI/THX-02 -
JEV-27B
Modelstext classification model by autotrust · transformers
autotrust/JEV-27B -
Ekbasis
MCP serversForesee what git commands and multi-step changes will do, as calibrated probabilities
ekbasis@0.1.42 -
fermi
MCP serversCalibrated probability ranges for forecasting questions, with the assumptions behind them.
-
Jev MCP Server
MCP serversMCP server for Jev (TypeSafe System One): typed decisions with calibrated probabilities.
jev-mcp-server@0.2.2 -
TypeSafe Jev
MCP serversMCP server over TypeSafe Jev: typed ask, rank and check judgments return calibrated probabilities.
jevcore-mcp@0.4.1 -
agent-jev
Agents & frameworksAgentJev-0.6B - a fast 'System One' decision model for AI Agents: feed it any unstructured state (diffs, traces, logs) and structured questions, get calibrated probability distributions back in one ~50ms forward pass. Zero output-token decoding.
git clone https://github.com/malevrigns/agent-jev.git -
EloEdge: Kalshi model probabilities
MCP serversCalibrated probabilities for Kalshi markets, a news wire and Polymarket outliers (Pro).
-
Veri Asia
MCP serversCalibrated probabilities, fair odds and value plays for Asian football, benchmarked vs Pinnacle.
-
awesome-jev
Docs & tutorialsA curated list of Jev use cases, projects, SDKs, and resources. Jev is TypeSafe AI's System One model for fast, typed decisions in software — Choice, Score, and Noul with calibrated probabilities.
git clone https://github.com/kraayenjon/awesome-jev.git -
jev-cli
MCP serversCommand-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.
git clone https://github.com/shaharia-lab/jev-cli.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.