0
Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to System 2 and a human queue. Optional TypeSafe Jev.
Local alternatives to Jev — page 7
Independent models and shims that follow the System One interface. They can replace hosted Jev for some workloads; they are not TypeSafe products.
195 active projects in this collection. All collections →
/compact-jev: Jev-guided verbatim compaction for Claude Code through Vercel AI Gateway, separate from /compact.
project
0
A local Jev-compatible decision engine powered by a 1.16 GB quantized 8B model.
0
Private Jev project workspace
0
Local playground for decision models in the shape of TypeSafe's Jev, running the open openjev replication (Qwen3.5 as an NLI cross-encoder). CPU-only, no API key.
Measures whether TypeSafe's Jev decision model flips actions on identical replays near shipped thresholds across 12,705 calls. Replication data, harness, and independent verification.
0
Kev decision models, with MiniCPM5 base support (fork of jaredpalmer/kev)
0
MCP server exposing the Laya System-1 decision engine (Jev) as agent tools
A Jev-compatible REST API wrapping the Laya System 1 decision model
0
No project description available.
One C# IDecider, three engines: TypeSafe Jev (cloud), any local model in a constrained-decoding harness, and a fake for tests. 'System One' bounded decisions in .NET.
Reproducing the Jev decision interface
A curated list of decision models similar to, alternatives to, or reimplementations of Jev (TypeSafe AI's System One model for typed decisions).
TypeSafe Jev SystemOne structured-judgment plugin for DeepSeek Harness (jev_judge: noul/choice/score)
An advisor called Jeff for pi: calibrated decisions via ask_jeff, backed by the Jev-compatible System One API (OpenRouter / TypeSafe / jev-agent)
Dockerized REST service, jev-compatible, that serves the Laya model (convaiinnovations/laya) for use from non-Python apps.
Scripts and raw results for a first hands-on look at Jev, TypeSafe AI's System One decision model: calibration, latency, edge cases, and a plain-LLM baseline.
Control your own Chrome by voice. Jev (TypeSafe System One) decides intent + target from typed probabilities in ~300 ms per spoken word; the extension acts before you finish the sentence. MV3 port of moritzkremb/jev-voice-browser.
0
No project description available.
No project description available.
Build evidence-backed, scoped product-equivalence graphs without inferring unverified compatibility.
tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.