Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks
-
Updated
Sep 25, 2026 - Python
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM in one forward pass (HF + vLLM), with honest benchmarks
Rust CLI and web UI that intercepts an LLM token stream live: per-token confidence and perplexity, on-the-fly token mutation, provider and A/B prompt comparison, replay and heatmap export. OpenAI and Anthropic.
Typed choices and probability distributions from text and images with llama.cpp, Ollama, and OpenRouter
Super fast Jev like server, model agnostic, working with any OpenAI compatible endpoint
Rust CLI and library that flags low-confidence spans in LLM answers from token logprobs (offline or live via any OpenAI-compatible API) and renders per-token confidence as terminal, HTML or Markdown.
Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients
Calibrated yes/no, pick-one and scale judgments from your own LLMs, on text and images, read straight off the logprobs. Runs on vLLM.
Interactive Streamlit app that visualises token-level log probabilities from Azure OpenAI
Jev-compatible /v1/systemone server reading typed decisions from LLM logits, benchmarked against TypeSafe's Jev on the same items via JevBench
Token-level entropy trajectories from LLM logprobs. Models can measure their own uncertainty — grounding it in truth requires external verification.
Jev-style /v1/systemone API in front of any OpenAI-compatible LLM server (one-token logprob scoring, MIT)
Model-agnostic substrate for running small local LLMs well — code agents, chat, image/video, speech. Small capable main model + tiny fast worker.
A TypeScript library that answers a decision question with a probability distribution over every option, using any existing LLM
An interactive client for exploring token-level log probabilities from OpenAI-compatible chat models.
Minimal demo of calibrated LLM-as-a-judge scores from the single-call token-logprob distribution (Wang et al. 2025; G-Eval).
Self-hosted System One decision engine (TypeSafe Jev's Choice/Score/Noul contract) running locally on LM Studio, with real probabilities from token logprobs.
Jev-style typed decisions (Choice / Noul / Score) from any model whose API exposes logprobs, plus a local /v1/systemone server
A drop-in confidence gate for LLM agents: turn token logprobs into an accept / verify / ask-a-human routing decision, with honest per-model calibration. Local & open-model first, plus an MCP server.
To associate your repository with the logprobs topic, visit your repo's landing page and select "manage topics."