LLM output confidence calibration — ECE scoring, temperature scaling, hallucination risk gating, and dynamic answer thresholds

Agent metacognitive monitoring and calibration — knowledge boundary detection, Ebbinghaus forgetting alerts, consolidation triggers, self-reflection, and 3-stream transformer confidence calibration (ECE + Brier)

The Sapience Suite transforms OpenClaw from a reactive assistant into a proactive agent with genuine autonomy. It learns when to act, when to propose, when to ask, and when to explore — calibrated to your actual preferences, not a static policy you had to

Character encoding detector

Character encoding auto-detection in JavaScript (port of python's chardet)

A confidence-calibration skill for any AI coding agent. Tags every claim 🟢 [VERIFIED] / 🟡 [INFERRED ~80%] / 🟠 [GUESSED ~30%] / 🔴 [UNKNOWN] so you can scan how much to trust each line.

API testing framework core

SOTA NPM module for agentic processes using local or cloud LLMs.

An npm package that uses guesslang's ML model to detect source code languages


Simple and complete React Native testing utilities that encourage good testing practices.

Spotify Confidence Open Feature provider

TypeScript library for converting Velodyne LIDAR packet data to point clouds


Configuration API

Adaptive trading intelligence system with Hebbian synapses, spreading activation, Wilson Score confidence, and adaptive calibration

Estimate calibration and wall-clock timing tools for pi agents

Deterministic confidence scorecards for RAG systems with signal policy, calibration, evaluator bridges, and index integrity

Dynamic, declarative configurations

Roav MEP is a modular JavaScript-based framework for running MEP . The application begins at `src/experiment/index.js`, which manages and calls the various views that control different aspects of the test.