Safety evaluation agents for content moderation and harm detection.
Loop agent and critic for Claude Code — enforce task completion before stopping
Pure-function policy-envelope evaluator for Glide agent banking. Evaluates 13 policy axes (per_tx_max, daily_cap, velocity_caps, counterparty_allowlist, time_window, etc.) against a TransactionIntent and returns ALLOW / DENY with reason codes.
Reference TypeScript runtime for the Agent Personality Protocol (APP) v1
CLI wrapper for LLM Test Bench - A production-grade framework for testing and benchmarking Large Language Models
AI agent with an internal ecology of strategies that compete and evolve based on real task performance
iClasser React Library
A simple, interpreted programming language designed for learning and experimentation.
This repo provides a **deterministic reducer** (state machine) skeleton for applying the events emitted by the DSL ruleset.
Daedalus SDK - Enterprise AI governance + reasoning layer with symbolic RL
  
See the inlined contents of a JS function
Interpreter for the lny programming language with multilingual support
Trust score computation from verification evidence - drives SHIP/NO-SHIP decisions
iClasser React Native component
Core DSL engine - expression evaluator, dependency tracker, schema loader
a stylus compiler for wepy
Slave stdio node js evaluator
CSP-compliant interpreter for Vega expressions.
**DiaEngine** is a minimal, intent-driven web backend runtime. It enforces executable semantics, structured context, and safe side-effects.
Browsary Pipeline AI Agent
Library for evaluting piecewise polynomials
An expression evaluator written in typescript with the goal to support SQL like WHERE clauses.
UAICP reliability primitives: identity validation and policy evaluation