9 projects
surprisal-search
MCTS with Bayesian surprise for open-ended scientific discovery
rlve-gym
RLVE Gym environments shim - exposes Gym.environments and Gym.parameter_controllers
arc-advisor
The learning co-pilot for AI agents. Implements the Executor-Advisor pattern for building self-improving agentic systems.
arc-runtime
Lightweight Python interceptor that prevents AI agent failures in real-time
acp-evals
Production-grade evaluation framework for Agent Communication Protocol (ACP) agents
arc-verifier
Verification and evaluation framework for autonomous agents across agentic protocols
arc-eval
ARC-Eval: Agent Reliability & Compliance evaluation platform for LLMs and AI agents
arc-trace
Lightweight, framework-agnostic Python SDK for AI agent tracing with automatic prompt extraction
arc-memory
Arc Memory - Local bi-temporal knowledge graph for code repositories
