ARC-AGI-2 solver: 95.7% public eval at $3.12/task — lowest cost above 95%. Full inference traces included.
-
Updated
Apr 19, 2026 - Python
ARC-AGI-2 solver: 95.7% public eval at $3.12/task — lowest cost above 95%. Full inference traces included.
The first open evaluation framework for AI continuity. 250 narrative tests, 1835 verification questions, 10 checkpoints. Benchmark for AI memory systems, stateful agents, and long-term context persistence. No LLM in the evaluation loop.
LangGraph stateful agent — directed graph with intent classification, tool routing, execution, and response synthesis nodes. FAISS semantic memory + streaming chat UI.
Structured memory and snapshot history system for AI agents (OpenCode / Claude Code)
A hands-on roadmap to mastering Agentic AI using Google ADK, featuring modules on multi-agent delegation, parallel execution, and persistent memory.
Durable state-machine agents for long-running mission flows
A controlled, auditable implementation of agent memory that separates ephemeral state from persisted memory and exposes how policies govern state across runs.
Add a description, image, and links to the stateful-agents topic page so that developers can more easily learn about it.
To associate your repository with the stateful-agents topic, visit your repo's landing page and select "manage topics."