Memory that AI Agents Love!
A MMORPS platform for persistent, branching AI stories using Gemini 3, LangGraph, and Firestore.
Operational Ontology public reference: principles, D+L+A, governance, and write-back for stateful AI operations. No production implementation.
An AI agent that acts as a "Generative Historian," inspired by Isaac Asimov's Foundation, to simulate the emergent history of a civilization from the stone age to the stars.
Complete hands-on Agentic AI bootcamp repository covering LangGraph, LangChain, AI Agents, multi-agent workflows, RAG pipelines, tool-augmented LLM systems, memory architectures, and production-grade AI application engineering for real-world intelligent systems.
A map showing where the pieces for growing an AI family live. Non-runtime, no install, every part works on its own.
First LLM runtime that preserves chain-of-thought under continuous user interruption. S(t+1)=f(S(t),ΔU)
A shared protocol that lets multiple AI agents and sessions develop the same codebase in parallel without colliding. Documentation only - runs on git and GitHub Issues / Pull Requests.
Bring your own AI agent into Google Meet & Zoom — as a real voice participant.
Collect AI/tech updates from 7 platform families into a daily newspaper for people and a searchable feed + MCP server for agents
Safe, policy-driven personality-mode engine for LLM agents
GraphNews is a multi-agent system that acts as a self-correcting editorial team, generating newsletters
A babysitter for long-running commands: watch AI agents and batch jobs, restart them safely within declared bounds, and reach you when something needs a human. Zero-dependency bash.
Evidence-backed experiments in recurrent state, EEG-derived observer trajectories, controlled perturbations, and causal continuity.
Stateful Telegram AI Assistant powered by Gemini 2.5 Flash & LangChain. Securely manages Google Calendar (CRUD) via custom tools. Features SQL-backed conversational memory for dynamic chats, zero-downtime error handling, strict access control, and cloud-ready architecture.
A self-improving harness for terminal AI agents — it learns from failures and runs your tasks to a verified done. Plain text files and real checks, no daemon.
Caty AI — org profile, story, and principles (EN/JA/ZH/TH)
Continuum — Open Loop OS. Memory that moves. Measure Open Loop Debt, close it with Cited Motion, write results back into graph memory.
Self-governed skill-growth loop for AI agents: propose -> owner-approve -> trial -> council-review -> adopt, with an append-only ledger and mechanical growth-lint
To associate your repository with the stateful-ai topic, visit your repo's landing page and select "manage topics."