Local-first identity, memory, and secrets for AI agents. Portable state across models and harnesses.

Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients.

WAKE.md for AI agents: compile project state so agents stop starting cold.

Operational Ontology Framework by FSTech — public reference for D+L+A, stateful AI governance and auditable operations. No production code.

A Workspace API client library for Node.js

Deepagents for Go, the easiest way to write LLM-based programs in Go

Automate Android APK analysis and patching with a model-agnostic, multi-agent AI pipeline using portable steering context and expert bytecode patterns.

Public-safe UI boundary for local-first agent-state observability experiments; no private runtime connectors or diagnostic claims.

A Workspace API client library for Java

Receipt-first Rust runtime for portable agent state, trustworthy handoff, read-only re-entry, and an observable local TUI.

Agent State & Context Runtime Contract schemas and validation tools.

Typed memory primitive for agentic PM work. The Memory rung of The PM Scaffold.

CNAA provides a lightweight cloud backend that allows AI agents to maintain persistent state across devices through MCP. Unlike traditional memory systems, CNAA does not perform reasoning or prompt engineering. It simply stores and serves structured agent state.

Agent State CI for coding agents: revert-aware invalidation and auditable context gating.

Git-like version control, audit trails, rollback, and branch/merge workflows for AI agent state.

A lightweight desktop companion that visualizes an MCP Agent's real-time work through character animations, status text, and completion bubbles