Local-first Agent OS that wraps Claude Code, Codex CLI, and other coding agents in a replayable Seed → Ledger → Runtime contract, driven by an interview → seed → execute → evaluate → evolve workflow loop.
Enables users to clarify vague goals through Socratic questioning and generate structured technical specifications, using a curated knowledge base and session state without external LLM APIs.
Prevents premature AI coding by transforming vague product ideas into structured specifications, architecture decisions, and acceptance criteria through a series of interrogation and compilation tools.
Living typed knowledge graph for software projects, exposed over MCP so coding assistants can capture and query modules, capabilities, flows, events, rules and decisions across sessions. SQLite-backed, schema-validated, ships as a Claude Code plugin.
Standardize Context, Not Intelligence. An open protocol and native MCP server for preserving, organizing, and serving structured project context (architecture, decision logs, domain rules, and roadmap) to AI coding assistants
(Cursor, Claude Desktop, Antigravity) with built-in CLI verification
Provides agent coordination for Claude Code through a shared blackboard, decision tracking with rationale, and local semantic search over git-trackable JSONL files. It enables users to assemble tailored context packages and manage a lightweight knowledge graph for complex development tasks.
