Bounded-autonomy plugin harness for agents. Intent to implementation: ready, then go.

The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.

Skills for agentic coding CLIs: output you can ship with minimal review, on work you can tell was worth doing.

A control plane with a durable state kernel for long-horizon agents and teams. Keep work moving and improving across sessions, with less human attention.

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

Persistent project-scoped memory for Claude Code. Auto-loads on session start, structured by schema, hot/cold layered.