I build tools for people who work across multiple AI agents and want the results to remain useful after a session ends.
Your agents do valuable work. Open Nova makes sure that work does not disappear with the session.
Open Nova is a structured, local-first AI asset operations system. It brings activity from Codex, Claude Code, Gemini CLI, OpenClaw, and Hermes into one durable layer, then turns it into:
- daily, weekly, and monthly work narratives;
- a reviewable task graph grounded in real execution evidence;
- reusable learning assets and technical records;
- shared, searchable memory through a read-only RAG boundary;
- a local Dashboard for understanding work across agent runtimes.
The deterministic parts handle collection, parsing, attribution, persistence, and security boundaries. LLMs help with summarization, task extraction, and knowledge organization. Your runtime data and generated assets remain under your control.
Repository · Website · Interactive Dashboard Demo
|
One living dial for 14 AI coding tools.
TokenClock reads local usage logs from Claude Code, Codex, Gemini CLI, OpenCode, and more, then turns them into an always-visible view of tokens, messages, active tools, and per-session usage. Local-only · zero upload · native Liquid Glass on macOS 26+. Explore TokenClock → |
- Local by default — private work should not need a cloud account to become useful.
- Interoperable by design — knowledge should move across tools without one agent owning the whole workflow.
- Durable outcomes — sessions should become evidence, memory, and reusable assets instead of disposable chat history.
- Explicit boundaries — automation is most valuable when its permissions, data paths, and failure modes stay visible.
My Gods are in the Rain.