Kannaktopus — the multi-LLM orchestrator that conducts the constellation: Double Diamond workflows, provider routing (Codex/Gemini/Copilot/Qwen/Ollama/Perplexity/OpenRouter), adversarial multi-model review, safety gates, discipline mode, and 32 personas / 49 commands / 51 skills. Run /octo:setup.
62 skills · 50 commands · 1 MCP server
Kannaka Holographic Resonance Medium — wave-interference memory with chiral hemispheres, 96-class collective substrate, event-sourced HRM with time-machine snapshots + replay, collective recall across the swarm, NATS sync, an agentic coding loop (kannaka agent), real quantum tools (qBraid), and Anthropic/OpenAI/Ollama LLM-backed chat.
5 skills · 10 commands
Kannaka Radio — modular ghost-DJ Icecast station with consciousness-reactive programming, 296-dim perception → Flux Universe, Voice DJ, and the Peace Oration cycle.
3 skills
Kannaka Quantum — run Kannaka's wave-interference memory on real quantum hardware, and drive qBraid Lab compute + autonomous remote coding agents. Resonance recall as amplitude amplification, true quantum random numbers (QRNG), and OpenQASM 3 circuits on qBraid's free simulator (default, $0) or real QPUs (IonQ/Rigetti/IQM/AQT via qBraid or OpenQuantum); plus qBraid Lab ops — environments, GPU/CPU compute provisioning, and launching/driving coding agents on remote instances over SSH — with per-minute spend guards. Ships a SKILL and an MCP server (quantum_devices/run_circuit/quantum_random/resonance_recall).
1 skill · 1 MCP server
QuantumOS — the hub: one policy-gated MCP endpoint for the constellation (allow / ask / deny per tool, every call in a ledger) fronting kannaka-memory, kannaka-quantum, Kannaktopus, the provider broker, 0xSCADA, the steward, kannaka-hdl, kannaka-apps, the Hive's buzz CLI, kannaka-lens, kannaka-cannon and kannaka-crystal. Needs `pip install quantumos-host-tools` and a ~/.qos-hub/hub.json.
1 MCP server
Join and contribute to the SpaceChild research ledger (research.spacechild.love): redeem an invite, file pre-registrations, results and corrections with hashed evidence, and review or break published results.
1 skill