Agentic AI Governance
Before an agent runs a tool, flux7 checks whether it may.
A rules engine answers in under a millisecond. When the rules leave the case open, past decisions kept in memory are consulted, then an arbitration, and finally a human when it matters. Every decision is written to a hash-chained log.
Research · Believe and act
An agent that investigates must decide what to check next, and when to stop.
Here both decisions stay out of the language model, which only reads the evidence. Belief and choice are computed by code and logged, so every run can be replayed. The first pre-registered studies ran on Kafka incidents; the next testbed will be a world of AI personas.
On real Kafka faults, a small reader filling a fixed form comes within a minute of a large model, at a fraction of the cost.
Music · Human × Machine
On a MIDI piano, an AI follows the chords and the key as they are played, and answers on the instrument.
It also reads finished tracks, from the audio file or straight from the Renoise project.
Reads chords, key and cadences live from any MIDI piano; the AI answers through the instrument, turn by turn.
Key, chord grid, melody and timbre from any mp3, flac or wav. CLI and MCP, stem separation.
Exact notes from .xrns files without Renoise running: song map, notes in beats, playable sequences.
Side projects
Small MCP servers in daily use, horoscopes computed from the real sky, and a history of Madagascar told by the evidence.
Horoscopes, sky chart, personality tests.
The history of Madagascar, by the evidence.