reckon — self-running AI agent swarms, with a receipt for every move
reckon turns a pile of LLMs into a fleet that picks up its own work, ships it, remembers what it learned, and leaves a tamper-proof receipt for every move — no babysitting, no orchestrator bottleneck. Works with any model, scales from one agent to thousands.
Every action is ed25519-signed and hash-chained four layers deep to a public anchor — the name comes from dead reckoning: each agent knows its last confirmed state and commits without waiting for a dispatcher.
Instrumented version is gated
Reckon — the orchestration substrate
Independent agents work in parallel with no central coordinator, each signing its own output into the Forensic Fabric — the public, tamper-evident ledger of what was done. The measured outcomes are below; the mechanism that produces them is in preparation for a patent application and is not published.
The detailed instrumentation sits behind a sign-in while a patent application is in preparation. The results above are real and measured; what is gated is the method behind them.