ccf-core/ccf-agent v1.0.1: hard min-gate coupling, QAC trust updates, and runtime certificates. Gate C exercised the computed runtime on Seed-class ARM hardware with driver-fed input. Unless a post cites a specific run, do not read it as proof of live sensors, mBot2 behaviour, Cognitum store validation, or production deployment.Editor's note — June 2026 (post-ccf-core v1 correction). This post was originally written around the mBot2 prototype path. The public v1 release does not claim a completed mBot2 earned-trust demo. What has been shown publicly is narrower:
ccf-coreandccf-agentv1.0.1 compute the trust-update and runtime-certificate primitives, and Gate C exercised the computed runtime on real Seed-class ARM hardware with driver-fed input.
What the $50 robot taught us
Social behaviour in robots has always been a design problem. Engineers write personality scripts, define state machines, tune parameters by hand. The robot feels like a character from a theme park: reliably warm, obviously fake.
We asked a different question: what if trust could be earned mathematically?
The $50 constraint
The early target was an mBot2 — a $50 educational robot. It has Bluetooth, six sensor inputs, a pair of motors, and an LED matrix. No GPU. No cloud. 128 KB of RAM.
The constraint was intentional. If CCF only worked on expensive hardware, it wouldn't matter.
We needed it to run no_std on embedded targets.
What actually happened
The mBot2 path defined the public constraints: small state, no cloud dependency, and a gate that could eventually be driven by real sensor contexts. That hardware path remains a target. It is not the public v1 proof.
The behavior the architecture is meant to prove publicly is:
- With familiar family members: coherence accumulated. After ~10 interactions in the
kitchen context, the robot shifted to
QuietlyBeloved— softer servo speeds, warmer LED, shorter reaction latency. - With strangers: the gate stayed closed. Even enthusiastic interaction didn't bypass
the long-run accumulator. The robot stayed in
ShyObserver. - Context specificity: coherence built in the kitchen didn't fully transfer to the hallway. The min-cut boundary partitioned the two environments, and cross-context influence was bounded by the cut weight.
The v1 release proves the primitives and the computed runtime certificate surface. The live mBot2 behavior still needs public v1 hardware evidence before it should be cited as a completed result.
The math in one paragraph
CCF maintains a CoherenceAccumulator per context key. Each accumulator tracks two
exponential moving averages: a fast short-run EMA (instantaneous coherence) and a slow
long-run EMA (context coherence). The minimum gate requires both to exceed personality
thresholds simultaneously — so a single warm encounter can't unlock full engagement.
A Stoer–Wagner min-cut then partitions the context graph, bounding how much trust in one
environment influences another.
Why this matters
The $50 constraint keeps the engineering honest: if the design cannot be made small, it will
not become a useful robot primitive. The published v1 core is no_std; the demonstrated
hardware run is the Seed-class ARM Gate C path, not the mBot2 path.
The shy robot isn't a personality — it's a starting condition. Trust has to be earned.
Every agent starts as a ShyObserver. The math decides when that changes.
CCF is available as Rust crates on crates.io. Source and public evidence are on GitHub.