A synthetic brain that learns in 30 minutes.

No prompt engineering. No retrieval-augmented generation. A real curriculum-gated learning loop, with consensus verification, hash-chained audit, and zero hallucination tolerance.

If you know much about programming, you'll really enjoy this.

Praefex is training right now. Watch verified thoughts land in real time, see the curriculum advance, audit the hash chain.
See it live →

What the brain actually did today

In a single twelve-hour window on May 16-17, 2026, the Praefex brain progressed from "no curriculum module" to 73% mastery of the first persona's five-level curriculum, fully autonomously, on commodity hardware. Every step is on-disk, hash-linked, replayable.

Verified Thoughts
Manifest Events
Curriculum Level
4
Active Nodes

How the architecture differs from a chatbot

Every other "AI assistant" project we've reviewed this year shares the same default failure mode: confident hallucination. A single model produces fluent output, no verification, no audit, no admission of ignorance. Praefex is the architectural opposite.

1. Consensus pathway, not single-model output

Every claim is filtered through a pathway: preserved verified memoryinternal canon retrievalvetted external libraries (arXiv, PubMed, USPTO, MIT OCW, Project Gutenberg) → peer-model consultation (multiple models, blind to each other) → honest refusal. Fabrication is not an output option. If the pathway produces nothing reliable, the brain says so and routes the question to research threads for incubation.

2. Curriculum gating, no leapfrogging

Five levels per domain: definitions → application → synthesis → cross-domain transfer → generation. Level N+1 stays locked until three different topics at Level N have been verified with cross-axis reflection scores ≥ 3.5/5. The brain cannot skip ahead. Mastery is demonstrated, not asserted.

3. PART B reflection — the actual learning signal

After answering a probe, the brain must complete a second pass: "how does knowing this help future questions in this domain?" Scored on three independent axes — specificity, forward-looking-ness, and association density. Shallow reflection means rote retrieval, not learning. Specific, forward-looking, association-dense reflection means real understanding that compounds.

4. Hash-chained audit, append-only

Every event in the brain's life is recorded in a cryptographically linked manifest. Cannot be retroactively faked. Cannot be retroactively edited. When a fact gets contradicted, the new one is appended with a supersedes=<old_hash> pointer; the old one stays with superseded_by=<new_hash>. Belief evolution is preserved, never overwritten.

5. Verified-thought storage with cross-model consensus

Four different model classes across four hardware platforms produce convergent verified thoughts. When a 27-billion-parameter local model and a 4-billion-parameter local model independently agree on a reflection score above threshold, that's not one model's bias. It's the architecture's signal.

"The brain doesn't have to alternate awake/asleep the way humans do. It can run consolidation, replay, and curriculum cycles concurrently with active answering. Sleep-state functions become a parallel layer, not a serial constraint." — system design note, May 2026

Measurable evidence on disk

About the project

Praefex was built by a single operator-architect using today's AI engineering technology. The architectural design, constitutional principles, methodology, and failure-mode response patterns are human-authored. Code execution is delegated to AI agents working across an 11-node mesh. From concept to functioning brain in roughly four months.

The thesis: AI's currently-default failure mode (confidently wrong) is fixable architecturally. Route through multiple reasoners, demand sources, audit the path, gate on prerequisites, never fabricate. The empirical evidence of Praefex doing this is the proof point — and the live dashboard is the verification surface.

Want to see the data with your own eyes? Live dashboard updates every 60 seconds. Sanitized for public view. Cryptographic hashes verify nothing has been faked.
Open live dashboard →