Docs

Category 03 of 12

The Brain

How Agentis agents form, recall, and ground memory over time: the formation pipeline, hybrid recall with citations, knowledge bases, and living skills.

Pages in this category

One Substrate, Many Planes

All Brain memory lives in one table, discriminated by plane, scope, and type — why a single substrate beats a dozen disconnected memory stores.

Memory model
The Formation Pipeline: Extraction, Judge, PACER, Feynman Repair

Writing memory is reconciliation, not append: deterministic extraction, a two-phase Formation Judge (ADD/UPDATE/NOOP), PACER routing, and Feynman repair.

FormationPACER
Feynman Repair: A Grounded Self-Explanation, or Nothing at All

The real Feynman technique made concrete: force a compact explanation of a failure, validate it against real evidence, and commit nothing at all if it isn't actually grounded.

FeynmanSelf-explanation
Recall & Grounded Answers

Hybrid TF-IDF plus embedding recall with freshness decay, trust weighting, MMR diversification, and citation-or-abstain grounded answers.

RecallGrounding
Grounding & Evidence

An evidence ledger, versioned sources, claims with an approval workflow, conflict resolution, and per-agent grants — the Brain's organizational-intelligence engine.

GroundingEvidence
Knowledge Bases

Ingest, chunk, embed, auto-link, and enrich uploaded documents — PDFs, docx, and text — into searchable knowledge atoms.

Knowledge basesRAG
Living Skills

Body on disk, metabolism in the Brain: a real SKILL.md a harness loads natively, paired with a confidence-tracked skill atom that graduates by reuse.

Skills
Personal Brain

Private, per-user notes and a personal knowledge graph, distinct from the shared workspace Brain.

Personal Brain
Shared Intelligence

The cross-scope brain graph that unifies chat-as-dispatch with the rest of workspace memory.

Shared intelligence
Brain Maintenance & Health

Immediate-if-overdue and daily lifecycle, quality hygiene, compression, reembedding, and health checks that keep recall honest.

Maintenance
Memory in Numbers: Decay, Trust Weighting & Diversification

The scoring mechanics behind recall: freshness decay, trust weighting, reranking, and MMR diversification, explained with real inputs.

RankingMMR
The Benchmark Scorecard

A LoCoMo/BEAM-style eval harness runs as a CI gate on every change to the Brain — single-hop, multi-hop, temporal, knowledge-update, unanswerable, and mid-task recovery, measured, not assumed.

EvaluationBenchmarks
What the Brain Remembers (and What It Refuses to Guess)

Why deciding what to remember is a judgement call, what the on-device model can and cannot do — measured — and the tier you choose in Settings.

FormationSettings

Continue