Skip to content
Cognition EnginesFORGENous

Most agents are brilliant.Almost none of them remember.

Nous is a continuous memory platform for AI agents. It gives any LLM persistent memory, decision intelligence, and the ability to learn from its own mistakes — an architecture that treats memory as part of cognition rather than as a database bolted to the side.

BRAINEvaluationQuality scoringBrier calibrationDecision trackingKnowledge graphCEL guardrailsHEARTMemoryEpisodesFactsProceduresWorking memoryCensorsCOGNITIVELOOPSENSEFRAMERECALLACTMONITORLEARNSLEEP CONSOLIDATION16 phases, between sessions
Automated tests
5,573

across 303 files

Feature specs
75

written before the code

Commits
1,151

single-engineer project

Figures generated from the Nous source repository, 2026-08-11.

The problem

Statelessness is not a missing feature. It is the ceiling.

An agent that forgets cannot compound. It repeats corrected mistakes, rebuilds context the user already supplied, and has no way to tell a judgement that worked from one that merely sounded convincing.

Stateless agent

  • Repeats mistakes it has already been corrected on
  • Rediscovers preferences every session
  • Accumulates no skill from work it has already done
  • Cannot say whether its confidence was ever justified

With Nous

  • Corrections become censors — a mistake blocks itself next time
  • Five memory types, each with a distinct retention rule
  • Procedures are learned, scored, and reused across sessions
  • Brier scoring measures whether confidence tracks reality

Architecture

Brain and Heart

Following Minsky's Society of Mind, cognition is split into two organs joined by an event bus: one that judges, one that remembers. Neither is useful alone.

Brain

Evaluation and judgement
Quality scoring
LLM-judged response quality against a multi-dimensional rubric.
Brier calibration
Tracks whether stated confidence matches real outcomes.
Decision tracking
Every decision logged with its outcome, so history is evidence.
Knowledge graph
Relationships across facts, entities and episodes via spreading activation.
CEL guardrails
Common Expression Language rules enforcing behavioural bounds.

Heart

Memory and identity
Episodes
Conversation summaries, temporally indexed and importance-scored.
Facts
Extracted knowledge with confidence, categories and staleness decay.
Procedures
Learned skills with triggers, tools and effectiveness ratings.
Working memory
Per-session context: active frame, loaded facts, execution ledger.
Censors
Guardrails that block known-bad patterns before they execute.

Memory architecture

Five kinds of memory

5

Modelled on human memory systems. Each type has its own write path, retention rule and retrieval strategy — collapsing them into one store is what makes most memory layers degrade as they grow.

Episodic

What happened and when. Conversation summaries with temporal ordering and importance scoring.

Semantic

What the agent knows. Facts carrying confidence scores, categories and staleness decay.

Procedural

How the agent works. Skills with triggers and effectiveness ratings, evolved via EvoSkill.

Working

What is live right now. Current frame, loaded facts, active task, execution ledger.

Censors

What must not happen. Regex and semantic guardrails evaluated before execution.

Capabilities

What it actually does

75 specs

Six of the 75 shipped feature specs. Each was written before its implementation, which is why they can be counted.

Sleep consolidation

Unique

A 16-phase autonomous cycle — pruning, compaction, contradiction resolution, procedure learning, graph densification and more — that runs between sessions.

Correction learning

F039

User corrections are detected and dual-written to facts and censors, so a mistake becomes a permanent guardrail.

EvoSkill

Unique

Procedural memory that proposes, tests and merges its own skills rather than waiting to be taught.

Decision intelligence

Core

Confidence, outcome and Brier score on every decision — the agent calibrates its own judgement.

Hybrid retrieval

Core

Vector, keyword and graph expansion fused by Reciprocal Rank Fusion, then re-ranked for diversity.

Execution integrity

Core

Action gating, claim verification and an execution ledger — the defence against hallucinated actions.

Foundations

Built on published work

Every architectural choice traces to a paper rather than to taste. The research below is what the design is accountable to.

Minsky

1986

Society of Mind — organ duality, frames, censors, K-lines

MemAlign

2025

Correction learning — dual-memory mistake capture

A-MEM

2025

Agentic memory — self-organising knowledge evolution

TIM

2025

Trajectory learning — improving from execution paths

ACC

2025

Adaptive context control — dynamic memory management

xMemory

2025

Diversity-aware retrieval — MMR re-ranking

77,369
Lines in the platform package
150
Modules
62
Schema migrations
5,573
Tests
Company · Cognition EnginesArchitecture · FORGEAgent · Nous

Memory is the part that compounds.

The architecture, the feature specs and the research trail are all public. Start with the docs.