Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are automatically re-evaluated, not just flagged.

Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

ἔνδοξα — agent memory that stores beliefs, not facts: append-only, defeasible, frontier-resolved

Embeddable Rust runtime for formal AGM belief revision in LLM agents — dual-process uncertainty quantification, C=(P,I,G,R) behavioral contracts, 9 Mnemonic Sovereignty primitives, MCP 2026 native, PyO3 SDK.

Agent identity, lifecycle management, and belief revision for AI agents

Implementation of an AI agent performing belief revision (using belief base entrenchment contraction and expansion)

MnemeBrain Benchmark Suite (BMB): 48 tasks evaluating belief dynamics in AI memory systems — contradiction detection, revision, provenance, and temporal reasoning.

DTU course 02180 Introduction to Artificial Intelligence, Spring 2024

Pyton SDK for MnemeBrain — a belief memory system for AI agents. Supports MnemeBrain Lite and Full APIs.

Verifiable state plane for autonomous agents: memory, belief revision, rollback, audit, and MCP tools.

Auditable finite PoC for preference reorganization under record absence on a fixed comparison frame, with disclosure updates, bounded-coupling certificates, and machine-readable manifests.

World-state belief management and contradiction repair for AI agents

Timestamp-free benchmark for comparing write-time belief revision with equal-compute read-time correction resolution.

Episode-scoped Hermes Agent plugin that tracks beliefs and evidence by pramāṇa, maintains justification and defeat graphs, injects a bounded ledger into every model request, validates final answers, and blocks high-stakes tool actions unless their preconditions are supported.

A protocol for evidence-bound AI memory: what an AI may store about a user, how it's evidenced, and when it's revised or deleted.

Self-reorganizing knowledge structures via truth pressure. Formalizes scientific paradigm shifts computationally — old knowledge is contextualized, not deleted. Three provable invariants. Validated on miasma→germ theory and classical→quantum physics.

Finite propositional belief sets with AGM revision/contraction, Spohn ranking states, iterated revision, epistemic entrenchment, and IC belief merging.

Deterministic, non-destructive, replayable memory substrate for AI agents: an append-only claim ledger with supersession, provenance, deterministic replay, and semantic recall over MCP.