HN Showcase
Back to browse
GitHub Repository

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.

58 starsPython

Atlas – local-first memory that re-evaluates beliefs when facts change

by RichSchefren·Jun 12, 2026·3 points·1 comment
Visit ProjectView on HN

AI Analysis

●●●BangerBig BrainWizardryNiche Gem

AGM-compliant belief revision that auto-re-evaluates downstream beliefs when facts change.

Strengths
  • •49/49 AGM postulate compliance is specific, verifiable, and rare in practical tooling.
  • •Ripple propagation engine recomputes dependent beliefs automatically instead of flagging stale data.
  • •SHA-256 hash chain verification on the ledger proves the revision loop actually works end-to-end.
Weaknesses
  • •Alpha status with ingestion and entity resolution on unstructured text still maturing.
  • •Niche audience limits adoption — most developers don't need belief revision systems.
Category
AI/ML
Target Audience

AI researchers, knowledge graph builders, cognitive system developers

Similar To

Obsidian · Logseq · Neo4j

Similar Projects

AI/ML●●Solid

ABES – a memory architecture for belief revision in AI agents

15-phase belief scheduler with decay mechanics, but unproven in production agent pipelines.

Big BrainWizardry
bradkinnard
103mo ago
AI/ML●●Solid

Experience-engine – reflection-based memory layer for local LLMs

Turns chat history into structured 'belief' and 'cognitive pattern' blocks you can inject into prompts, with simple APIs like run_reflection and run_synthesis that read like a research prototype. It's smart about separating V1 (domain beliefs) from V2 (transferable cognitive patterns), but it's clearly early-stage — tiny repo, Ollama-only workflow, and few commits mean you should treat it as an experimental MVP rather than a drop-in production memory system.

Big BrainNiche GemShip It
ashishluthara
314mo ago