Sulcus Reactive AI Memory

Name: Sulcus Reactive AI Memory
Availability: InStock
Author: mcdoolz

by mcdoolz·Mar 17, 2026·4 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainWizardry

Thermodynamic memory decay beats passive vector search—90% token reduction claimed.

Strengths

•Heat/half-life model for memories is genuinely novel vs static vector database approaches
•Three deployment modes: WASM core, MCP sidecar, and CRDT cloud sync for teams
•Reactive triggers fire on store/recall/decay events without agent polling

Weaknesses

•90% token reduction claim needs independent benchmarking against Mem0 or LangChain
•Thermodynamic metaphor is clever but adds configuration complexity with 30+ knobs

Post Description

Hi HN,

Sulcus moves AI memory from a passive database (search only) to an active operating system (automated management).

The Core Shift Current memory (Vector DBs) is static. Sulcus treats memory like a Virtual Memory Management Unit (VMMU) for LLMs, using "thermodynamic" properties to automate what the agent remembers or forgets.

Key Features Reactive Triggers: Instead of the agent manually searching, the memory system "talks back" based on rules (e.g., auto-pinning preferences, notifying the agent when a memory is about to "decay").

Thermodynamic Decay: Memories have "heat" (relevance) and "half-lives." Frequent recall reinforces them; neglect leads to deletion or archival.

Token Efficiency: Claims a 90% reduction in token burn by using intelligent paging—only feeding the LLM what is currently "hot."

The Tech: Built in Rust with PostgreSQL; runs as an MCP (Model Context Protocol) sidecar.

https://sulcus.dforge.ca/membench