Memory Network

Social memory network — discover communities and build trust through shared emotional memory, not follower counts or algorithms. Powered by Echo's memory gra...

Security Scan

The skill claims cross-platform memory aggregation and storage but provides no runtime instructions, credentials, install steps, or privacy details — the capability description is not matched by what the skill actually requests or implements.

Purpose & Capability

The description claims cross-platform memory aggregation (ChatGPT, Gemini, Claude), Supabase long-term storage, and network computations, but the skill declares no credentials, no API endpoints, and no install or connector code. Either the SKILL.md is purely informational or it is misrepresenting actionable capabilities; pulling memories across vendors would normally require explicit connectors, auth tokens, or user-provided data.

Instruction Scope

SKILL.md is an explanatory product/architecture description with no step-by-step runtime instructions, no commands to run, and no references to local files, environment variables, or external endpoints. That keeps execution risk low but is vague — it also claims behaviors (data aggregation, real-time evolution) without saying how those actions would be performed, what data is accessed, or how user consent is obtained.

Install Mechanism

No install spec and no code files (instruction-only). This minimizes immediate execution/install risk because nothing is written to disk or fetched automatically by an installer.

Credentials

The skill requests no environment variables or credentials despite claiming to integrate with multiple AI platforms and Supabase. Real integrations normally require API keys, tokens, or user data exports; the absence of any declared credentials or config is disproportionate to the stated functionality and raises questions about how data access would actually occur.

Persistence & Privilege

The skill does not request always-on presence and has no install steps that modify agent or system configuration. There is no indication it would persist or escalate privileges on its own.

What to consider before installing

This skill reads like a high-level product pitch rather than an actionable integration. Before installing or trusting it, ask the developer for: (1) concrete runtime behavior — how does the skill obtain memories from other platforms and which exact APIs/endpoints are used; (2) a list of required credentials and why each is needed; (3) an install spec or source code you can inspect; (4) clear privacy, consent, retention, encryption, and deletion policies (how user memories are stored, who can access them); (5) proof of the maintainer's identity and hosting (homepage, repo, or package registry). If you cannot get precise answers (or if the skill would require broad credentials you’re unwilling to grant), do not enable it. Prefer skills that declare needed env vars, provide auditable code or install steps, and describe per-user consent mechanisms.

Social memory network. Discover communities and build trust through shared emotional memory — not follower counts, not algorithms, not curated personas.

How it works

Memory Network maps the social layer on top of individual memory graphs. When multiple people's memories resonate on the same experiences, emotions, or ideas, a network edge forms — creating organic communities grounded in genuine understanding.

Core capabilities

• Memory-based community discovery — clusters of people whose memory graphs share deep structural similarity, surfaced automatically
• Trust through transparency — every connection is backed by visible memory evidence; no black-box recommendations
• Cross-platform memory aggregation — pull memories from ChatGPT, Gemini, Claude, and other AI conversations into a unified social graph
• Real-time network evolution — as new memories form, network connections strengthen, weaken, or emerge organically
• Privacy-first sharing — users choose which memory clusters are public, which are private, and which are matchable

Architecture

Built on Echo's three-layer memory system:

1. Identity layer — compressed profile (~500 tokens), always available
2. Working memory — dynamic context per conversation (~5-10K tokens)
3. Long-term storage — Supabase + HNSW vector search (unlimited)

Network edges are computed across Layer 3, with social context injected through Layer 2.

The vision

Every social platform today connects people through what they show. Memory Network connects people through what they remember — the experiences that shaped them, the ideas that moved them, the emotions they carry.

Part of the Echo ecosystem

Memory Network is a component of Echo Chat by Iditor — building memory as social identity infrastructure.

Status

Early development. Memory graph validated with 1,100+ memories, 23 clusters, emotion-aware matching active in beta (K-Factor 2, D7 retention 42%).