Memoria Viva

Note

This analysis is based entirely on self-reported information from the project description. No external verification or historical data are available. All claims are treated as stated by the author and not proven.

The description states that Memoria Viva is:

• A system for managing attention and commitments in response to external events.
• Built for founders and small teams whose commitments are scattered across calendars, messages, and operational systems.
• Designed to transform a verifiable external event into a reproducible before-and-after attention state.
• Capable of:
  • Preserving existing commitments
  • Creating new commitments when justified by an event
  • Computing versioned attention rankings
  • Representing dependencies, conflicts, protection, and conditional displacement
  • Keeping uncertainty visible instead of inventing certainty
  • Identifying decisions requiring human confirmation
  • Producing evidence-backed receipts explaining why the state changed

It uses a deterministic engine and a GPT-5.6 explanation layer, where the latter does not alter system outputs but only explains them.

Inference The product is described as a hybrid deterministic-AI system with strong emphasis on traceability and non-decision-making authority of the language model.

The author states:

• The inspiration came from personal experience with scattered commitments and lack of tools that explain how new opportunities affect existing ones.
• The goal was to move beyond simple task lists or memory storage into a system where "attention should be a traceable decision."
• Memoria Viva is positioned as a tool for managing attention in response to external events, not just storing tasks.

Inference This is a positioning shift from generic productivity tools toward a more structured, evidence-backed approach to attention management. The claim evolution centers on moving away from "remembering" to "understanding and tracing decisions."

The description states:

• Memoria Viva is built for founders and small teams whose commitments are scattered across calendars, messages, and operational systems.

Inference The initial target customer segment appears to be early-stage entrepreneurs or small team leaders who face complex attention management challenges due to fragmented workflows. No further segmentation or persona details are provided.

Not evidenced.

The description does not contain any information about pricing, monetization strategy, revenue model, or commercial viability beyond the fact that it was submitted as a hackathon project.

Finding

No evidence of business model or pricing structure.

The system has two clearly separated layers:

1. Deterministic engine:
   • Validates sanitized fixtures against canonical JSON schemas
   • Builds immutable Snapshot T0 and T1
   • Applies one canonical trigger
   • Constructs a 21-change GraphDelta
   • Generates an immutable RunRecord
   • Compares results against three human-authored oracles

1. GPT-5.6 explanation layer:
   • Does not decide what deserves attention
   • Receives only completed, sanitized deterministic answers
   • Provides explanations and recommendations without altering system outputs
   • Uses strict Structured Outputs validated before display

The project was built using:

• Codex as primary engineering collaborator
• Python, OpenAI API, Streamlit, JSON, Graphviz, GitHub, unittest, schema, SHA-256, responses, codex, GPT-5.6

Inference The architecture shows deliberate separation between decision logic and explanation, with strong emphasis on deterministic replayability and validation.

Not evidenced.

The description mentions:

• A public demo using a reviewed synthetic founder scenario
• 260 passing tests
• No-login deployment
• Public-safe synthetic scenario
• A complete deterministic T0 → trigger → T1 replay
• Three human-authored oracle comparisons passing
• Stable ReplayResult digest
• 21-change GraphDelta across seven semantic categories

However, there is no mention of:

• Real users or customers
• Revenue or monetization
• Adoption metrics
• Product usage data
• Any form of live integration or production use

Finding

No evidence of traction or real-world adoption beyond the synthetic demo.

Not evidenced.

The description does not reference existing competitors, market positioning relative to other attention management tools, or competitive advantages claimed by the author.

Finding

No evidence of competitive landscape or differentiation strategy.

1. No real-world usage or traction – The entire system is described as a synthetic demo with no live users or adoption.
2. Unproven commercial viability – No business model, pricing, or revenue data are provided.
3. High technical complexity without clarity on user experience – While the architecture is detailed, it's unclear whether the interface remains accessible to non-technical users.
4. Dependency on GPT-5.6 for explanation layer – If the LLM becomes unavailable or returns invalid results, the system may still function but lose its explanatory value.
5. Limited scalability assumptions – The system is described as built for small teams and founders; no indication of how it scales to larger organizations.

Inference The project lacks commercial proof-of-concept and real-world validation, which raises concerns about viability beyond the hackathon context.

1. What specific external events does Memoria Viva currently support?
2. How is the deterministic engine validated in practice? Are there any known edge cases or failure modes?
3. Has the system been tested with actual users, not just synthetic scenarios?
4. What are the plans for integrating real-world data sources like calendars and communication platforms?
5. Is there a plan to monetize this tool, and if so, what is the proposed business model?
6. How does Memoria Viva handle privacy concerns when ingesting sensitive data from users?
7. What kind of feedback have you received from potential early adopters or partners?