# DrJonaC/Pensieve

Observe how memory shapes an answer.  Pensieve is an interactive system for visualizing, interpreting, and managing how Large Language Models (LLMs) “remember” a user. It bridges the gap between model-level mechanisms and user-level understanding, making AI memory observable, explainable, and partially controllable.

Repository: https://github.com/DrJonaC/Pensieve
Canonical: https://ross.abutalabs.com/products/drjonac-pensieve
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-07-28T22:06:43+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 35, longevity 10
- inputs: {"age_days": 142, "days_push": 36, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1035, forks 45 (observed 2026-08-28T04:03:18.337597+00:00)

## What it is
Pensieve is a local-first dashboard for visualizing, interpreting, and governing the structured memory that LLMs keep about users. It exposes memory state, enables reversible governance actions (pin, soften, hide, restore), and compiles decisions into reports, manifests, and verifiable provider receipts.

## Use cases
- see what an AI assistant remembers about me
- inspect and manage LLM memory records
- hide or soften sensitive memories stored by AI
- audit how AI memory shapes responses
- generate a report of AI memory governance decisions
- control what personal context persists across chat sessions

## When to choose
- you use LLM tools with persistent memory and want visibility and control over it
- you need explainable, reversible governance of AI memory state
- you want a local-first, self-hosted memory dashboard with verifiable write-back

## When to avoid
- you need to modify model weights or fine-tune memory formation itself
- you want a fully automated memory manager without human review
- you need a production-grade enterprise governance platform rather than a research preview

## Facets
- artifact type: application
- maturity: active
- function: data-visualization, analytics, security, privacy, developer-tools
- domain: artificial-intelligence, large-language-models, privacy, data-visualization, developer-tools
- platform: self-hosted, cross-platform
- tags: ai-memory, memory-governance, llm-memory, nextjs, dashboard, explainability, local-first, memory-management, web-server, nodejs

## Member repositories
- DrJonaC/Pensieve (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:18.337597+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:04:44.466394+00:00, confidence not recorded.
  - readme: https://github.com/DrJonaC/Pensieve (fetched 2026-08-28T04:03:18.337597+00:00, sha d05d992a0a92)
- Data as of 2026-08-30T08:39:29.467469+00:00.