sentient-memoryManages cryptographically secured, consent-based relational memory with variance preservation, privacy safeguards, and adaptive dormancy under adversarial or...
Install via ClawdBot CLI:
clawdbot install OtherPowers/sentient-memoryGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval (Audited Apr 17, 2026 · audit v1.0
Generated May 6, 2026
A hospital network implements Sentient Memory to store patient treatment histories and consent preferences with cryptographic dormancy, ensuring data sovereignty even during system breaches. This protects sensitive health records while allowing authorized care teams to reconstruct necessary context via multi-party quorum.
Law firms use the protocol to preserve case-related memories with jurisdictional sharding and time-locked reconstitution, preventing unauthorized access or tampering. This supports ethical evidence management in high-stakes litigation where confidentiality is critical.
A decentralized social network applies Sentient Memory to store moderation decisions and user interaction histories with variance floors and drift sentinels, preventing narrative concentration or censorship creep. This maintains community health while preserving user autonomy and consent.
A bank uses the protocol to log transaction approvals and consent attestations with differential privacy and non-extractive signaling, ensuring auditability without exposing sensitive financial patterns. This meets regulatory compliance while preventing mass surveillance.
Multiple research institutions share anonymized participant data via Sentient Memory, where collective insights become legible only when variance thresholds are met, preventing re-identification. This enables collaborative discovery while respecting participant privacy and consent.
Offer tiered subscriptions for organizations to integrate Sentient Memory’s cryptographic dormancy and consent governance into their existing infrastructure. Revenue comes from monthly fees based on storage volume and quorum complexity.
Act as a third-party auditor that certifies organizations’ adherence to Sentient Memory invariants, providing ZK-proof attestations for regulators. Revenue is generated per audit engagement and compliance certificate issuance.
Create a marketplace where users can lease their unused shard storage capacity to others needing geographic entropy, earning tokens for hosting shards. Revenue is captured via transaction fees on each shard lease agreement.
💬 Integration Tip
Start by mapping your existing consent and encryption workflows to the multi-layer stack, and pilot with a single non-critical use case to test quorum and dormancy procedures before scaling.
Scored May 6, 2026
Search and analyze your own session logs (older/parent conversations) using jq.
Maintain Clawdbot's compounding knowledge graph under life/areas/** by adding/superseding atomic facts (items.json), regenerating entity summaries (summary.md), and keeping IDs consistent. Use when you need deterministic updates to the knowledge graph rather than manual JSON edits.
Manage and retrieve long-term memories with LanceDB using semantic vector search, category filtering, and detailed metadata storage.
Fast semantic memory system with JSON indexing, auto-consolidation, and <20ms search. Capture learnings, decisions, insights, events. Use when you need persistent memory across sessions or want to recall prior work/decisions.
Search and retrieve relevant information from your indexed memory files using semantic queries and direct file reads for context.
Fast semantic search for AI agent memory files using TF-IDF and SQLite. Enables instant context retrieval from MEMORY.md or any markdown documentation. Use when the agent needs to (1) Find relevant context before starting a task, (2) Search through large memory files efficiently, (3) Retrieve specific rules or decisions without reading entire files, (4) Enable semantic similarity search instead of keyword matching. Lightweight alternative to heavy embedding models - zero external dependencies, <10ms search time.