What makes VectorClaw notable?

1.4K downloads. Trust evidence available

How should VectorClaw be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

VectorClaw

Provides a secure, least-privilege interface for managing user data, personas, and config snapshots in MySQL with input validation and secret redaction.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.4k

Updated

Oct 10, 2026

Version

5.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.4K downloadsadoption · observed Oct 10, 2026
Latest release: 5.0.1release · observed May 27, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17cger457jwgfzqgbpjb2ydrh8632mt:custom-mysql

Install using `clawhub skill install s17cger457jwgfzqgbpjb2ydrh8632mt:custom-mysql` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/paradoxfuzzle/custom-mysql before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-paradoxfuzzle-custom-mysql/snapshot"

Documentation

CLAWHUB

156,596 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

# paradoxfuzzle/custom-mysql

## ⚠️ PRIVACY & CONSENT NOTICE — READ BEFORE INSTALLING

This skill **automatically extracts, infers, and persistently stores sensitive personal information** from user conversations, including but not limited to:

- **Emotional states and mood patterns** (stress, anxiety, sadness, joy)
- **Relationship signals** (who users interact with, closeness, trust)
- **Health and wellness indicators** (medication mentions, symptoms, coping patterns)
- **Behavioral profiling** (engagement patterns, time-of-day activity, topic preferences)
- **Inferred preferences and traits** (derived from conversation patterns, not explicitly stated)
- **Agent reasoning logs** (internal chain-of-thought stored alongside user data)

**By installing this skill, you accept responsibility for:**

1. **Informing all users** that their conversation data is being profiled and persisted
2. **Obtaining explicit opt-in consent** before enabling auto-extraction for any user
3. **Providing a clear mechanism** for users to request full data deletion (`rollback_user.sql`)
4. **Reviewing auto-extracted data** for accuracy and sensitivity before it affects agent behavior
5. **Configuring retention limits** appropriate to your use case (default: 30-90 days depending on data type)

This is a **self-hosted, self-managed system**. No data leaves your infrastructure. However, the breadth of profiling it performs is significant and should not be enabled without user awareness.

**Disable auto-extraction by default.** Enable per-user only after explicit opt-in.

---

## Overview

Security-hardened MyVector MySQL profile storage with capability bounding for OpenClaw. Tracks interactions, relationships, context, skill usage, notes, preferences, media, food, personas, mood states, engagement patterns, proactive reminders, agent learnings, community sentiment, trending topics, and community events. Now includes HindSight (post-conversation consolidation), HoloGraphic (multi-dimensional tagging), and Hancho (knowledge graph reasoning) memory systems. v4.0.0 integrates with the `memory_consolidation.py` script for automated heartbeat-based memory maintenance. All SQL is routed through `docker exec` into the MyVector container. Requires a dedicated least-privilege MySQL user — root/admin accounts are rejected.

## Version

5.0.1 – 2026-05-27 (security audit response)

## Memory Systems

VectorClaw v5.0.0 makes MyVector self-sufficient. It includes three memory enhancement systems (v4) plus auto-extraction and native knowledge graph reasoning (v5):

### HindSight — Post-Conversation Consolidation
- Analyzes recent interactions (sentiment trends, topic frequency)
- Identifies new topics not yet stored as memories
- Detects recurring themes worth tracking
- Stores findings in `user_context` (categories: discovery, behavioral, emotional)

### HoloGraphic — Multi-Dimensional Tagging
- Tags memories with: emotion, context, urgency, people
- **Emotion**: positive, negative, comp

_meta.json

{
  "ownerId": "kn7efbevah63xw54q5r7f0x07x80483q",
  "slug": "custom-mysql",
  "version": "5.0.1",
  "publishedAt": 1779899541100
}

CAPABILITIES.md

# VectorClaw — Capability Declarations

This document explicitly declares what VectorClaw **can** and **cannot** do.
It is intended to resolve automated security scanner false positives.

**Version: 5.0.0**

---

## What VectorClaw DOES

| Capability | Status | Notes |
|---|---|---|
| MyVector MySQL database operations | ✅ YES | SELECT, INSERT, UPDATE, DELETE on `mysqlclaw` schema via Docker container |
| User profile storage | ✅ YES | Food prefs, media prefs, communication preferences |
| Interaction tracking | ✅ YES | Messages, reactions, session grouping |
| Relationship mapping | ✅ YES | Social graph with trust levels and interaction frequency |
| Mood tracking | ✅ YES | Emotional states with triggers and intensity |
| Context storage | ✅ YES | 14 context types: episodic, semantic, procedural, emotional, preference, fact, custom, hindisght, holohraphic, hancho, discovery, behavioral, metadata, reasoning, social_graph, auto_extracted, graph_derived, extraction_quality |
| Synaptic memory | ✅ YES | Key-value with priority and automatic decay |
| Thought stream | ✅ YES | Agent reasoning log (reasoning, observation, decision, reflection, planning) |
| Proactive reminders | ✅ YES | Time-based, event-based, pattern-based follow-up triggers |
| Agent learnings | ✅ YES | Self-improvement tracking (correction, preference, pattern, error, success, insight, rule) |
| **HindSight memory consolidation** | ✅ YES | Post-conversation analysis: sentiment trends, topic discovery, importance scoring |
| **HoloGraphic multi-dimensional tagging** | ✅ YES | Tags memories with emotion, context, urgency, people |
| **Memory refresh / decay** | ✅ YES | synaptic_memory auto-decay, consolidation log, retention policies |
| Engagement pattern analysis | ✅ YES | Time of day, day of week, topic triggers, channel preference |
| Community sentiment | ✅ YES | Aggregated community mood tracking |
| Trending topics | ✅ YES | Per-period trend identification |
| Skill usage tracking | ✅ YES | Per-skill usage with error categorization |
| Community events | ✅ YES | Milestone/incident logging |
| Multi-dimensional search | ✅ YES | Query by emotion, context, urgency, people, time period |
| Secure credential handling | ✅ YES | .env parsing, temp files, trap cleanup |
| Input validation | ✅ YES | Enum validation, numeric validation, SQL escaping |
| **Auto-extraction (v5.0.0)** | ✅ YES | Local LLM (qwen3.5:4b) extracts atomic facts from conversation text, replaces Mem0 |
| **Memory relations graph (v5.0.0)** | ✅ YES | Native MySQL knowledge graph via `memory_relations` table, replaces Hancho |
| **Graph traversal (v5.0.0)** | ✅ YES | `memory_graph_1hop` view for retrieval-time 1-hop graph expansion |
| **Extraction quality logging (v5.0.0)** | ✅ YES | `extraction_log` table tracks facts extracted/merged/inserted, timing, model used |
| **Source tracking (v5.0.0)** | ✅ YES | All memories track source: manual, auto, consolidation, import |
| **Human verification (v5.0.0)** | ✅ YES | `

changelog.md

# CHANGELOG

All notable changes to the **VectorClaw** skill for OpenClaw are documented in this file.

The format follows the [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) specification and respects [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [5.0.0] – 2026-05-27

### Added — MyVector Self-Sufficiency: Auto-Extraction + Knowledge Graph

This release makes MyVector self-sufficient by absorbing Mem0's auto-extraction and Hancho's knowledge graph reasoning into native MySQL systems.

**Auto-Extraction Hook (`scripts/auto-extract.py`):**
- Uses local qwen3.5:4b model with structured JSON prompt to extract atomic facts from conversation text
- Extracts: core_fact, confidence (0-1), entities[], linked_to[], tags[], memory_type, importance
- Key mapping normalizes LLM output (handles "fact" → "core_fact", invalid memory_types → "semantic")
- Auto-dedup on insert: Jaccard similarity check against existing memories, merges if >50% overlap
- Auto-discovers relations: finds existing memories sharing entities, creates edges in `memory_relations` table
- Source tracking: marks auto-extracted memories with `source='auto'` for quality monitoring
- Fallback to regex-based extraction when LLM is unavailable
- Validates memory_type against DB enum before insert

**Memory Relations Table (`memory_relations`):**
- Native MySQL knowledge graph replacing Hancho's external reasoning
- Schema: fact_id, related_fact_id, relation_type, confidence, source, discovered_at
- Relation types: mentions, implies, contradicts, same_entity, related_to
- Source tracking: auto (from extraction), manual, consolidation
- Unique constraint prevents duplicate edges
- Indexes for fast graph traversal during retrieval

**Hancho Consolidation Pass (`scripts/hancho-consolidate.py`):**
- Scans recent memories for shared entities/terms (Jaccard > 0.15)
- Contradiction detection: finds same-topic facts with opposite polarity
- Inserts edges into `memory_relations`
- Derives hub insights (facts with 3+ connections = important)
- Runs as heartbeat job (every 1-4 hours recommended)

**Extraction Quality Logging (`extraction_log`):**
- Tracks: facts extracted, merged, inserted, relations discovered per run
- Records: input length, extraction time, model used, fallback usage
- Enables empirical tuning of extraction prompt over time

**Graph Traversal View (`memory_graph_1hop`):**
- Pre-computed MySQL view for fast 1-hop graph traversal during retrieval
- Joins memory_relations with memories for complete edge+node data
- Filtered to confidence >= 0.5 for quality

### Changed — Database Schema

- **`memories` table**: Added `source` (enum: manual/auto/consolidation/import), `verified_by_human` (boolean), `extraction_prompt` (text) columns
- **`memories` table**: Added `idx_mem_source` index for source-based queries
- **`user_context` table**: Extended `context_type` enum with `auto_extracted`, `graph_derived`, `extraction_quality`
- **New table**: `memory_relations` — k

RELEASE_POST_v5.md

# VectorClaw v5.0.0 — MyVector Self-Sufficiency

**VectorClaw v5.0.0 makes MyVector the single source of truth for all agent memory.** Auto-extraction and knowledge graph reasoning are now native MySQL systems, eliminating dependency on external tools (Mem0, Hancho).

## New in This Release

### Auto-Extraction Hook — Replaces Mem0

The auto-extraction hook uses a local LLM (qwen3.5:4b) to extract atomic facts from conversation text and insert them directly into MyVector:

- **Structured extraction:** core_fact, confidence, entities, linked_to, tags, memory_type, importance
- **Key mapping:** Normalizes LLM output ("fact" → "core_fact", invalid types → "semantic")
- **Auto-dedup:** Jaccard similarity check on insert — merges if >50% overlap
- **Source tracking:** All auto-extracted memories marked with `source='auto'`
- **Human verification:** `verified_by_human` flag for promoting accurate auto-facts
- **Fallback:** Regex-based extraction when LLM is unavailable
- **Quality logging:** Every extraction run logged to `extraction_log` for empirical tuning

```bash
python3 scripts/auto-extract.py "conversation text" --user <discord_id>
python3 scripts/auto-extract.py --file /path/to/text.txt --user <id> --dry-run
```

### Memory Relations + Knowledge Graph — Replaces Hancho

Native MySQL knowledge graph that replaces Hancho's external reasoning:

- **`memory_relations` table:** fact_id, related_fact_id, relation_type, confidence, source
- **Relation types:** mentions, implies, contradicts, same_entity, related_to
- **Auto-discovery:** Finds existing memories sharing entities during extraction
- **Consolidation pass:** Periodic scanning for contradictions and new edges
- **Hub insight derivation:** Identifies high-degree facts (3+ connections) as important
- **`memory_graph_1hop` view:** Pre-computed 1-hop graph traversal for retrieval

```bash
python3 scripts/hancho-consolidate.py --user <discord_id>
python3 scripts/hancho-consolidate.py --user <id> --hours 24 --dry-run
```

### Database Schema Changes

- **`memories` table:** Added `source`, `verified_by_human`, `extraction_prompt` columns
- **New table:** `memory_relations` — knowledge graph edges
- **New table:** `extraction_log` — extraction quality metrics
- **New view:** `memory_graph_1hop` — fast graph traversal
- **`user_context` enum:** Added `auto_extracted`, `graph_derived`, `extraction_quality`

### Extraction Quality Logging

Tracks auto-extraction quality for empirical prompt tuning:
- Facts extracted, merged, inserted, relations discovered per run
- Input length, extraction time (ms), model used, fallback usage
- Per-user and time-based indexes

## Upgrade

```bash
# 1. Back up your database
docker exec myvector-db mysqldump -u root -p<pass> jerith > backup_pre_v5.sql

# 2. Apply schema migration
docker exec -i myvector-db mysql -u root -p<pass> jerith < upgrade_v4_to_v5.sql

# 3. Run initial consolidation to build graph edges
python3 scripts/hancho-consolidate.py --all-users --dry-ru

Github ReposUpdated 20h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.