Xpersona

Crawler Summary

PocketMind answer-first brief

A privacy first personal knowledge agent built via crewai . PocketMind – Offline Personal Knowledge Agent PocketMind is a fully local, privacy-first personal knowledge agent. It lets you index your own documents (PDFs, Word files, Markdown, plain text) and chat with them — no internet connection required, no data sent to the cloud. Built on top of local SLMs via Ollama and a ChromaDB vector store, PocketMind retrieves relevant chunks from your files using semantic search and Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

PocketMind is best for crewai, multi-agent workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB REPOS, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Agent DossierGITHUB REPOSSafety: 66/100

PocketMind

A privacy first personal knowledge agent built via crewai . PocketMind – Offline Personal Knowledge Agent PocketMind is a fully local, privacy-first personal knowledge agent. It lets you index your own documents (PDFs, Word files, Markdown, plain text) and chat with them — no internet connection required, no data sent to the cloud. Built on top of local SLMs via Ollama and a ChromaDB vector store, PocketMind retrieves relevant chunks from your files using semantic search and

OpenClawself-declared

Public facts

4

Change events

1

Artifacts

0

Freshness

Oct 9, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Oct 9, 2026

Vendor

Spectre V 101

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

View Source

Setup snapshot

  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Spectre V 101

profilemedium
Observed Oct 9, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Oct 9, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB REPOS

Extracted files

0

Examples

3

Snippets

0

Languages

python

Executable Examples

text

pocketmind/
├── main.py                   # Entry point – launches the PySide6 GUI app
├── requirements.txt          # Python dependencies
├── config.py                 # Global config: paths, model names, chunk sizes, UI settings
│
├── core/                     # Document processing and vector search pipeline
│   ├── indexer.py            # Scans folders, extracts text, and chunks documents
│   ├── embedder.py           # Generates embeddings via a local Ollama model
│   ├── vector_store.py       # ChromaDB wrapper for adding, querying, and deleting vectors
│   └── document_parser.py    # Text extraction for PDF, DOCX, TXT, and MD files
│
├── agent/                    # Query reasoning and tool orchestration layer
│   ├── crew.py               # Wires together the retrieval and reasoning flow
│   ├── agents.py             # Agent role definitions for query handling
│   ├── tasks.py              # Task definitions for retrieval and answer generation
│   └── tools.py              # Custom tools: semantic retrieval, file opener, re-indexer
│
├── ui/                       # PySide6 desktop interface
│   ├── main_window.py        # Main application window
│   ├── chat_panel.py         # Chat input and response display widget
│   ├── source_panel.py       # Sidebar showing source document references
│   └── settings_dialog.py    # Folder selection and model configuration dialog
│
└── utils/
    └── helpers.py            # Shared utilities: text cleaning, path formatting

bash

# 1. Pull the required Ollama models
ollama pull qwen2.5:3b
ollama pull nomic-embed-text

# 2. Install Python dependencies
pip install -r requirements.txt

bash

python main.py

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

A privacy first personal knowledge agent built via crewai . PocketMind – Offline Personal Knowledge Agent PocketMind is a fully local, privacy-first personal knowledge agent. It lets you index your own documents (PDFs, Word files, Markdown, plain text) and chat with them — no internet connection required, no data sent to the cloud. Built on top of local SLMs via Ollama and a ChromaDB vector store, PocketMind retrieves relevant chunks from your files using semantic search and

Full README

PocketMind – Offline Personal Knowledge Agent

PocketMind is a fully local, privacy-first personal knowledge agent. It lets you index your own documents (PDFs, Word files, Markdown, plain text) and chat with them — no internet connection required, no data sent to the cloud. Built on top of local SLMs via Ollama and a ChromaDB vector store, PocketMind retrieves relevant chunks from your files using semantic search and answers questions grounded in your own knowledge base.

A key feature is semantic file search: instead of matching keywords, PocketMind understands the meaning and context behind your query and surfaces the most relevant passages from your documents — even when the exact words don't appear in the text.

Intended use cases:

  • Personal research assistant over a local document library
  • Semantic search across notes, reports, and reference documents
  • Offline document Q&A without uploading sensitive files to external services
  • Teams or individuals needing an air-gapped RAG (Retrieval-Augmented Generation) setup

Folder Structure

pocketmind/
├── main.py                   # Entry point – launches the PySide6 GUI app
├── requirements.txt          # Python dependencies
├── config.py                 # Global config: paths, model names, chunk sizes, UI settings
│
├── core/                     # Document processing and vector search pipeline
│   ├── indexer.py            # Scans folders, extracts text, and chunks documents
│   ├── embedder.py           # Generates embeddings via a local Ollama model
│   ├── vector_store.py       # ChromaDB wrapper for adding, querying, and deleting vectors
│   └── document_parser.py    # Text extraction for PDF, DOCX, TXT, and MD files
│
├── agent/                    # Query reasoning and tool orchestration layer
│   ├── crew.py               # Wires together the retrieval and reasoning flow
│   ├── agents.py             # Agent role definitions for query handling
│   ├── tasks.py              # Task definitions for retrieval and answer generation
│   └── tools.py              # Custom tools: semantic retrieval, file opener, re-indexer
│
├── ui/                       # PySide6 desktop interface
│   ├── main_window.py        # Main application window
│   ├── chat_panel.py         # Chat input and response display widget
│   ├── source_panel.py       # Sidebar showing source document references
│   └── settings_dialog.py    # Folder selection and model configuration dialog
│
└── utils/
    └── helpers.py            # Shared utilities: text cleaning, path formatting

Key Files at a Glance

| File | Purpose | |---|---| | config.py | Single source of truth for model names, directory paths, chunk sizes, and UI constants. Edit here to swap models or change storage locations. | | core/indexer.py | Walks a root directory, calls the parser, chunks text, and feeds chunks to the embedder and vector store. | | core/embedder.py | Talks to Ollama's embedding endpoint to turn text chunks into vectors. | | core/vector_store.py | Wraps ChromaDB — handles collection creation, upserts, similarity search, and deletions. | | core/document_parser.py | Extracts raw text from .pdf, .docx, .txt, and .md files. | | agent/crew.py | Wires together the retrieval and reasoning flow — takes a query, runs semantic search, and produces a grounded answer. | | agent/tools.py | Callable tools used during query handling: semantic retrieval from the vector store, file opener, and re-index trigger. | | ui/chat_panel.py | The main user-facing chat widget where queries are entered and answers are displayed. | | ui/source_panel.py | Shows which document chunks were used to generate each answer. | | ui/settings_dialog.py | Lets the user pick the folder to index and configure which Ollama models to use. |

Setup & Installation

Prerequisites

  • Ollama installed and running locally
  • Python 3.10+
# 1. Pull the required Ollama models
ollama pull qwen2.5:3b
ollama pull nomic-embed-text

# 2. Install Python dependencies
pip install -r requirements.txt

Running the App

python main.py

This launches the PySide6 desktop window. Use the Settings dialog to point PocketMind at a folder, trigger indexing, and then start asking questions in the chat panel.

Configuration

All tunable parameters live in config.py:

| Setting | Default | Description | |---|---|---| | LLM_MODEL | qwen3.5:4b | Ollama model used for answer generation. Swap for qwen2.5:7b on stronger hardware. | | EMBED_MODEL | nomic-embed-text | Ollama model used to generate embeddings. | | CHUNK_SIZE | 512 | Characters per document chunk. | | CHUNK_OVERLAP | 64 | Character overlap between consecutive chunks. | | TOP_K_RESULTS | 5 | Number of chunks retrieved per query. | | CHROMA_DIR | .pocketmind_data/chroma | Where ChromaDB persists its index on disk. |

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB REPOS

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
Github ReposUpdated 4h 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.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW
Agent hubMore from this sourceOpenClaw agents
Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T22:49:32.679Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "crewai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "multi-agent",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Spectre V 101",
    "href": "https://github.com/spectre-v-101/PocketMind",
    "sourceUrl": "https://github.com/spectre-v-101/PocketMind",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T18:18:11.634Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T18:18:11.634Z",
    "isPublic": true
  },
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-spectre-v-101-pocketmind/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to PocketMind and adjacent AI workflows.