Xpersona

Crawler Summary

amazon-review-crew answer-first brief

Beginner CrewAI + MCP project for review sentiment analysis Amazon Review Sentiment Crew **Status:** 73.3% accuracy on a balanced 60-review test set — see $1. A beginner-friendly multi-agent project using **CrewAI** + **MCP** + **OpenRouter** to classify Amazon reviews as Positive, Negative, or Neutral. Architecture A 3-agent sequential pipeline: 1. **Fetcher** — pulls a review by ID via an MCP server tool. 2. **Analyst** — produces a structured breakdown (topic, praises, com Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

amazon-review-crew 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

amazon-review-crew

Beginner CrewAI + MCP project for review sentiment analysis Amazon Review Sentiment Crew **Status:** 73.3% accuracy on a balanced 60-review test set — see $1. A beginner-friendly multi-agent project using **CrewAI** + **MCP** + **OpenRouter** to classify Amazon reviews as Positive, Negative, or Neutral. Architecture A 3-agent sequential pipeline: 1. **Fetcher** — pulls a review by ID via an MCP server tool. 2. **Analyst** — produces a structured breakdown (topic, praises, com

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

Rajkaipa

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Unpublished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

Rajkaipa

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

2

Snippets

0

Languages

python

Executable Examples

powershell

python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txt
copy .env.example .env
# Edit .env and paste your OpenRouter key
python full_crew.py

bash

python prepare_data.py        # downloads 200 reviews from Hugging Face
python evaluate.py --limit 60 # runs balanced subset, prints metrics

Docs & README

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

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

Beginner CrewAI + MCP project for review sentiment analysis Amazon Review Sentiment Crew **Status:** 73.3% accuracy on a balanced 60-review test set — see $1. A beginner-friendly multi-agent project using **CrewAI** + **MCP** + **OpenRouter** to classify Amazon reviews as Positive, Negative, or Neutral. Architecture A 3-agent sequential pipeline: 1. **Fetcher** — pulls a review by ID via an MCP server tool. 2. **Analyst** — produces a structured breakdown (topic, praises, com

Full README

Amazon Review Sentiment Crew

Status: 73.3% accuracy on a balanced 60-review test set — see Evaluation.

A beginner-friendly multi-agent project using CrewAI + MCP + OpenRouter to classify Amazon reviews as Positive, Negative, or Neutral.

Architecture

A 3-agent sequential pipeline:

  1. Fetcher — pulls a review by ID via an MCP server tool.
  2. Analyst — produces a structured breakdown (topic, praises, complaints, tone, factual claims).
  3. Classifier — outputs the final sentiment label with a confidence score.

Project structure

  • data/reviews.json — 200 real Amazon reviews from Hugging Face (SetFit/amazon_reviews_multi_en)
  • data/labels.json — ground-truth ratings and sentiment labels for evaluation
  • prepare_data.py — one-time script to download and sample the dataset
  • review_server.py — MCP server exposing get_review and list_review_ids tools
  • crew_lib.py — shared crew-building logic (used by full_crew.py and evaluate.py)
  • fetcher.py — standalone Fetcher script (MCP-using)
  • full_crew.py — full 3-agent pipeline
  • evaluate.py — runs the crew against the dataset and reports accuracy / precision / recall
  • notebooks/01_analyst_agent.ipynb — Analyst in isolation
  • notebooks/02_classifier_agent.ipynb — Classifier in isolation

Setup

python -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install -r requirements.txt
copy .env.example .env
# Edit .env and paste your OpenRouter key
python full_crew.py

Tech

  • CrewAI for agent orchestration
  • Model Context Protocol (MCP) for the review-fetching tool
  • OpenRouter as the LLM gateway (currently openai/gpt-oss-20b:free)

Evaluation

The system was evaluated against a balanced subset of 60 real Amazon reviews drawn from SetFit/amazon_reviews_multi_en on Hugging Face — 20 each of NEGATIVE (1-2 star), NEUTRAL (3 star), and POSITIVE (4-5 star).

Results

| Metric | Baseline | After Prompt Iteration | |---|---:|---:| | Overall accuracy | 71.7% | 73.3% | | Parse failures | 0 | 0 | | POSITIVE — precision / recall | 0.93 / 0.70 | 0.89 / 0.80 | | NEGATIVE — precision / recall | 0.68 / 0.96 | 0.71 / 1.00 | | NEUTRAL — precision / recall | 0.43 / 0.23 | 0.25 / 0.08 | | Avg time per review | 59.6s | 31.8s |

What the iteration changed

The Classifier prompt was extended with explicit label definitions, a decision rule ("would the reviewer buy this again?"), and guidance to reserve NEGATIVE for clearly frustrated reviewers. This improved POSITIVE recall by 10 points and brought NEGATIVE recall to 100%, but pushed NEUTRAL detection in the wrong direction — a textbook case of prompt fragility where fixing one class shifts confusion elsewhere.

Known limitations

  • Label noise: Amazon's 1-5 star ratings don't perfectly track sentiment in the review text. Manual inspection of "wrong" NEUTRAL predictions shows many are defensible reads — reviewers giving 3 stars to text that reads as clearly negative.
  • NEUTRAL is genuinely hard: with the current data and model, the classifier collapses much of the NEUTRAL class into NEGATIVE. Further prompt-tuning on the same free-tier model is hitting diminishing returns.
  • Free-tier latency: ~32 seconds per review on gpt-oss-20b:free, with occasional rate-limit pauses. A paid frontier model (Gemini Flash / Claude Haiku / GPT-4o-mini) would likely close most of the NEUTRAL gap and run ~10× faster.

Reproducing the evaluation

python prepare_data.py        # downloads 200 reviews from Hugging Face
python evaluate.py --limit 60 # runs balanced subset, prints metrics

The full report (per-review predictions, justifications, timings) is saved to evaluation_report.json.

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-rajkaipa-amazon-review-crew/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/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 9h 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-rajkaipa-amazon-review-crew/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-10T04:39:11.821Z"
    }
  },
  "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": "Rajkaipa",
    "href": "https://github.com/Rajkaipa/amazon-review-crew",
    "sourceUrl": "https://github.com/Rajkaipa/amazon-review-crew",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T21:25:46.473Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T21:25:46.473Z",
    "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-rajkaipa-amazon-review-crew/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-rajkaipa-amazon-review-crew/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 amazon-review-crew and adjacent AI workflows.