Xpersona

Crawler Summary

crewai-agent-using-awsbedrock answer-first brief

CrewAI with Amazon Bedrock showcases an enterprise AI agent using a secure Action & Trust Layer. It combines multi-agent orchestration, MCP, Human-in-the-Loop approvals, safety guardrails, observability, and continuous evaluation to build secure, scalable, and production-ready AI applications on AWS. Prerequisites Create a .env file with below content for AWS and CrewAI configuration AWS Configuration AWS_ACCESS_KEY_ID=YOUR_ACCESS_KEY AWS_SECRET_ACCESS_KEY=YOUR_SECRET_KEY AWS_SESSION_TOKEN=YOUR_SESSION_TOKEN AWS_REGION=us-east-1 CrewAI Configuration CREWAI_TRACING_ENABLED=false Multi-Agent Chat — Architecture & Guide Files | File | Purpose | |---|---| | Crewai.py | Main entry point. Chat loop, router, guardrail w Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

crewai-agent-using-awsbedrock 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

crewai-agent-using-awsbedrock

CrewAI with Amazon Bedrock showcases an enterprise AI agent using a secure Action & Trust Layer. It combines multi-agent orchestration, MCP, Human-in-the-Loop approvals, safety guardrails, observability, and continuous evaluation to build secure, scalable, and production-ready AI applications on AWS. Prerequisites Create a .env file with below content for AWS and CrewAI configuration AWS Configuration AWS_ACCESS_KEY_ID=YOUR_ACCESS_KEY AWS_SECRET_ACCESS_KEY=YOUR_SECRET_KEY AWS_SESSION_TOKEN=YOUR_SESSION_TOKEN AWS_REGION=us-east-1 CrewAI Configuration CREWAI_TRACING_ENABLED=false Multi-Agent Chat — Architecture & Guide Files | File | Purpose | |---|---| | Crewai.py | Main entry point. Chat loop, router, guardrail w

OpenClawself-declared

Public facts

5

Change events

1

Artifacts

0

Freshness

Oct 9, 2026

Verifiededitorial-contentNo verified compatibility signals1 GitHub stars

Capability contract not published. No trust telemetry is available yet. 1 GitHub stars reported by the source. Last updated 10/9/2026.

1 GitHub starsTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Oct 9, 2026

Vendor

Anoopt123

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. 1 GitHub stars reported by the source. 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

Anoopt123

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

Protocol compatibility

OpenClaw

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

Adoption signal

1 GitHub stars

profilemedium
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

6

Snippets

0

Languages

python

Executable Examples

bash

pip install --upgrade crewai crewai-tools[mcp] litellm mcp \
    opentelemetry-sdk opentelemetry-exporter-otlp --break-system-packages
python3 Crewai.py

bash

export GITHUB_PERSONAL_ACCESS_TOKEN=ghp_xxx   # fine-grained PAT, read-only is enough

bash

python3 mcp_integration.py --chat                      # filesystem server (default)
python3 mcp_integration.py --chat --target github       # GitHub's official MCP server

text

mcp[github]> call search_repositories {"query": "org:anthropics"}
mcp[github]> call list_issues {"owner": "anthropics", "repo": "..."}

text

User input
   │
   ▼
[Rate limiter] ──blocked──► "try again in Ns"
   │ ok
   ▼
[Prompt-injection scan] ──flagged──► human approval gate ──reject──► skipped
   │ clean/approved
   ▼
[Secret redaction] ──found──► redact before it reaches the model or logs
   │
   ▼
[Router] ─┬─ math ─────────► Mathematical Analyst
          ├─ code ─────────► Software Analyst
          ├─ virt ─────────► human approval ─► Virtualization Engineer ─► human review of output
          ├─ web ──────────► Web Content Analyst (URL allowlist enforced)
          ├─ pipeline ─────► human approval ─► Coder → Build → Test → Run
          │                    (Build/Run stages: per-command approval, sandboxed exec)
          └─ general ──────► direct LLM call with chat history
   │
   ▼
[Output sanitization] ──► printed to user
   │
   ▼
[Tracing span + JSONL log entry] (agent_runs.jsonl, OpenTelemetry console/OTLP)

bash

python3 evals.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

CrewAI with Amazon Bedrock showcases an enterprise AI agent using a secure Action & Trust Layer. It combines multi-agent orchestration, MCP, Human-in-the-Loop approvals, safety guardrails, observability, and continuous evaluation to build secure, scalable, and production-ready AI applications on AWS. Prerequisites Create a .env file with below content for AWS and CrewAI configuration AWS Configuration AWS_ACCESS_KEY_ID=YOUR_ACCESS_KEY AWS_SECRET_ACCESS_KEY=YOUR_SECRET_KEY AWS_SESSION_TOKEN=YOUR_SESSION_TOKEN AWS_REGION=us-east-1 CrewAI Configuration CREWAI_TRACING_ENABLED=false Multi-Agent Chat — Architecture & Guide Files | File | Purpose | |---|---| | Crewai.py | Main entry point. Chat loop, router, guardrail w

Full README

Prerequisites

Create a .env file with below content for AWS and CrewAI configuration

AWS Configuration

AWS_ACCESS_KEY_ID=YOUR_ACCESS_KEY AWS_SECRET_ACCESS_KEY=YOUR_SECRET_KEY AWS_SESSION_TOKEN=YOUR_SESSION_TOKEN AWS_REGION=us-east-1

CrewAI Configuration

CREWAI_TRACING_ENABLED=false

Multi-Agent Chat — Architecture & Guide

Files

| File | Purpose | |---|---| | Crewai.py | Main entry point. Chat loop, router, guardrail wiring. Run this. | | guardrails.py | OWASP LLM Top-10 controls: injection detection, secret redaction, URL allowlist, output sanitization, rate limiting | | human_loop.py | Console approval gate (request_human_approval) | | observability.py | OpenTelemetry tracing + JSONL structured logs (agent_runs.jsonl) | | mcp_integration.py | Connects MCP server tools to an agent. Ships two example targets (filesystem, github) and an interactive --chat --target <name> REPL | | shell_tools.py | Sandboxed shell/file tools for the dev pipeline, gated per-call | | dev_pipeline.py | Coder → Build → Test → Run specialist pipeline | | evals.py | Router-accuracy suite (fast) + agent-quality suite (real LLM calls) |

Setup

pip install --upgrade crewai crewai-tools[mcp] litellm mcp \
    opentelemetry-sdk opentelemetry-exporter-otlp --break-system-packages
python3 Crewai.py

AWS credentials must be available in the environment (AWS_REGION, etc.) since the LLM is routed through Bedrock.

To also demo the GitHub MCP target, set:

export GITHUB_PERSONAL_ACCESS_TOKEN=ghp_xxx   # fine-grained PAT, read-only is enough

MCP live chat (interactive demo)

python3 mcp_integration.py --chat                      # filesystem server (default)
python3 mcp_integration.py --chat --target github       # GitHub's official MCP server

Both targets share one REPL and one connection-handling code path — only the server_params passed in changes. The filesystem target has named shortcuts (write, read, list, tree, ...); every target — including github — also supports a generic passthrough that needs no per-server code:

mcp[github]> call search_repositories {"query": "org:anthropics"}
mcp[github]> call list_issues {"owner": "anthropics", "repo": "..."}

tools (in either target) prints the exact tool manifest the connected server advertised, so you can call anything it exposes without it being hardcoded here.

Architecture at a glance

User input
   │
   ▼
[Rate limiter] ──blocked──► "try again in Ns"
   │ ok
   ▼
[Prompt-injection scan] ──flagged──► human approval gate ──reject──► skipped
   │ clean/approved
   ▼
[Secret redaction] ──found──► redact before it reaches the model or logs
   │
   ▼
[Router] ─┬─ math ─────────► Mathematical Analyst
          ├─ code ─────────► Software Analyst
          ├─ virt ─────────► human approval ─► Virtualization Engineer ─► human review of output
          ├─ web ──────────► Web Content Analyst (URL allowlist enforced)
          ├─ pipeline ─────► human approval ─► Coder → Build → Test → Run
          │                    (Build/Run stages: per-command approval, sandboxed exec)
          └─ general ──────► direct LLM call with chat history
   │
   ▼
[Output sanitization] ──► printed to user
   │
   ▼
[Tracing span + JSONL log entry] (agent_runs.jsonl, OpenTelemetry console/OTLP)

OWASP LLM Top-10 mapping

| Risk | Control | Where | |---|---|---| | LLM01 Prompt Injection | Regex heuristic screen on every input; human approval to proceed if flagged | guardrails.detect_prompt_injection, Crewai.py | | LLM02 Insecure Output Handling | Outputs are never auto-executed; shell-looking output gets a review banner | guardrails.sanitize_output | | LLM04 Model Denial of Service | Sliding-window rate limiter (20 calls/60s) | guardrails.RateLimiter | | LLM06 Sensitive Information Disclosure | Redacts AWS keys, generic API keys/tokens, private key blocks, emails before they hit the model or logs | guardrails.redact_secrets | | LLM08 Excessive Agency | Human approval required before: virt/code-route execution, pipeline run, and every individual shell command in the dev pipeline | human_loop.py, gates in Crewai.py and shell_tools.py | | LLM10 (SSRF-adjacent) | URL allowlist blocks localhost / private IP ranges / cloud metadata endpoint | guardrails.is_allowed_url |

Note: these are heuristic, defense-in-depth controls suitable for a demo/prototype. Production hardening would add a real moderation classifier for LLM01, a non-blocking approval queue instead of console input(), and container-level isolation (not just subprocess sandboxing) for the shell tool. Any MCP target added here — the github target included — is wired in through the same mcp_tools() context manager as the rest of the app, so a live write-style GitHub action would still need the same human-approval pattern before this app would trust it.

Observability

  • Every turn gets one OpenTelemetry span (turn.<route>) with attributes route, agent, turn_id, latency_ms.
  • Every turn also appends one line to agent_runs.jsonl: timestamp, route, agent, query preview, output preview, flags (prompt_injection, redacted secret types), latency, and error if any.
  • To watch live: tail -f agent_runs.jsonl in a second terminal while demoing.
  • Swap ConsoleSpanExporter for OTLPSpanExporter in observability.py to ship to Langfuse/Datadog/Jaeger — one line change, everything else stays the same.

Evals

python3 evals.py
  • Router suite: 10 fixed cases checking route_query() picks the right specialist, no LLM calls, instant, safe to run on every commit.
  • Quality suite (opt-in, real LLM calls): checks actual agent output against simple rubrics (contains code block, correct math result, mentions qemu-img). Both suites log results to eval_results.jsonl for trend tracking.

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-anoopt123-crewai-agent-using-awsbedrock/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/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 2h 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-anoopt123-crewai-agent-using-awsbedrock/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T20:56:54.700Z"
    }
  },
  "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": "Anoopt123",
    "href": "https://github.com/anoopt123/crewai-agent-using-awsbedrock",
    "sourceUrl": "https://github.com/anoopt123/crewai-agent-using-awsbedrock",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T16:16:45.676Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T16:16:45.676Z",
    "isPublic": true
  },
  {
    "factKey": "traction",
    "category": "adoption",
    "label": "Adoption signal",
    "value": "1 GitHub stars",
    "href": "https://github.com/anoopt123/crewai-agent-using-awsbedrock",
    "sourceUrl": "https://github.com/anoopt123/crewai-agent-using-awsbedrock",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T16:16:45.676Z",
    "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-anoopt123-crewai-agent-using-awsbedrock/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-anoopt123-crewai-agent-using-awsbedrock/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 crewai-agent-using-awsbedrock and adjacent AI workflows.