Xpersona

Crawler Summary

agentic-rag-router-retriever answer-first brief

Agentic RAG with CrewAI a Router Agent classifies queries, a Retriever Agent answers via PDF search, web search, or direct response. Includes a pytest suite with mocked network calls and CI. Agentic RAG: Router-Retriever System $1 A two-agent $1 system that routes each incoming question to the correct information source before answering: - **Router Agent** — classifies a question as pdf, web, or direct. It never answers the question itself. - **Retriever Agent** — has both a PDF search tool and a web search tool available, and uses whichever one the Router's classification points to. The two tasks run ** Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

agentic-rag-router-retriever 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
Claim this agent
Agent DossierGITHUB REPOSSafety: 66/100

agentic-rag-router-retriever

Agentic RAG with CrewAI a Router Agent classifies queries, a Retriever Agent answers via PDF search, web search, or direct response. Includes a pytest suite with mocked network calls and CI. Agentic RAG: Router-Retriever System $1 A two-agent $1 system that routes each incoming question to the correct information source before answering: - **Router Agent** — classifies a question as pdf, web, or direct. It never answers the question itself. - **Retriever Agent** — has both a PDF search tool and a web search tool available, and uses whichever one the Router's classification points to. The two tasks run **

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

Deepighaj

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Unpublished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

Deepighaj

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

6

Snippets

0

Languages

python

Executable Examples

text

src/agentic_rag/
├── config.py        # env-based settings, validated at startup
├── llm.py            # Azure OpenAI LLM client factory
├── agents.py         # Router / Retriever agent definitions
├── tasks.py          # Task builder (sequential dependency wiring)
├── system.py         # RouterRetrieverSystem: reusable orchestration wrapper
└── tools/
    ├── web_search.py  # Tavily-backed web search tool
    └── pdf_search.py  # Native PDFSearchTool + LangChain/FAISS fallback
scripts/run_demo.py    # CLI entrypoint
tests/                 # pytest suite (no live API calls — network is mocked)
.github/workflows/ci.yml

bash

python3 -m venv venv
source venv/bin/activate        # Windows: venv\Scripts\activate
pip install -e ".[dev]"
cp .env.example .env             # then fill in your credentials

bash

python scripts/run_demo.py

bash

python scripts/run_demo.py --question "How many attention heads does the base Transformer model use?"

bash

python scripts/run_demo.py --fallback-pdf-tool

python

import asyncio
from agentic_rag.system import RouterRetrieverSystem

async def main():
    system = RouterRetrieverSystem.create()
    result = await system.ask_with_trace("What is scaled dot-product attention?")
    print(result.raw)

asyncio.run(main())

Docs & README

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

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

Agentic RAG with CrewAI a Router Agent classifies queries, a Retriever Agent answers via PDF search, web search, or direct response. Includes a pytest suite with mocked network calls and CI. Agentic RAG: Router-Retriever System $1 A two-agent $1 system that routes each incoming question to the correct information source before answering: - **Router Agent** — classifies a question as pdf, web, or direct. It never answers the question itself. - **Retriever Agent** — has both a PDF search tool and a web search tool available, and uses whichever one the Router's classification points to. The two tasks run **

Full README

Agentic RAG: Router-Retriever System

CI

A two-agent CrewAI system that routes each incoming question to the correct information source before answering:

  • Router Agent — classifies a question as pdf, web, or direct. It never answers the question itself.
  • Retriever Agent — has both a PDF search tool and a web search tool available, and uses whichever one the Router's classification points to.

The two tasks run sequentially: the Retriever's tool choice depends on the Router's output, so this is a dependency chain rather than two independent jobs.

Source document: the original Attention Is All You Need (Vaswani et al., 2017) paper, used as the static/PDF knowledge source. Anything the paper cannot know about (current events, post-2017 developments) is expected to route to live web search instead.

Architecture

Architecture diagram

Sequential Crew execution (Process.sequential) is used deliberately, not left as an incidental default — the Retriever task declares context=[task_route], which is what creates the dependency.

Project layout

src/agentic_rag/
├── config.py        # env-based settings, validated at startup
├── llm.py            # Azure OpenAI LLM client factory
├── agents.py         # Router / Retriever agent definitions
├── tasks.py          # Task builder (sequential dependency wiring)
├── system.py         # RouterRetrieverSystem: reusable orchestration wrapper
└── tools/
    ├── web_search.py  # Tavily-backed web search tool
    └── pdf_search.py  # Native PDFSearchTool + LangChain/FAISS fallback
scripts/run_demo.py    # CLI entrypoint
tests/                 # pytest suite (no live API calls — network is mocked)
.github/workflows/ci.yml

Setup

Prerequisites: an Azure OpenAI resource with chat + embedding deployments, and a free Tavily API key.

python3 -m venv venv
source venv/bin/activate        # Windows: venv\Scripts\activate
pip install -e ".[dev]"
cp .env.example .env             # then fill in your credentials

Usage

Run the built-in test set (PDF-routed, web-routed, and direct questions):

python scripts/run_demo.py

Ask a single question:

python scripts/run_demo.py --question "How many attention heads does the base Transformer model use?"

Use the LangChain/FAISS fallback PDF tool instead of CrewAI's native PDFSearchTool:

python scripts/run_demo.py --fallback-pdf-tool

Each run writes a structured reasoning trace (reasoning_trace_log.json) capturing the Router's classification, the Retriever's output, and the final answer — for interaction logging and reasoning traceability across agents.

Using it as a library

import asyncio
from agentic_rag.system import RouterRetrieverSystem

async def main():
    system = RouterRetrieverSystem.create()
    result = await system.ask_with_trace("What is scaled dot-product attention?")
    print(result.raw)

asyncio.run(main())

Testing

pytest -v

All tests mock network calls (Tavily, PDF download) and use injected environment variables — no live API keys or credits are needed to run the suite locally or in CI.

Notes on Azure OpenAI configuration

  • The LLM client uses the openai/ provider prefix with the Azure /openai/v1 endpoint and no api_version parameter — the combination confirmed to work with CrewAI's LiteLLM routing for *.services.ai.azure.com-style resources.
  • No temperature is set: gpt-5-mini is a reasoning-family model and only supports its default value.
  • load_dotenv(override=True) is used so re-running picks up .env changes without restarting the process.

License

MIT

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-deepighaj-agentic-rag-router-retriever/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/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 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 6mo 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 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-deepighaj-agentic-rag-router-retriever/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T17:00:09.475Z"
    }
  },
  "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": "Deepighaj",
    "href": "https://github.com/DeepighaJ/agentic-rag-router-retriever",
    "sourceUrl": "https://github.com/DeepighaJ/agentic-rag-router-retriever",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T12:48:05.455Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T12:48:05.455Z",
    "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-deepighaj-agentic-rag-router-retriever/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-deepighaj-agentic-rag-router-retriever/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 agentic-rag-router-retriever and adjacent AI workflows.