Xpersona

Crawler Summary

discovery-agent answer-first brief

Multi-agent CrewAI pipeline that turns a sales discovery call transcript into a client proposal PDF and an engineering spec, with RAG-grounded context and a hybrid local/cloud architecture Discovery Agent **The problem:** after a sales discovery call, turning a raw transcript into a client-ready proposal and an internal engineering spec is manual, slow, and inconsistent between deals. **The solution:** Discovery Agent listens to (or ingests) a discovery call, then runs a multi-agent CrewAI pipeline that produces a polished client_proposal.pdf and a structured engineering_spec.md — with zero manual draf Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

discovery-agent 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

discovery-agent

Multi-agent CrewAI pipeline that turns a sales discovery call transcript into a client proposal PDF and an engineering spec, with RAG-grounded context and a hybrid local/cloud architecture Discovery Agent **The problem:** after a sales discovery call, turning a raw transcript into a client-ready proposal and an internal engineering spec is manual, slow, and inconsistent between deals. **The solution:** Discovery Agent listens to (or ingests) a discovery call, then runs a multi-agent CrewAI pipeline that produces a polished client_proposal.pdf and a structured engineering_spec.md — with zero manual draf

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

Thaynabarreiro

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Unpublished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

Thaynabarreiro

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

bash

python3.11 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env

bash

brew install switchaudio-osx

bash

python main.py

bash

./scripts/run_local_worker.sh

bash

./scripts/run_n8n.sh

text

n8n/workflows/discovery_agent_hybrid_workflow.json

Docs & README

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

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

Multi-agent CrewAI pipeline that turns a sales discovery call transcript into a client proposal PDF and an engineering spec, with RAG-grounded context and a hybrid local/cloud architecture Discovery Agent **The problem:** after a sales discovery call, turning a raw transcript into a client-ready proposal and an internal engineering spec is manual, slow, and inconsistent between deals. **The solution:** Discovery Agent listens to (or ingests) a discovery call, then runs a multi-agent CrewAI pipeline that produces a polished client_proposal.pdf and a structured engineering_spec.md — with zero manual draf

Full README

Discovery Agent

The problem: after a sales discovery call, turning a raw transcript into a client-ready proposal and an internal engineering spec is manual, slow, and inconsistent between deals.

The solution: Discovery Agent listens to (or ingests) a discovery call, then runs a multi-agent CrewAI pipeline that produces a polished client_proposal.pdf and a structured engineering_spec.md — with zero manual drafting.

Architecture

The project follows a WAT (Workflows / Agents / Tools) pattern:

  • Workflows — SOPs in _agent/workflows/ define when and in what order things happen
  • Agents — CrewAI-backed coordination in _agent/agents/ define who decides what
  • Tools — deterministic Python scripts in _agent/tools/ define how work actually gets done (RAG lookup, PDF rendering, transcription, etc.)

It runs as a hybrid local/cloud system: live audio capture and transcription happen on a local macOS worker (for latency and privacy), while orchestration can run locally or be deployed to CrewAI AMP for production use.

Hybrid Discovery Agent Architecture

Discovery Agent — Hybrid Workflow, Agents, Tools, and Outputs

Editable sources: docs/hybrid_discovery_agent_architecture.drawio and docs/clear_hybrid_process_flow.drawio (open at app.diagrams.net).

Key design decisions:

  • Deterministic-first, AI-enhanced: the pipeline runs on plain Python by default so it's testable without any API key configured; CrewAI orchestration is layered on top and degrades gracefully if a model/provider call fails
  • RAG-grounded output: a local knowledge base (ChromaDB) is used so generated proposals/specs reference real past case patterns instead of hallucinating context
  • Local-first audio, cloud-optional orchestration: keeps sensitive call audio on-device while still allowing the agent crew to run in CrewAI AMP

Setup

python3.11 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env

Fill .env with your API keys. For live call capture on macOS, install:

brew install switchaudio-osx

Install BlackHole 2ch separately and make sure it appears as an audio input device.

Run

python main.py

Hybrid Local Automation

Start the local worker:

./scripts/run_local_worker.sh

Start n8n with Docker/Colima:

./scripts/run_n8n.sh

Import this workflow in n8n:

n8n/workflows/discovery_agent_hybrid_workflow.json

Create the macOS Dock launcher:

./scripts/create_dock_launcher.sh
open "$HOME/Applications/Discovery Agent Launcher.app"

Note: with Colima, Docker containers may not be able to call a macOS host service on localhost:8765 without extra networking/tunnel setup. The local worker endpoint itself is functional at http://localhost:8765. For a fully reliable hybrid setup, run n8n on the host machine, use n8n Cloud with a tunnel to the worker, or expose the worker through a local tunnel.

The default pipeline uses deterministic local Python classes so you can test the project before every API is configured. _agent/agents/crew.py provides the CrewAI orchestration layer for production-style coordination with the configured model.

CrewAI runs when ENABLE_CREWAI=true is present in .env. It runs after a transcript is available and before PDF/Markdown generation. If CrewAI fails because of a dependency, model name, or provider issue, the deterministic pipeline continues and prints a warning.

CrewAI AMP / Studio Deployment

This project includes pyproject.toml and _agent/crew_entrypoint.py so CrewAI AMP can detect and run it as a deployable crew.

Local login and deploy flow:

source .venv/bin/activate
crewai login
crewai deploy create
crewai deploy status

Required environment variables for AMP:

ANTHROPIC_API_KEY=...
OPENAI_API_KEY=...
CHROMA_PERSIST_DIR=.chromadb
DEFAULT_MODEL=anthropic/claude-sonnet-4-6
GITHUB_REPO_NAME=discovery-agent
ENABLE_CREWAI=true
ENABLE_GITHUB_UPLOAD=false

For AMP deployment, keep ENABLE_GITHUB_UPLOAD=false unless the deployed runtime should push generated artifacts back to GitHub.

pyproject.toml intentionally keeps only the lightweight CrewAI deployment dependencies. requirements.txt keeps the full local app stack for live audio, RAG, PDF generation, and GitHub upload.

What You Need To Provide

  • ANTHROPIC_API_KEY for Claude generation.
  • OPENAI_API_KEY for Whisper transcription in live mode.
  • Any client system credentials required by the generated engineering spec.
  • GitHub CLI authentication if you want automatic repository creation and push:
gh auth login

Notes

  • output/ and .chromadb/ are intentionally ignored by git.
  • If knowledge_base/ is empty, RAG search will warn and the agents will continue without case references.

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-thaynabarreiro-discovery-agent/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/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-thaynabarreiro-discovery-agent/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T10:44:55.611Z"
    }
  },
  "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": "Thaynabarreiro",
    "href": "https://github.com/Thaynabarreiro/discovery-agent",
    "sourceUrl": "https://github.com/Thaynabarreiro/discovery-agent",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T04:28:05.908Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T04:28:05.908Z",
    "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-thaynabarreiro-discovery-agent/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-thaynabarreiro-discovery-agent/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 discovery-agent and adjacent AI workflows.