{"id":"a5e1f99e-ec45-4256-89ca-ca9ee8116365","entityType":"agent","slug":"crewai-maithreshvaddi-27-resume-crew","name":"Resume_Crew","canonicalUrl":"https://www.xpersona.co/agent/crewai-maithreshvaddi-27-resume-crew","canonicalPath":"/agent/crewai-maithreshvaddi-27-resume-crew","generatedAt":"2026-10-09T23:16:00.589Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T13:52:36.413Z","emptyReason":null},"description":"Local-first multi-agent career intelligence system built with Python and CrewAI for evidence-based resume analysis, job matching, skill-gap detection, resume tailoring, and interview preparation. Resume_Crew $1 $1 $1 $1 **Resume_Crew** compares a resume against a job description and produces an evidence-focused match report — no invented skills, no guessed experience. It runs entirely on your machine by default (via $1), with an optional cloud fallback to Google Gemini. It ships two ways to use it: - **CLI** (main.py) — scriptable, good for batch/automation work - **Gradio web UI** (app.py) — point-and-click,","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.","installCommand":null,"sourceUrl":"https://github.com/MaithreshVaddi-27/Resume_Crew","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/MaithreshVaddi-27/Resume_Crew","kind":"source"}],"safetyScore":66,"overallRank":23,"popularityScore":0,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Local-first multi-agent career intelligence system built with Python and CrewAI for evidence-based resume analysis, job matching, skill-gap detection, resume ta"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T13:52:36.413Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"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"}},"adoption":{"evidence":{"source":"no-adoption-signals","verified":false,"confidence":"low","updatedAt":"2026-10-09T13:52:36.413Z","emptyReason":"No source adoption metrics were available."},"stars":0,"forks":0,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":null},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-10-09T13:52:36.402Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T13:52:36.413Z","lastCrawledAt":"2026-10-09T13:52:36.402Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-16T13:52:36.402Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-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":"2026-10-09T23:16:00.588Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-maithreshvaddi-27-resume-crew/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-10-09T13:52:36.413Z","emptyReason":null},"readme":"# Resume_Crew\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n[![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-blue.svg)](https://www.python.org/downloads/)\n[![UI: Gradio](https://img.shields.io/badge/UI-Gradio-orange.svg)](https://www.gradio.app/)\n[![LLM: Ollama%20%7C%20Gemini](https://img.shields.io/badge/LLM-Ollama%20%7C%20Gemini-8A2BE2.svg)](#requirements)\n\n**Resume_Crew** compares a resume against a job description and produces an evidence-focused match report — no invented skills, no guessed experience. It runs entirely on your machine by default (via [Ollama](https://ollama.com)), with an optional cloud fallback to Google Gemini.\n\nIt ships two ways to use it:\n\n- **CLI** (`main.py`) — scriptable, good for batch/automation work\n- **Gradio web UI** (`app.py`) — point-and-click, with optional public sharing via ngrok\n\nSupports **PDF, DOCX, TXT, and Markdown** inputs.\n\n---\n\n## Table of contents\n\n- [What it produces](#what-it-produces)\n- [Requirements](#requirements)\n- [Getting an API key (optional — only for Gemini)](#getting-an-api-key-optional--only-for-gemini)\n- [Installation](#installation)\n  - [macOS](#macos)\n  - [Windows](#windows-powershell)\n  - [Linux](#linux)\n- [Configuration](#configuration)\n- [Usage — CLI](#usage--command-line-cli)\n- [Usage — Web UI](#usage--web-ui-gradio)\n- [Project layout](#project-layout)\n- [Tracing and telemetry](#tracing-and-telemetry)\n- [Privacy and data retention](#privacy-and-data-retention)\n- [Troubleshooting](#troubleshooting)\n- [Development and verification](#development-and-verification)\n- [Disclaimer](#disclaimer)\n- [License](#license)\n\n---\n\n## What it produces\n\nEach analysis creates a new report folder containing:\n\n| File | Description |\n|---|---|\n| `match_report.md` | Combined report (all sections below, in one file) |\n| `match_report.pdf` | PDF version — default download in the Gradio UI (Full Report tab) |\n| `match_report.docx` | Word version — secondary download alongside the PDF |\n| `resume_profile.md` | Factual candidate profile |\n| `job_description_profile.md` | Job requirements profile |\n| `skills_gap_analysis.md` | Strengths, evidence gaps, and interview risks |\n| `tailored_resume_bullets.md` | Evidence-based bullet suggestions |\n| `interview_preparation.md` | Role-specific questions and honest answer guidance |\n| `run_meta.json` | Small sidecar (candidate, job title, score, timestamp) that powers the History tab |\n\nThe deterministic keyword score is a **whole-term overlap signal**, not an ATS simulation or a hiring recommendation.\n\n## Requirements\n\n- Python 3.10 or newer\n- One LLM provider for full analysis:\n  - **Ollama** (recommended) — runs locally, keeps data on your machine, no API key needed\n  - **Gemini** (optional) — cloud fallback; needs an API key and sends document text to Google\n\nHardware diagnostics (`--check-hardware`) work with no LLM provider configured. Resume ranking uses the LLM too, so it needs a working provider just like full analysis does.\n\n## Getting an API key (optional — only for Gemini)\n\nYou only need this if you want to use `--provider gemini`, or as a fallback when Ollama isn't running. If you're staying fully local with Ollama, skip this section.\n\n1. Go to **[Google AI Studio → API Keys](https://aistudio.google.com/app/apikey)** and sign in with a Google account.\n2. Click **Create API key**, and select or create a Google Cloud project when prompted (no billing account required for the free tier).\n3. Copy the key — it starts with `AIza...`.\n4. Paste it into your `.env` file as `GEMINI_API_KEY=your_key_here` (see [Configuration](#configuration) below).\n\nTreat this key like a password: never commit it to Git, share it in chat, or paste it into client-side code. `.env` is already ignored by Git in this project.\n\n> Optional: if you also want a **live public URL** for the Gradio app (via ngrok), grab a free authtoken at [dashboard.ngrok.com](https://dashboard.ngrok.com/get-started/your-authtoken) — see [Live public URL via ngrok](#live-public-url-via-ngrok).\n\n## Installation\n\nClone the repository first:\n\n```bash\ngit clone https://github.com/MaithreshVaddi-27/Resume_Crew\ncd Resume_Crew\n```\n\nThen follow the instructions for your OS below.\n\n### macOS\n\n1. Install Python 3.10+ from [python.org](https://www.python.org/downloads/) or via Homebrew (`brew install python`).\n2. In Terminal, from the project folder:\n\n   ```bash\n   python3 -m venv venv\n   source venv/bin/activate\n   python -m pip install --upgrade pip\n   pip install -r requirements.txt\n   ```\n\n3. For local (no API key) analysis, install [Ollama](https://ollama.com/download), open it once, then run:\n\n   ```bash\n   ollama pull gemma3:4b\n   ```\n\nApple Silicon (M1/M2/M3/M4) is detected automatically. Check the recommended profile with:\n\n```bash\npython main.py --check-hardware\n```\n\n### Windows (PowerShell)\n\n1. Install Python 3.10+ from [python.org](https://www.python.org/downloads/) and select **Add Python to PATH** during setup.\n2. Open PowerShell in the project folder:\n\n   ```powershell\n   py -m venv venv\n   .\\venv\\Scripts\\Activate.ps1\n   py -m pip install --upgrade pip\n   pip install -r requirements.txt\n   ```\n\n   If PowerShell blocks activation with an execution-policy error, run this once in the same window, then activate again:\n\n   ```powershell\n   Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass\n   ```\n\n3. For local (no API key) analysis, install [Ollama for Windows](https://ollama.com/download/windows), then run:\n\n   ```powershell\n   ollama pull gemma3:4b\n   ```\n\nCheck hardware detection with:\n\n```powershell\npy main.py --check-hardware\n```\n\n### Linux\n\nOn Debian/Ubuntu, install Python tooling first if you don't already have it:\n\n```bash\nsudo apt update\nsudo apt install python3 python3-venv python3-pip\n```\n\nThen install the project:\n\n```bash\npython3 -m venv venv\nsource venv/bin/activate\npython -m pip install --upgrade pip\npip install -r requirements.txt\n```\n\nFor local (no API key) analysis, install [Ollama](https://ollama.com/download/linux) using its official install script, then pull a model:\n\n```bash\nollama pull gemma3:4b\n```\n\nFor NVIDIA systems, confirm the driver and `nvidia-smi` work **before** starting Ollama, so GPU acceleration is detected correctly. Check with:\n\n```bash\npython main.py --check-hardware\n```\n\n## Configuration\n\nCopy the template file to create your local config:\n\n```bash\n# macOS / Linux\ncp .env.example .env\n```\n\n```powershell\n# Windows PowerShell\nCopy-Item .env.example .env\n```\n\nThen open `.env` and set the values you need. The most relevant settings:\n\n```env\nRESUME_PATH=./samples/Resumes/sample_resume.pdf\nJD_PATH=./samples/Job_description/sample_job_description.pdf\n\n# auto = use local Ollama when reachable, then fall back to Gemini.\nLLM_PROVIDER=auto\n\nOLLAMA_BASE_URL=http://localhost:11434\nOLLAMA_MODEL=gemma3:4b\nOLLAMA_TIMEOUT=3.0        # Raise this on slow machines or WSL2\nOLLAMA_PROFILE=auto       # auto detects CUDA > MPS > CPU\n\n# Only needed for --provider gemini, or as the auto fallback.\n# Get this at https://aistudio.google.com/app/apikey — see \"Getting an API key\" above.\nGEMINI_API_KEY=\nGEMINI_MODEL=gemini/gemini-3.1-flash-lite\n\nCREWAI_TRACING_ENABLED=false\nCREWAI_DISABLE_TELEMETRY=true\nCREWAI_DISABLE_TRACKING=true\nOTEL_SDK_DISABLED=true\n\nGRADIO_PORT=7860\nGRADIO_SHARE=false        # true = use Gradio's built-in tunnel instead of ngrok\n\n# Optional: for a live public URL. Get a free token at\n# https://dashboard.ngrok.com/get-started/your-authtoken\nNGROK_AUTHTOKEN=your_ngrok_authtoken\n\n# Recommended if you use NGROK_AUTHTOKEN or GRADIO_SHARE — a public URL has\n# no login by default, so set both to require a username/password.\nGRADIO_AUTH_USER=user\nGRADIO_AUTH_PASS=user@123\n```\n\n`.env` is listed in `.gitignore` — never commit it, since it can hold API keys.\n\n## Usage — Command Line (CLI)\n\nActivate the virtual environment for your OS (see [Installation](#installation)) before each session, then run commands from the project root.\n\n### Full local analysis (Ollama, no API key)\n\n**macOS / Linux:**\n\n```bash\npython main.py \\\n  --resume samples/Resumes/sample_resume.pdf \\\n  --job-description samples/Job_description/sample_job_description.pdf \\\n  --provider ollama\n```\n\n**Windows PowerShell:**\n\n```powershell\npython main.py `\n  --resume .\\samples\\Resumes\\sample_resume.pdf `\n  --job-description .\\samples\\Job_description\\sample_job_description.pdf `\n  --provider ollama\n```\n\n### Gemini analysis (needs an API key)\n\nAfter setting `GEMINI_API_KEY` in `.env` (see [Getting an API key](#getting-an-api-key-optional--only-for-gemini)):\n\n```bash\npython main.py --resume ./my_resume.pdf --job-description ./job.docx --provider gemini\n```\n\n### Rank several resume versions with the LLM\n\n```bash\npython main.py --rank-resumes ./resume_versions --job-description ./job.docx --provider ollama\n```\n\nEach resume in the folder gets its own LLM scoring call (0–100 with a one-line note), so ranking a large folder takes proportionally longer and, on `--provider gemini`, costs one API call per file.\n\n### Hardware and model diagnostics\n\n```bash\npython main.py --check-hardware\npython main.py --check-hardware --ollama-profile mps\npython main.py --version\n```\n\n## Usage — Web UI (Gradio)\n\nStart the browser interface from the project root (same command on every OS, once your virtual environment is active):\n\n```bash\npython app.py\n```\n\nThe UI opens automatically at `http://localhost:7860` and includes:\n\n- **Analyze Resume** — upload resume + JD, pick provider, watch step-by-step progress, view results across 8 sub-tabs (Score, Resume Profile, Job Profile, Gap Analysis, Resume Bullets, Interview Prep, Resume Highlights, Full Report). Includes a **Cancel** button to stop a run between pipeline steps. The Full Report tab offers **PDF (default)** and **Word (.docx)** downloads.\n- **Build Resume** — draft a resume tailored to a target job description, using *only* facts from an uploaded resume and/or freeform notes you provide. Nothing is invented: no employer, date, skill, or number appears unless it's in your source material.\n- **Rank Resumes** — score a local folder of resumes against a JD, one lightweight LLM call per resume.\n- **Batch Analyze** — run the *full* 4-step analysis for every resume in a folder against one JD, saving a separate report per resume.\n- **Compare JDs** — score one resume against several job descriptions at once, to see which posting fits best.\n- **History** — browse past saved runs, reload any report back into the tabs, and view a score-trend chart across runs.\n- **Hardware** — detect GPU, RAM, and Ollama status from the browser.\n\n### Live public URL via ngrok\n\n1. Get a free authtoken at [dashboard.ngrok.com](https://dashboard.ngrok.com/get-started/your-authtoken).\n2. Add it to `.env`:\n\n   ```env\n   NGROK_AUTHTOKEN=your_token_here\n   ```\n\n3. Run `python app.py`. A live public URL prints in the terminal at startup:\n\n   ```text\n   ============================================================\n     🌐  Live ngrok URL: https://xxxx-xx-xx.ngrok-free.app\n   ============================================================\n   ```\n\nShare this URL with anyone — no port-forwarding or VPN required.\n\n**A public URL has no login by default** — anyone with the link can upload documents and run analysis. Set both of these in `.env` to require a username/password before the app loads:\n\n```env\nGRADIO_AUTH_USER=someuser\nGRADIO_AUTH_PASS=some-strong-password\n```\n\n### Port and share settings\n\n```env\nGRADIO_PORT=7860        # Change the local port\nGRADIO_SHARE=true        # Use Gradio's built-in tunnel instead of ngrok\n```\n\n## Project layout\n\n```text\nResume_Crew/\n├── src/resume_crew/          # Application package\n├── tests/                    # Automated tests\n├── samples/                  # Versioned demonstration documents\n│   ├── Resumes/               #   sample_resume.pdf\n│   └── Job_description/       #   sample_job_description.pdf\n├── output/                   # Created locally for generated reports (ignored)\n├── app.py                    # Gradio web UI entry point\n├── main.py                   # CLI entry point (source-checkout)\n├── .env.example               # Safe configuration template\n└── pyproject.toml             # Package and dependency metadata\n```\n\n## Tracing and telemetry\n\nCrewAI execution traces and telemetry are disabled by default, both in `.env.example` and in the application itself. The project passes `tracing=False` for every CrewAI task and disables CrewAI/OpenTelemetry telemetry. This keeps candidate data and execution metadata out of CrewAI's tracing services.\n\n## Privacy and data retention\n\n- With `--provider ollama`, resume and job text stay on the local machine, subject to your local Ollama installation.\n- With `--provider gemini`, source text is sent to Google — use it only when that's acceptable.\n- Reports are created in `output/` and can contain personal information. That folder is ignored by Git.\n- The current version does not persist analysis history outside your own `output/` folder.\n\n## Troubleshooting\n\n| Problem | Resolution |\n|---|---|\n| `ModuleNotFoundError` on startup | Activate the project virtual environment and run `pip install -r requirements.txt`. |\n| `Ollama is not reachable` | Start the Ollama application/service, run `ollama pull gemma3:4b`, then retry. Raise `OLLAMA_TIMEOUT` in `.env` if on a slow machine. |\n| Gemini fallback error | Add a valid `GEMINI_API_KEY` to `.env` (see [Getting an API key](#getting-an-api-key-optional--only-for-gemini)), or use `--provider ollama`. |\n| PDF has no extractable text | The PDF is likely scanned. Run OCR first, then supply the OCR result. |\n| Unsupported file type | Convert the file to PDF, DOCX, TXT, or Markdown. |\n| Input exceeds character limit | Split the document or remove irrelevant appendices. |\n| PowerShell will not activate venv | Use the temporary execution-policy command in the [Windows installation](#windows-powershell) section. |\n| Slow local analysis | Run `python main.py --check-hardware`; reduce Ollama context or use a smaller local model. |\n| ngrok tunnel not created | Ensure `pyngrok` is installed (`pip install pyngrok`) and `NGROK_AUTHTOKEN` is set in `.env`. |\n| Gradio port already in use | Set `GRADIO_PORT=7861` (or any free port) in `.env`. |\n| `python app.py` fails with `DLL load failed... Application Control policy has blocked this file` (Windows) | A managed/corporate Windows security policy (WDAC/AppLocker) is blocking a native DLL — usually pandas, pulled in by Gradio — often because the project folder still has the \"downloaded from the internet\" flag. In PowerShell from the project root: `Get-ChildItem -Path .\\venv -Recurse \\| Unblock-File`, then retry. If it still fails, move the project out of `Downloads` to a plain local folder (e.g. `C:\\Resume_Crew`), delete `venv`, and reinstall. On a company-managed device the policy may be enforced centrally — ask IT to allow Python/pandas, or run the project inside WSL2 instead. |\n\n## Development and verification\n\n```bash\npython -m pytest -q\npython -m py_compile main.py app.py src/resume_crew/*.py\npython -m pip check\n```\n\nThe test suite covers document validation, keyword scoring (including single-char tokens like `R`), report structure, CRLF handling, output safety, timestamp format, and hardware-setting validation. A live LLM run requires an available Ollama server or valid Gemini credentials.\n\n## Disclaimer\n\nThis project is intended for educational, research, and learning purposes. The keyword-match score and LLM-generated output are a starting point for your own judgment — not an ATS simulation, hiring recommendation, or guarantee of job-search outcomes. Always review generated content before using it.\n\n## License\n\nThis project is licensed under the MIT License — see [LICENSE](https://github.com/MaithreshVaddi-27/Resume_Crew/blob/main/LICENSE) for the full text.\n","readmeExcerpt":"Resume_Crew $1 $1 $1 $1 **Resume_Crew** compares a resume against a job description and produces an evidence-focused match report — no invented skills, no guessed experience. It runs entirely on your machine by default (via $1), with an optional cloud fallback to Google Gemini. It ships two ways to use it: - **CLI** (main.py) — scriptable, good for batch/automation work - **Gradio web UI** (app.py) — point-and-click,","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"git clone https://github.com/MaithreshVaddi-27/Resume_Crew\ncd Resume_Crew"},{"language":"bash","snippet":"python3 -m venv venv\n   source venv/bin/activate\n   python -m pip install --upgrade pip\n   pip install -r requirements.txt"},{"language":"bash","snippet":"ollama pull gemma3:4b"},{"language":"bash","snippet":"python main.py --check-hardware"},{"language":"powershell","snippet":"py -m venv venv\n   .\\venv\\Scripts\\Activate.ps1\n   py -m pip install --upgrade pip\n   pip install -r requirements.txt"},{"language":"powershell","snippet":"Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"Local-first multi-agent career intelligence system built with Python and CrewAI for evidence-based resume analysis, job matching, skill-gap detection, resume tailoring, and interview preparation. Resume_Crew $1 $1 $1 $1 **Resume_Crew** compares a resume against a job description and produces an evidence-focused match report — no invented skills, no guessed experience. It runs entirely on your machine by default (via $1), with an optional cloud fallback to Google Gemini. It ships two ways to use it: - **CLI** (main.py) — scriptable, good for batch/automation work - **Gradio web UI** (app.py) — point-and-click,","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":393,"uniquenessScore":70,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T13:52:36.413Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T13:52:36.413Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T23:16:00.589Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"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!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"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","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}