Skip to content

candidate_analyser

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History
 
 

candidate_analyser

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
README.md
README.md
 
 
hiring_prompts.yaml
hiring_prompts.yaml
 
 
main.py
main.py
 
 
pyproject.toml
pyproject.toml
 
 
requirements.txt
requirements.txt
 
 

README.md

🧠 Candilyzer

AI-Powered Candidate Analyzer for GitHub & LinkedIn
Strict, expert-level screening for tech candidates

Streamlit Nebius Token Factory Agno

🔍 What is Candilyzer?

Candilyzer is an advanced, AI-powered app that strictly analyzes technical candidates based on their GitHub and LinkedIn profiles. Designed like a tough hiring manager, it gives you detailed evaluations, skill assessments, and a final decision — all with zero assumptions.

⚡ Features

  • ✅ Multi-Candidate Analyzer
    Analyze multiple GitHub users side-by-side for any job role.

  • ✅ Single Candidate Profiler
    Deep analysis of one candidate's GitHub + optional LinkedIn profile.

  • ✅ Strict Scoring System
    Each candidate is scored out of 100 with a clear final verdict.

  • ✅ Professional-Grade Reports
    No fluff. Only data-backed, AI-generated expert-level assessments.

  • ✅ Powered by Agents
    Uses Agno’s agent framework with Nebius + GitHubTools + ExaTools.

🧰 Tech Stack

Component Tool/Library
UI 🧼 Streamlit
AI Model 🧠 DeepSeek via Nebius
Agent Framework 🧠 Agno Agents
GitHub Analysis 🛠️ GitHubTools
LinkedIn Parsing 🔎 ExaTools
Reasoning Engine 🧩 ReasoningTools + ThinkingTools

🚀 How to Run Locally

1. Clone the Repository

git clone https://github.com/Arindam200/awesome-ai-apps.git
cd advance_ai_agents/candidate_analyser

2. Install Requirements

# Using pip
pip install -r requirements.txt

# Or using uv (recommended)
uv sync

3. Get API Keys

You'll need:

4. Launch App

streamlit run main.py

🖥️ How to Use

🔁 Multi-Candidate Analyzer

  1. Paste GitHub usernames (one per line)
  2. Enter target Job Role (e.g. Backend Engineer)
  3. Click Analyze Candidates

🔎 Single Candidate Analyzer

  1. Enter GitHub username
  2. (Optionally) Add LinkedIn profile link
  3. Enter Job Role (e.g. ML Engineer)
  4. Click Analyze Candidate 🔥

📊 Evaluation Logic

Candilyzer uses no assumptions and follows strict rules:

  • 📁 GitHub Repos → code quality, structure, frequency
  • 🧑‍💻 Commits → consistency, activity, skills shown
  • 💼 LinkedIn → job titles, descriptions, keywords (via Exa)
  • 🎯 Job Fit → match with required skills & experience
  • 🧠 AI Reasoning → Final combined judgment with score

🧪 Powered by Agno Agents

Candilyzer builds a smart agent with:

Agent(
  model=Nebius(...),
  tools=[
    GithubTools(...),
    ExaTools(...),
    ThinkingTools(...),
    ReasoningTools(...)
  ]
)

This agent:

  • Thinks before evaluating (🧠)
  • Gathers accurate GitHub + LinkedIn info (🔍)
  • Reasons like an expert hiring manager (📈)
  • Provides a final score with strict justification (✅❌)

🔗 Links

💡 Candilyzer is your AI hiring expert. Use it to save time, reduce bias, and get straight to the point.