orca - GitLite

KO | EN

gitlite — search

#hacktoberfest #ai #typescript #machine-learning #docker #macos #windows #cli #kubernetes #vue #pytorch #mcp #ios #open-source

orca

(★ 1,297)

AI agent for deep LinkedIn profile analysis.

File Explorer

Download Latest Version (.zip)

- - ci.yml
- - login-form.tsx
  - page.tsx
- - profile-analysis-collected-data-modal.tsx
  - profile-analysis-insights-modal.tsx
  - profile-analysis-progress.tsx
  - profile-analysis-result-activity.tsx
  - profile-analysis-result-header.tsx
  - profile-analysis-result-insights.tsx
  - profile-analysis-result-timeline.tsx
  - profile-analysis-result.tsx
  - profile-analysis.tsx
  - use-insights.ts
- - auth.ts
  - client.ts
  - database.types.ts
  - middleware.ts
  - orm.ts
  - server.ts
- dummy-data.ts
- favicon.ico
- globals.css
- layout.tsx
- page.tsx
- - alert.tsx
  - autosize-textarea.tsx
  - badge.tsx
  - button.tsx
  - card.tsx
  - dialog.tsx
  - dropdown-menu.tsx
  - form.tsx
  - input.tsx
  - label.tsx
  - separator.tsx
  - skeleton.tsx
  - switch.tsx
  - tooltip.tsx
- logout-button.tsx
- utils.ts
- - analysis-agent.test.ts
- - collect-linkedin-data.ts
  - linkedin-activity-scraper.ts
  - linkedin-post-comments-scraper.ts
  - linkedin-post-reactions-scraper.ts
  - linkedin-profile-scraper.ts
- - format-linkedin-data.ts
  - linkedin-api-credits.ts
- analysis-agent.ts
- config.ts
- index.ts
- orchestrator.ts
- types.ts
- logo-black.png
- logo-white.png
.gitignore
CLAUDE.md
components.json
CONTRIBUTING.md
demo.gif
eslint.config.mjs
LICENSE
next.config.ts
package.json
pnpm-lock.yaml
pnpm-workspace.yaml
postcss.config.mjs
proxy.ts
README.md
tsconfig.json
vitest.config.mts
vitest.setup.mts

# Installation Guide

1. Get the code

git clone https://github.com/DimiMikadze/orca

Downloads the entire project code from GitHub to your computer.

cd orca

Moves into the project folder you just downloaded.

2. Node.js

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Node.js Node.js must be installed to use npm. The LTS version is recommended.

pnpm install

Downloads and installs the libraries listed in package.json.

pnpm dev

Starts the development/run server.

✅ After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.

Pulled directly from this repo's README.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<p align="center">
  <img src="public/logo-black.png" alt="Orca Logo" width="300" />
</p>

<p align="center">AI agent for deep LinkedIn profile analysis.</p>

<div align="center">

[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://raw.githubusercontent.com/DimiMikadze/orca/main/LICENSE)
[![Build Status](https://github.com/dimimikadze/orca/actions/workflows/ci.yml/badge.svg)](https://github.com/dimimikadze/orca/actions/workflows/ci.yml)
[![Contributions Welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://raw.githubusercontent.com/DimiMikadze/orca/main/CONTRIBUTING.md)

</div>

<p align="center">
  <a href="https://youtu.be/bNrJuVCOIaU">
    <img src="https://img.shields.io/badge/Watch%20Demo%20Video-red?style=for-the-badge&logo=youtube" />
  </a>
</p>

Orca is an AI agent for deep LinkedIn profile analysis. You define the insights you care about, and Orca extracts them.

It scrapes posts, comments, reactions, and interaction networks, then reasons over the data autonomously to extract structured insights like pain points, current focus, values, expertise, network influence, communication style, and how interests change over time. It calls additional scraping tools on its own when it needs more data.

The core logic lives in orca-ai/ as a standalone library. You can plug it into any Node.js project and run it at scale.

**Use cases**

- Sales: understand a prospect's real priorities before outreach
- Recruiting: assess what a candidate actually cares about beyond their résumé
- Investing: map a founder's thinking and evaluate positioning

<p align="center">
  <img src="./demo.gif" alt="Orca Demo" width="80%" />

</p>

## How it works

1. Provide a LinkedIn profile URL and define the insights you want to extract.
2. Orca scrapes the baseline data: profile, posts, comments, reactions, and top post engagement.
3. The agent reasons over the data and extracts structured insights. If it needs more data for a specific insight, it calls scraping tools autonomously.
4. Results stream back to the UI as the agent works.

## Tech Stack

- Next.js 16, TypeScript, Tailwind CSS
- LangChain (supports OpenAI, Anthropic, and other LLM providers)

## Requirements

- Node.js 20+, pnpm
- [Fresh LinkedIn Profile Data](https://rapidapi.com/freshdata-freshdata-default/api/fresh-linkedin-profile-data) API key
- API key for your LLM provider of choice (default: OpenAI)

## Environment Variables

Create `.env.local` in the project root:

```
RAPIDAPI_KEY=your_key
OPENAI_API_KEY=your_key
```

Authentication is **optional**. To restrict access with a login page, add Supabase credentials:

```
NEXT_PUBLIC_SUPABASE_URL=your_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_anon_key
```

When set, all pages and the API are protected behind email/password login. Without them, the app runs open with no auth.

## Installation

```bash
git clone https://github.com/dimimikadze/orca.git
cd orca
pnpm install
pnpm dev
```

Open http://localhost:3000.

## Tests

All scrapers and the analysis agent are covered by tests. Each test can run against recorded fixtures (no live API needed) or against real LinkedIn data by setting `USE_LIVE_DATA = true` in the test file.

Dedicated test cases and all available test commands are in `package.json`.

## Contributing

See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.

## License

Distributed under the MIT License. See [LICENSE](./LICENSE) for details.