# DimiMikadze/orca

AI agent for deep LinkedIn profile analysis.

Repository: https://github.com/DimiMikadze/orca
Canonical: https://ross.abutalabs.com/products/dimimikadze-orca
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-07-27T23:27:20+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 35, longevity 100
- inputs: {"age_days": 2529, "days_push": 37, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1297, forks 301 (observed 2026-08-28T04:04:16.984718+00:00)

## What it is
Orca is an AI agent application for deep LinkedIn profile analysis that scrapes posts, comments, reactions, and interaction networks, then autonomously reasons over the data to extract structured insights. It is built with Next.js and LangChain, with the core analysis logic available as a standalone Node.js library.

## Use cases
- analyze a LinkedIn profile before sales outreach
- assess what a job candidate actually cares about beyond their resume
- research a founder's thinking for investment decisions
- extract pain points and expertise from someone's LinkedIn activity
- track how a person's interests change over time on LinkedIn
- map someone's network influence and communication style

## When to choose
- you need autonomous, structured insights from LinkedIn profiles rather than simple profile summaries
- you want a self-hosted Next.js app with a streaming UI for profile analysis
- you want to reuse the analysis agent as a Node.js library in your own project
- you support multiple LLM providers via LangChain and need flexible agent tooling

## When to avoid
- you need bulk LinkedIn scraping without API costs - it requires a paid RapidAPI key
- you want a fully managed SaaS with no setup - this is self-hosted
- your target data is not LinkedIn (e.g., Twitter/X or generic web profiles)
- you cannot share profile data with third-party LLM providers due to privacy constraints

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, web-scraping, llm-inference, nlp, rag
- domain: artificial-intelligence, social-media, web-development
- platform: self-hosted
- tags: linkedin-analysis, nextjs, langchain, sales-intelligence, recruiting, profile-scraping, structured-insights, ai-agents, natural-language-processing, nodejs, web-server, typescript

## Member repositories
- DimiMikadze/orca (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:16.984718+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:53:51.599742+00:00, confidence not recorded.
  - readme: https://github.com/DimiMikadze/orca (fetched 2026-08-28T04:04:16.984718+00:00, sha 870f55c1d084)
- Data as of 2026-08-30T08:39:29.467469+00:00.