Skip to content

About

Autonomous engineering intelligence and career targeting system that discovers, scores, and investigates high-leverage open-source issues across high-growth AI startups.

Resources

Stars

1 star

Watchers

0 watching

Forks

Latest commit

Β 

History

1 Commit

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Startup Opportunity Radar πŸš€

Autonomous engineering intelligence and career targeting system that discovers, scores, and investigates high-leverage open-source issues across high-growth AI startups.

Python 3.11+ Test Suite License: MIT Code Grounding


1. Overview & Strategy

The Startup Opportunity Radar is an end-to-end engineering pipeline built to solve a specific career problem:

How does a talented solo engineer systematically identify real, high-value technical problems in promising startup codebases, solve them, and use those contributions as proof-of-work to earn a high-paying USD role or paid collaboration?

Instead of guessing or browsing GitHub manually, the Radar builds a multi-phase intelligence pipeline:

YC Open Source Universe (Phase 4)
            β”‚
            β–Ό
Company β†’ GitHub Entity Resolution (Phase 1)
            β”‚
            β–Ό
Public Repository Enumeration & Quality Scoring (Phase 0)
            β”‚
            β–Ό
Deterministic Issue Mining & Opportunity Scoring (Phase 2 & 2.1)
            β”‚
            β–Ό
Strategic Career Target Ranking (Phase 5)
            β”‚
            β–Ό
Code-Grounded AI Engineering Investigation (Phase 3)
            β”‚
            β–Ό
Actionable Build Brief & Targeted Upstream Pull Request

2. System Architecture & Phases

Startup Opportunity Radar
β”‚
β”œβ”€β”€ Phase 0: Repository Discovery & Quality Scoring
β”‚   β”œβ”€β”€ Multi-query GitHub search orchestrator
β”‚   β”œβ”€β”€ Deterministic noise/tutorial/boilerplate filter
β”‚   └── 4-dimensional scoring (Activity, Quality, Product Likeness, Opportunity Potential)
β”‚
β”œβ”€β”€ Phase 1: Company Entity Resolution
β”‚   β”œβ”€β”€ Links startup brands (e.g. "Steel", "E2B") to GitHub orgs (steel-dev, e2b-dev)
β”‚   β”œβ”€β”€ Multi-signal domain matching, homepage normalization, and login heuristics
β”‚   └── Strict confidence tagging (HIGH, MEDIUM, LOW, REJECTED, NOT_FOUND)
β”‚
β”œβ”€β”€ Phase 2 & 2.1: Deterministic Engineering Opportunity Mining
β”‚   β”œβ”€β”€ Issue taxonomy classification (MCP, AI SDK, Agent Framework, Performance, Security)
β”‚   β”œβ”€β”€ Maintainer participation signals and PR collision context
β”‚   β”œβ”€β”€ Feasibility estimation (days, solo-engineer boundary clarity)
β”‚   └── Multi-dimensional opportunity scoring (Proof-of-Work, Issue Quality, Feasibility, etc.)
β”‚
β”œβ”€β”€ Phase 3: Code-Grounded AI Engineering Investigator
β”‚   β”œβ”€β”€ AST & file-level codebase retrieval via GitHub API / local tree
β”‚   β”œβ”€β”€ Strict fail-closed grounding guardrails (zero hallucinated filepaths/symbols)
β”‚   β”œβ”€β”€ Powered by Google Gemini Interactions API with bounded retries and sanitized logging
β”‚   └── Actionable Build Brief synthesis for high-confidence BUILD recommendations
β”‚
β”œβ”€β”€ Phase 4: Curated YC Startup Ingestion
β”‚   β”œβ”€β”€ Respectful, cached ingestion of YC Open Source startup directory
β”‚   β”œβ”€β”€ Complete company target normalization (batch, headcount, domain, subindustry)
β”‚   └── Deduplicated SQLite persistence
β”‚
└── Phase 5: Career Target Ranking
    β”œβ”€β”€ Evaluates expected return on engineering effort for proof-of-work strategy
    β”œβ”€β”€ Combines Technical Opportunity Density (25%), Open-Source Quality (20%),
    β”‚   Contribution Accessibility (15%), and Founder/Team Accessibility (15%)
    └── Target classification tiers: S (Immediate Priority), A (Strong), B, C, D

3. Core Principles

  1. Fact vs. Inference vs. Explicit Unknown:
    • Facts: Direct data from GitHub API / YC Directory (stars, open issues, exact commit timestamps, license SPDX, team size).
    • Inferences: Deterministic algorithms derived from facts (opportunity score, career target score, activity tier).
    • Unknowns: Attributes unverifiable from public APIs (venture round size, code review latency) are explicitly marked as UNKNOWN rather than guessed.
  2. Fail-Closed Code Grounding:
    • The AI Investigator never claims an implementation root cause if the target code file was not retrieved. Unretrieved hypotheses are labeled [HYPOTHESIS].
  3. Non-Destructive Persistence:
    • Successful investigation reports and verified company mappings in SQLite are preserved and never overwritten by temporary network or validation failures.

4. Installation & Quickstart

Prerequisites

  • Python 3.11+
  • Git
  • (Optional) GitHub Personal Access Token (increases GitHub API limit from 60 to 5,000 req/hr)
  • (Optional) Google Gemini API Key (for Phase 3 AI Codebase Investigation)

Setup

# 1. Clone the repository
git clone https://github.com/Priyavart/startup-opportunity-radar.git
cd startup-opportunity-radar

# 2. Create and activate a virtual environment
python -m venv .venv

# On Windows (PowerShell):
.venv\Scripts\Activate.ps1

# On macOS/Linux:
source .venv/bin/activate

# 3. Install dependencies in editable mode
pip install -e .

# 4. Configure environment variables
cp .env.example .env
# Edit .env and add your GITHUB_TOKEN and GEMINI_API_KEY

5. CLI Command Reference

The radar provides a unified CLI via radar:

🎯 Career Target Ranking (Phase 5)

# View Top 20 Career Targets ranked for proof-of-work leverage
radar career-targets --top 20

# Inspect a specific company's career target profile
radar career-target "Browser Use"

# Export ranked career targets to JSON or CSV
radar career-targets export --format json
radar career-targets export --format csv

🏒 YC Directory Ingestion (Phase 4)

# Ingest all YC Open Source companies with GitHub entity resolution
radar source yc --resolve-github

# List all stored YC companies
radar source yc companies --limit 50

# Export ingested YC dataset
radar source yc export --format json

πŸ” Company Resolution & Repository Enumeration (Phase 1)

# Resolve a company name to its verified GitHub organization
radar company "Browser Use"

# Resolve multiple companies from a text file
radar company --file companies.txt

⛏️ Engineering Opportunity Mining (Phase 2 & 2.1)

# Mine and score all open issues across a company's repositories
radar mine-company "Browser Use"

# View top deterministic opportunities across all indexed repositories
radar opportunities --top 10 --tier S

# Inspect a single opportunity in detail with why-worth vs why-not-worth building
radar opportunity browser-use/browser-use#5252

πŸ€– AI Engineering Investigation (Phase 3)

# Run deep technical codebase investigation on an issue
radar investigate browser-use/browser-use#5252

# Force refresh code retrieval and re-run AI evaluation
radar investigate browser-use/browser-use#5252 --refresh-ai

🌐 Repository Discovery & Exploration (Phase 0)

# Run multi-query GitHub repository discovery
radar discover --queries 5 --min-stars 50

# View highest scoring discovered repositories
radar top --limit 20

# Inspect repository metadata, licensing, and activity signals
radar inspect browser-use/browser-use

6. Project Structure

Git-o-hub/
β”œβ”€β”€ config.yaml               # System queries, scoring weights, and cache TTL
β”œβ”€β”€ pyproject.toml            # Package specification and dependencies
β”œβ”€β”€ .env.example              # Template for API keys
β”œβ”€β”€ .gitignore                # Production-ready git ignore
β”œβ”€β”€ data/
β”‚   └── .gitkeep              # SQLite database storage directory (data/radar.db)
β”œβ”€β”€ exports/
β”‚   └── .gitkeep              # Directory for JSON/CSV report exports
β”œβ”€β”€ src/
β”‚   └── radar/
β”‚       β”œβ”€β”€ cli.py            # Rich + Typer CLI interface
β”‚       β”œβ”€β”€ config.py         # Pydantic Settings & YAML loader
β”‚       β”œβ”€β”€ db.py             # SQLite schema manager & WAL connection pool
β”‚       β”œβ”€β”€ models.py         # Unified Pydantic models for all 5 phases
β”‚       β”œβ”€β”€ ai/               # Phase 3: Code retriever, Gemini provider, investigator
β”‚       β”œβ”€β”€ career/           # Phase 5: Attractiveness scoring, eligibility, service
β”‚       β”œβ”€β”€ discovery/        # Phase 0: Search orchestrator, filter, classifier
β”‚       β”œβ”€β”€ entity/           # Phase 1: Candidate generator, evidence matcher, resolver
β”‚       β”œβ”€β”€ github/           # HTTPX client with rate limiting, cache, and retries
β”‚       β”œβ”€β”€ mining/           # Phase 2: Issue mining, feasibility, maintainer signals
β”‚       β”œβ”€β”€ scoring/          # Phase 0 & 2.1: Multi-dimensional scoring engines
β”‚       β”œβ”€β”€ storage/          # SQLite persistence layers for all entities
β”‚       └── yc/               # Phase 4: YC directory client, parser, normalizer
└── tests/                    # 93 automated pytest unit & integration tests

7. Running Tests

The test suite contains 93 unit and integration tests covering all phases, scoring models, rate limiting, and failure handling:

# Run full test suite
pytest -v

# Run specific phase tests
pytest tests/test_career_ranking.py -v
pytest tests/test_ai_investigator.py -v
pytest tests/test_mining.py -v
pytest tests/test_entity_resolution.py -v
pytest tests/test_yc_source.py -v

8. Shortlisted Target Codebases

Based on the Radar's deterministic ranking and practicality filter, the top repositories to clone and contribute to are:

Priority Repository Tech Stack Domain Why Clone
#1 browser-use/browser-use Python 3.11+, Playwright AI Agent Infrastructure Massive traction (111kβ˜…), 7-person team with direct founder review, clean local pytest setup.
#2 better-auth/better-auth TypeScript, Node.js Developer Tooling & Auth Exploding ecosystem (30kβ˜…), 4-person team, zero native binary dependencies, instant Vitest execution.
#3 activepieces/activepieces TypeScript, Node.js MCP & Workflow Automation Leading MCP server repository (~400 tools), modular piece SDK, active maintainers.
#4 cactus-compute/needle Python, PyTorch Edge AI & Model Optimization 14MB edge foundation model, cutting-edge token optimization, 8-person startup team.
#5 beam-cloud/beta9 Go 1.22+, Docker Serverless GPU Infrastructure Distributed systems runtime, container sandboxes, high-value cloud engineering proof-of-work.

9. License

This project is licensed under the MIT License β€” see the LICENSE file for details.

About

Autonomous engineering intelligence and career targeting system that discovers, scores, and investigates high-leverage open-source issues across high-growth AI startups.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages