Repository files navigation

The open-source growth engine that puts your LinkedIn B2B lead generation on autopilot.

Demo:

OpenOutreach is aself-hosted, open-source LinkedIn automation tool designed for B2B lead generation, without the risks and costs of cloud SaaS services.

It automates the entire outreach process in astealthy, human-like way:

• Discovers and enriches target profiles
• Qualifies and ranks profiles using online Bayesian active learning (BALD acquisition + entropy-gated auto-decisions)
• Sends personalized connection requests
• Follows up with custom messages after acceptance
• Tracks everything in a built-in CRM with web UI (full data ownership, resumable workflows)

Why choose OpenOutreach?

• 🛡️Undetectable — Playwright + stealth plugins mimic real user behavior
• 🐍Fully customizable — Python-based campaigns for unlimited flexibility
• 💾Local execution + CRM — You own your data, browse it in a web UI
• 🐳Easy deployment — Dockerized, one-command setup
• ✨AI-ready — Built-in templating for hyper-personalized messages (easy integration with latest models like GPT-5.3-Codex)

Perfect for founders, sales teams, and agencies who want powerful automationwithout account bans or subscription lock-in.

The fastest way to get started. Pre-built images are published to GitHub Container Registry on every push tomaster.

docker run --pull always -it -p 5900:5900 -v openoutreach_data:/app/assets ghcr.io/eracle/openoutreach:latest

The interactive onboarding will prompt you for LinkedIn credentials, LLM API key, and campaign details on first run. Your data persists in theopenoutreach_data Docker volume across restarts.

Connect a VNC client tolocalhost:5900 to watch the browser live.

For Docker Compose, build-from-source, and more options see theDocker Guide.

For contributors or if you prefer running directly on your machine.

• Git
• Python (3.12+)

git clone https://github.com/eracle/OpenOutreach.gitcd OpenOutreach# Install deps, Playwright browsers, run migrations, and bootstrap CRMmake setup

make run

The interactive onboarding will prompt for LinkedIn credentials, LLM API key, and campaign details on first run. Fully resumable — stop/restart anytime without losing progress.

OpenOutreach includes a full CRM web interface powered by DjangoCRM:

# Create an admin account (first time only)python manage.py createsuperuser# Start the web servermake admin

Then open:

• Django Admin:http://localhost:8000/admin/
• CRM UI:http://localhost:8000/crm/

This project is built in spare time to provide powerful,free open-source growth tools.

Maintaining stealth, fixing bugs, adding features (multi-account scaling, better templates, AI enhancements), and staying ahead of LinkedIn changes takes serious effort.

Your sponsorship funds faster updates and keeps it free for everyone.

Got a specific use case, feature request, or questions about setup?

Book afree 15-minute call — I’d love to hear your needs and improve the tool based on real feedback.

The daemon (linkedin/daemon.py) priority-schedules five action lanes:

Profile states:DISCOVERED →ENRICHED →QUALIFIED →PENDING →CONNECTED →COMPLETED (orFAILED /IGNORED /DISQUALIFIED)

Pre-existing connections (already connected before automation) are automatically set toIGNORED during enrichment. Ifconnection_degree was unknown at scrape time, they're caught during the connect step. Profiles rejected by the qualification pipeline are set toDISQUALIFIED.

Configure rate limits, timing, and behavior in thecampaign: section ofaccounts.secrets.yaml.

├── analytics/                       # dbt project (DuckDB analytics, ML training sets)│   ├── models/staging/              # Staging views (stg_leads, stg_deals, stg_stages)│   └── models/marts/                # ML training set (ml_connection_accepted)├── assets/│   ├── accounts.secrets.yaml        # Credentials + campaign + LLM config (gitignored)│   ├── inputs/                      # Optional input files│   ├── campaign/                    # Onboarding files (product_docs.txt, campaign_objective.txt)│   └── data/                        # crm.db (SQLite), analytics.duckdb (embeddings + analytics)├── docs/│   ├── architecture.md              # System architecture│   ├── configuration.md             # Configuration reference│   ├── docker.md                    # Docker setup guide│   ├── templating.md                # Message template guide│   └── testing.md                   # Testing strategy├── linkedin/│   ├── actions/                     # Browser actions (connect, message, scrape)│   ├── api/                         # Voyager API client + parser│   ├── conf.py                      # Configuration loading (secrets YAML + env vars)│   ├── daemon.py                    # Main daemon loop (priority-scheduled lanes)│   ├── db/crm_profiles.py           # CRM-backed profile CRUD (Lead, Contact, Company, Deal)│   ├── django_settings.py           # Django/CRM settings (SQLite at assets/data/crm.db)│   ├── lanes/                       # Action lanes (enrich, qualify, connect, check_pending, follow_up, search)│   ├── management/setup_crm.py      # Idempotent CRM bootstrap (Dept, Stages, Users)│   ├── ml/                          # Bayesian qualifier, DuckDB embeddings, profile text, search keywords│   ├── navigation/                  # Login, throttling, browser utilities, enums│   ├── onboarding.py                # Interactive onboarding (product docs + campaign objective)│   ├── gdpr.py                      # GDPR location detection for newsletter│   ├── rate_limiter.py              # Daily/weekly rate limiting│   ├── sessions/                    # Session management (AccountSession)│   └── templates/                   # Message rendering (Jinja2 / AI-prompt)├── manage.py                         # Entry point (no args = daemon, or Django commands)├── local.yml                        # Docker Compose└── Makefile                         # Shortcuts (setup, run, admin, analytics, test)

• Architecture
• Configuration
• Docker Installation
• Templating
• Template Variables
• Testing

Join for support and discussions:
Telegram Group

GNU GPLv3 — seeLICENCE.md

Not affiliated with LinkedIn.

By using this software you accept theLegal Notice. It covers LinkedIn ToS risks, built-in self-promotional actions, automatic newsletter subscription for non-GDPR accounts, and liability disclaimers.

Use at your own risk — no liability assumed.