You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+52-46Lines changed: 52 additions & 46 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -45,15 +45,27 @@ Perfect for founders, sales teams, and agencies who want powerful automation **w
45
45
46
46
---
47
47
48
+
## 📋 What You Need
49
+
50
+
| # | What | Example |
51
+
|---|------|---------|
52
+
| 1 |**A LinkedIn account**| Your email + password |
53
+
| 2 |**An LLM API key**| OpenAI, Anthropic, or any OpenAI-compatible endpoint |
54
+
| 3 |**A product description + target market**| "We sell cloud cost optimization for DevOps teams at mid-market SaaS companies" |
55
+
56
+
That's it. No spreadsheets, no lead databases, no scraping setup.
57
+
58
+
---
59
+
48
60
## ⚡ Quick Start (Docker — Recommended)
49
61
50
-
The fastest way to get started. Pre-built images are published to GitHub Container Registry on every push to `master`.
62
+
Pre-built images are published to GitHub Container Registry on every push to `master`.
51
63
52
64
```bash
53
65
docker run --pull always -it -p 5900:5900 -v openoutreach_data:/app/assets ghcr.io/eracle/openoutreach:latest
54
66
```
55
67
56
-
The interactive onboarding will prompt you for LinkedIn credentials, LLM API key, and campaign details on first run. Your data persists in the `openoutreach_data` Docker volume across restarts.
68
+
The interactive onboarding walks you through the three inputs above on first run. Your data persists in the `openoutreach_data` Docker volume across restarts.
57
69
58
70
Connect a VNC client to `localhost:5900` to watch the browser live.
59
71
@@ -117,49 +129,6 @@ Then open:
117
129
118
130
---
119
131
120
-
### ❤️ Support OpenOutreach – Keep the Leads Flowing!
121
-
122
-
This project is built in spare time to provide powerful, **free** open-source growth tools.
123
-
124
-
Maintaining stealth, fixing bugs, adding features (multi-account scaling, better templates, AI enhancements), and staying ahead of LinkedIn changes takes serious effort.
125
-
126
-
**Your sponsorship funds faster updates and keeps it free for everyone.**
127
-
128
-
<divalign="center">
129
-
130
-
[](https://github.com/sponsors/eracle)
| ☕ Supporter | $5 | Huge thanks + name in README supporters list |
139
-
| 🚀 Booster | $25 | All above + priority feature requests + early access to new campaigns |
140
-
| 🦸 Hero | $100 | All above + personal 1-on-1 support + influence roadmap |
141
-
| 💎 Legend | $500+ | All above + custom feature development + shoutout in releases |
142
-
143
-
**Thank you to all sponsors — you're powering open-source B2B growth!** 🚀
144
-
145
-
</div>
146
-
147
-
---
148
-
149
-
### 🗓️ Book a Free 15-Minute Call
150
-
151
-
Got a specific use case, feature request, or questions about setup?
152
-
153
-
Book a **free 15-minute call** — I’d love to hear your needs and improve the tool based on real feedback.
154
-
155
-
<divalign="center">
156
-
157
-
[](https://calendly.com/eracle/new-meeting)
158
-
159
-
</div>
160
-
161
-
---
162
-
163
132
## 📖 How the ML Pipeline Works
164
133
165
134
The daemon runs a continuous loop with priority-scheduled action lanes:
@@ -183,6 +152,8 @@ For each selected profile, the Gaussian Process model checks if it's confident e
183
152
184
153
**Cold start:** With fewer than 2 labelled profiles, the model can't fit — all decisions go through the LLM. As labels accumulate, the GP auto-decides more profiles, reducing LLM calls over time.
185
154
155
+
**Cost curve:** The system gets cheaper to run the longer it operates. Early on, every profile requires an LLM call (~100% LLM usage). As the Gaussian Process learns your preferences, it auto-decides with high confidence on an increasing share of profiles — the LLM is only queried for genuinely uncertain cases. A mature model can auto-decide the majority of profiles, cutting LLM costs dramatically.
156
+
186
157
Configure rate limits and behavior via Django Admin (LinkedInProfile + Campaign models).
187
158
188
159
---
@@ -238,11 +209,46 @@ Configure rate limits and behavior via Django Admin (LinkedInProfile + Campaign
238
209
239
210
## 💬 Community
240
211
241
-
Join for support and discussions:
212
+
Join for support and discussions:
242
213
[Telegram Group](https://t.me/+Y5bh9Vg8UVg5ODU0)
243
214
244
215
---
245
216
217
+
### 🗓️ Book a Free 15-Minute Call
218
+
219
+
Got a specific use case, feature request, or questions about setup?
220
+
221
+
Book a **free 15-minute call** — I'd love to hear your needs and improve the tool based on real feedback.
222
+
223
+
<divalign="center">
224
+
225
+
[](https://calendly.com/eracle/new-meeting)
226
+
227
+
</div>
228
+
229
+
---
230
+
231
+
### ❤️ Support OpenOutreach
232
+
233
+
This project is built in spare time to provide powerful, **free** open-source growth tools. Your sponsorship funds faster updates and keeps it free for everyone.
234
+
235
+
<divalign="center">
236
+
237
+
[](https://github.com/sponsors/eracle)
0 commit comments