AI MCN 自动推广工具 — 多Agent内容营销自动化,支持掘金/知乎/Dev.to
Project description
AgentCrew MCN 🤖
📖 中文文档 | English
What is AgentCrew?
AgentCrew MCN is an open-source multi-agent content marketing automation tool. A team of AI "employees" handles the entire pipeline — from content creation to cross-platform distribution.
- Writer Agent — Copywriter: generates technical articles, social posts, and threads
- Reviewer Agent — QA: pre-publish content safety and quality review
- Publisher Agent — Operations: publishes to Juejin, Zhihu, Dev.to, and more
- Analyst Agent — Data Analyst: tracks performance and smart scheduling
Features
- 🧠 4 AI Agents — Writer, Reviewer, Publisher, Analyst — each operates independently
- 🔧 Skills + Tools System — Atomic operations composed into high-level capabilities (v0.4: LLM-driven)
- 📚 RAG Knowledge Base — Retrieval-augmented generation from historical content
- 🌍 Cross-Platform Publishing — Juejin, Zhihu, Dev.to with platform-specific style adaptation
- 🔌 Multi-Provider LLM — DeepSeek, OpenAI, Anthropic, Ollama — switch with one config field
- 🖼️ Image Generation — DALL-E 3 cover images for articles
- ⏰ Smart Scheduling — Analyst predicts best publish times with random jitter anti-detection
- 📊 Dashboard + Growth Tracking — Web UI for analytics + GROWTH.md for metrics
- 🐳 Docker — One-command deployment with docker-compose
- 🔁 Dogfooding — The project promotes itself
Quick Start
Option 1: pip install (recommended)
# 1. Install
pip install agentcrew-mcn
# 2. Initialize config
agentcrew-mcn init
# 3. Edit .env with your API keys
# DEEPSEEK_API_KEY=sk-...
# 4. Start using
agentcrew-mcn write generate --topic "Python async programming" --style technical
agentcrew-mcn publish post --file article.md --platform juejin --dry-run
💡
agent-crewis also available as an alias foragentcrew-mcn.
Option 2: From source
# 1. Clone
git clone https://github.com/super-rick/agentcrew-mcn.git
cd agentcrew-mcn
# 2. Install dependencies
pip install -r requirements.txt
# 3. Initialize
python -m cli.main init
# 4. Edit .env with your API keys
Configuration
agentcrew-mcn init creates a config template. Key settings:
# config.yaml
llm:
api_key: ${DEEPSEEK_API_KEY} # Reads from .env
model: deepseek-chat
platforms:
juejin:
cookie: ${JUEJIN_COOKIE} # Export cookie from browser
devto:
api_key: ${DEVTO_API_KEY} # https://dev.to/settings/extensions
Usage
# Generate a technical article
agentcrew-mcn write generate --topic "Python async programming" --style technical
# Preview mode (no LLM call, inspect parameters)
agentcrew-mcn write generate --topic "Python async" --dry-run
# Publish to Juejin
agentcrew-mcn publish post --file article.md --platform juejin
# Scheduled publishing (every 6 hours)
agentcrew-mcn schedule start --topic-file topics.txt --platform juejin --interval 6
# RAG knowledge base
agentcrew-mcn rag ingest --file article.md --source "my_blog"
agentcrew-mcn rag search --query "AI Agent architecture"
Architecture
┌─────────────────────────────────────────────────────┐
│ Orchestrator │
│ Task dispatch / Scheduler / Config │
└──┬──────────┬──────────────┬────────────────────────┘
│ │ │
┌──▼──────┐ ┌▼────────┐ ┌──▼────────┐
│ Writer │ │Publisher│ │ Analyst │
│ Agent │ │Agent │ │ Agent │
│ │ │ │ │ │
│ Skills: │ │ Skills: │ │ Skills: │
│ trending│ │ schedule│ │ report │
│ tech │ │ multi │ │ recommend │
│ thread │ │ batch │ │ │
│ │ │ │ │ │
│ Tools: │ │ Tools: │ │ Tools: │
│ search │ │ devto │ │ analytics │
│ rag │ │ juejin │ │ compare │
│ compose │ │ zhihu │ │ report │
└─────────┘ └─────────┘ └───────────┘
Dashboard
AgentCrew includes a Streamlit Dashboard for monitoring your AI marketing team.
More Dashboard Pages
| Publish Analysis | AI Analysis |
|---|---|
Tech Stack
| Component | Technology |
|---|---|
| Language | Python 3.10+ |
| CLI | Click + Rich |
| LLM | DeepSeek API (OpenAI-compatible) |
| Vector DB | ChromaDB |
| Automation | Playwright |
| Dashboard | Streamlit + Plotly |
Roadmap
See ROADMAP.md for details.
- v0.1 ✅ Writer + Publisher + CLI + Juejin/Zhihu + Dashboard
- v0.2 ✅ Dev.to adapter + RAG + MCP + Bilingual README
- v0.3 ✅ Reviewer Agent + Retry + Persistence + Docker (332 tests)
- v0.4 ✅ LLM-driven Skills + Multi-provider + Image gen + Smart scheduling
- v0.5 ✅ 6 new platforms (CSDN/WeChat/SegmentFault/X/Xiaohongshu/Medium)
- v1.0 🔮 Web API + Plugins + Community
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agentcrew_mcn-0.5.4.tar.gz.
File metadata
- Download URL: agentcrew_mcn-0.5.4.tar.gz
- Upload date:
- Size: 93.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2f11e0e137af149218e2a13f4079d97f99ff6bc4c366171ed47f951e3db127a1
|
|
| MD5 |
f30c837e3b67279025fb50a4ec13f05a
|
|
| BLAKE2b-256 |
9402e27ca11dc51f8461ef2cd87310254f9f9c837989d48816d559488918c0ac
|
Provenance
The following attestation bundles were made for agentcrew_mcn-0.5.4.tar.gz:
Publisher:
publish.yml on super-rick/agentcrew-mcn
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
agentcrew_mcn-0.5.4.tar.gz -
Subject digest:
2f11e0e137af149218e2a13f4079d97f99ff6bc4c366171ed47f951e3db127a1 - Sigstore transparency entry: 2211820588
- Sigstore integration time:
-
Permalink:
super-rick/agentcrew-mcn@971f16bd229aeaf916ce6c993b05b9666a21c616 -
Branch / Tag:
refs/tags/v0.5.4 - Owner: https://github.com/super-rick
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@971f16bd229aeaf916ce6c993b05b9666a21c616 -
Trigger Event:
push
-
Statement type:
File details
Details for the file agentcrew_mcn-0.5.4-py3-none-any.whl.
File metadata
- Download URL: agentcrew_mcn-0.5.4-py3-none-any.whl
- Upload date:
- Size: 120.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
16a134078c508d35b8d7e025a034ffa3c68c06b3fdfe290961c9261d2916bc45
|
|
| MD5 |
51c7cc7a6079638d0bf8435682eeabe4
|
|
| BLAKE2b-256 |
a3261bbabd52ee38c6417067d1cbb66e88dd2d8a496b8cbc0cfcbdffb1847a48
|
Provenance
The following attestation bundles were made for agentcrew_mcn-0.5.4-py3-none-any.whl:
Publisher:
publish.yml on super-rick/agentcrew-mcn
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
agentcrew_mcn-0.5.4-py3-none-any.whl -
Subject digest:
16a134078c508d35b8d7e025a034ffa3c68c06b3fdfe290961c9261d2916bc45 - Sigstore transparency entry: 2211820623
- Sigstore integration time:
-
Permalink:
super-rick/agentcrew-mcn@971f16bd229aeaf916ce6c993b05b9666a21c616 -
Branch / Tag:
refs/tags/v0.5.4 - Owner: https://github.com/super-rick
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@971f16bd229aeaf916ce6c993b05b9666a21c616 -
Trigger Event:
push
-
Statement type: