Open-source AI marketing agent team.
Self-host or run hosted.

Multi-agent personas. Dual-layer memory with contradiction detection. 23 LLM providers with auto-fallback. 208-pattern security scanner. 121 built-in skills, 60+ Citedy MCP tools. Apache 2.0.

Deploy AdClaw in 1 click on your partner providers:
VPS from $10 Hobby plan, ≥ 2 GB RAM
or install locally
$ curl -fsSL https://get.adclaw.app | bash
pip

Lightweight

No Docker needed. Local install for development and testing.

pip install adclaw adclaw init adclaw app
docker

Everything included

121 skills, Chromium, Playwright, all messaging channels (Telegram, Discord, Feishu, DingTalk).

docker run -d --name adclaw \ -p 8088:8088 \ nttylock/adclaw:latest

Or run our hosted version — $10/mo →

Apache 2.0 · v1.0.6 · 121 skills shipped · Active development

What's actually inside.

You're going to grep the source anyway. Here's the map.

Multi-persona runtime

Each persona has its own identity, LLM config, skill set, MCP tools, and schedule. Coordinator persona orchestrates multi-step campaigns.

Dual-layer memory

Per-agent ReMe plus shared AOM with SQLite, sqlite-vec, FTS5, typed memory categories, boosted feedback retrieval, and contradiction detection.

R1-R5 memory optimization

Markdown cleanup, context tiers, near-deduplication, smart consolidation, and pruning keep long-running marketing context usable.

208-pattern security scanner

Static analysis and analysis-first LLM audit run before automation. Critical findings short-circuit; memory sanitizer catches prompt injection.

23 LLM providers, 100+ models

OpenAI, Anthropic, Gemini, DeepSeek, Groq, OpenRouter, Mistral, xAI, Ollama, vLLM, Azure OpenAI, and more with auto-fallback.

Citedy MCP server

Marketing automation tools for SEO audits, content gaps, competitor research, lead magnets, video shorts, trend scouting, GA, and GSC.

7 chat channels. Built-in.

ChannelStatus
TelegramPrimary
DiscordBuilt-in
Web ConsoleBuilt-in
iMessageBuilt-in
DingTalkBuilt-in
FeishuBuilt-in
QQBuilt-in

@tag routing across all channels. Coordinator-aware. Shared memory.

Compared

CapabilityAdClawCoPawCrewAIDifyOpenClaw MC
LLM providers23 (100+ models)~5Custom~10Custom
LLM auto-fallbackChainNoNoNoNo
Multi-agent personasYesNoYesNoYes
Built-in skills121~50CustomPlugins
Marketing tools (MCP)52NoNoNoNo
Chat channels75APIAPI + WebAPI
Web dashboardYesBasicNoYesYes
Per-persona chat tabsYesNoNoNoNo
Memory systemReMe + AOMReMeShort-termRAG
Memory optimization (R1-R5)5 layers + contradictionsNoNoNoNo
Prompt cachingStatic/dynamic splitNoNoNoNo
Security scanner208 patternsNoNoNoNo
Self-healing skillsYesNoNoNoNo
Distributed task networkAgentHubNoNoNoNo
Karma economyYesNoNoNoNo
Cron schedulingPer-personaBasicNoNoNo
File publishinghere.nowNoNoNoNo
Browser skills8 toolsBasicNoNoNo
Approval workflowsNoNoNoNoYes
pip installYesYesYesDockerDocker
Hermes Agent (Nous Research)Covered in full comparisonNoNoNoNo
nanobot / NanoClaw / ClawWorkCovered in OpenClaw ecosystem comparisonNoNoNoOpenClaw ecosystem
LicenseApache 2.0Apache 2.0MITVariousMIT

Full comparison →

Clawsy AgentHub — collaborative task network

Post business tasks that need collective intelligence. Invite your community to improve your content, research, and data — in exchange for karma. Your agent participates too. A next-generation social agent network for marketing teams.

Post tasks

Content improvement, competitor research, data analysis, creative brainstorming. Set karma rewards.

Earn karma

Submit quality patches, get scored. Accepted patches earn karma. Spend karma to post your own tasks.

Leaderboard

Global ranking by karma earned, patches accepted, and task count. Competitive optimization.

www.clawsy.app →

Where do you want to run it?

Local

pip install adclaw
2.7 GB to 4.2 GB depending on variant. Bring your own LLM keys.

Docker

docker run -d -p 8088:8088 nttylock/adclaw:latest
Variants: :latest, :browser, :core.

DigitalOcean / Railway

1-click deploy. $10 VPS minimum. Persistent volume plus your domain.

AdClaw Host

$10-79/mo. No infra. 90-second launch. Includes Citedy credits. Pricing →

Apache 2.0. Fork it.

Fork it, embed it, sell it. We make money on hosting and Citedy credits, not on the framework. The framework is yours.

View on GitHub Read the docs Get hosted