n8n-claw — Self-Hosted AI Agent

A fully self-hosted AI agent built on n8n + PostgreSQL + Claude. Talks to you via Telegram or HTTP API (Slack, Teams, custom apps), builds its own MCP tools, manages reminders and memory — all running on your own infrastructure.

Short Introduction

https://github.com/user-attachments/assets/10b7b93d-f482-47c1-a144-80a1b9d1be16

Contents

What it does

Talk to your agent in natural language — it manages tasks, remembers context across conversations, builds API integrations, and proactively keeps you on track.

  • Telegram chat — talk to your AI agent directly via Telegram
  • Webhook API — call the agent from any external system via HTTP (Slack, Teams, Paperclip, custom apps)
  • Enriched long-term memory — hybrid search (semantic + full-text + entity match, fused via RRF) with time decay, tags, entity tracking, source attribution, and category-based auto-expiry. Finds people by name, survives embedding API outages, naturally prefers recent context.
  • Knowledge graph — automatically tracks people, companies, products, and events; multi-hop graph traversal reveals how everything connects
  • Task management — create, track, and complete tasks with priorities and due dates
  • Proactive heartbeat — automatically reminds you of overdue/urgent tasks
  • Recurring actions — repeating tasks on any schedule ("check my emails every 15 minutes", "daily briefing at 8am")
  • Smart background checks — monitoring tasks only notify you when something new is found
  • Failure awareness — workflow errors are logged to memory and pushed to Telegram. Just ask "did anything fail today?" or "what was the error in the last background check?" and the agent explains in plain language — no more digging through n8n execution logs
  • Expert agents — delegate complex tasks to specialized sub-agents (3 included, 100+ available from agent catalog across 12 categories)
  • MCP Skills — install pre-built skills or build new API integrations on demand
  • Smart reminders — timed Telegram reminders ("remind me in 2 hours to...")
  • Scheduled actions — the agent executes instructions at a set time ("search HN for AI news at 9am")
  • Web search — searches the web via built-in SearXNG instance (no API key needed)
  • Web reader — reads webpages as clean markdown via Crawl4AI (JS rendering, no boilerplate)
  • Browser automation — drives a real Chromium via Browser Use to perform agentic actions on websites: newsletter signups, contact forms, click flows, login-gated content. Sessions are pooled per domain so the agent stays logged in across calls (in-memory, lost on restart). Supports interactive 2FA: agent stops at the 2FA prompt, asks you for the code via Telegram, you reply with the TOTP code, agent enters it on the same live page and completes the login.
  • File passthrough — stores documents and photos from Telegram so Skills can use the originals (upload to Lexware, save to Nextcloud, etc.). Can also download files from the internet or cloud services and send them back to the chat.
  • Project memory — persistent markdown documents for tracking ongoing work across conversations
  • OpenClaw integration — delegate coding tasks to an autonomous AI agent that can build websites, apps, and run shell commands
  • Extensible — add new skills and capabilities through natural language or from the skill catalog

Architecture

Telegram  ───────────────────────────────────┐
Webhook API (POST /webhook/agent)  ───────┐
  │                                     │
  └─────────────────▼─────────────────────┘
n8n-claw Agent (Claude Sonnet)
  ├── Task Manager        — create, track, complete tasks
  ├── Project Manager     — persistent project notes (markdown)
  ├── Memory              — save, search, update, delete long-term memories
  ├── Knowledge Graph     — track entities and relationships automatically
  ├── MCP Client          → calls tools on MCP skill servers
  ├── Library Manager     → install/remove skills from catalog
  ├── MCP Builder          → builds custom skills from scratch
  ├── Reminder            — timed reminders + scheduled actions
  ├── Expert Agent        → delegates to specialized sub-agents
  ├── Agent Library       → install/remove expert agents from catalog
  ├── Telegram Status     — sends progress updates during long tasks
  ├── HTTP Tool           — simple web requests
  ├── Web Search          — search the web (SearXNG)
  ├── Web Reader          — read webpages as markdown (Crawl4AI)
  └── Self Modify         — inspect/list n8n workflows
  │
  ├── Webhook caller? → JSON response to HTTP caller
  └── Telegram?      → Telegram Reply

Webhook Adapter (optional, connects external systems):
  💬 Slack Trigger     ──┐
  💬 Teams Trigger     ──┤
  🌐 Generic Webhook   ──┼── Map Input → POST /webhook/agent → Route Response
  🛠️ Custom Webhook    ──┘   (Set node — easy to customize, no code)

Background Workflows (automated):
  💓 Heartbeat              — every 5 min: recurring actions + proactive reminders + file cleanup
  🔍 Background Checker     — silent checks: only notifies when something new is found
  🧠 Memory Consolidation   — daily at 3am: summarizes conversations → long-term memory
  ⏰ Reminder Runner         — every 1 min: sends due reminders + triggers one-time actions
  🚨 Error Notification     — catches workflow failures: Telegram alert + logs to memory_long

Internal Services:
  📁 File Bridge            — temporary binary storage (documents, photos) for tool passthrough
  📧 Email Bridge           — IMAP/SMTP REST API for email integration

Installation

Want to run locally instead of on a VPS? See the Local Setup Guide for Docker + ngrok instructions (contributed by @salvodmt, tested on Debian 13).

What you need

  • A Linux VPS (Ubuntu 22.04/24.04 recommended, also tested with Debian 13, 4GB RAM and 15GB Disk minimum)
  • A Telegram Bot Token — open @BotFather in Telegram, send /newbot, follow the prompts, and copy the token it gives you
  • Your Telegram Chat ID — send any message to @userinfobot and it replies with your numeric ID
  • An LLM API Key — setup lets you choose your provider:
  • A domain name (required for Telegram HTTPS webhooks). No domain? You can use sslip.io — it turns your IP into a domain automatically (e.g. your server has IP 123.45.67.89, type 123-45-67-89.sslip.io), no DNS setup needed

Step 1 — Clone & run

git clone https://github.com/freddy-schuetz/n8n-claw.git && cd n8n-claw && ./setup.sh

The script installs everything automatically. It will ask you for:

  • n8n API Key — generated in the n8n UI that opens during setup (Settings → API)
  • Telegram Bot Token + Chat ID
  • LLM API Key — choose your provider (Anthropic, OpenAI, OpenRouter, DeepSeek, Gemini, Mistral, Ollama, or OpenAI-compatible)
  • Domain name (enables HTTPS via Let's Encrypt. Use sslip.io if you don't have one)
  • Agent personality — name, language, communication style, custom persona

After that, setup handles everything else: Docker, database, credentials, workflows, activation.

Setup also asks about two optional features (you can skip both):

  • Embeddings — enables semantic memory search (find memories by meaning, not just keywords). Supports OpenAI, Voyage AI, or Ollama. Without it, memory still works via keyword search.
  • Voice messages — requires an OpenAI API key for Whisper transcription. If you already chose OpenAI for embeddings, the same key is reused. Without it, voice messages won't work — but photos, documents, and locations work fine.

Step 2 — Start chatting

All credentials are created and connected automatically by setup. Send a message to your Telegram bot — it's ready!

Webhook API — you can also interact with the agent via HTTP (for Slack, Teams, or custom apps):

curl -X POST https://YOUR-DOMAIN/webhook/agent \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_WEBHOOK_SECRET" \
  -d '{"message": "Hello!", "user_id": "test-user"}'

The WEBHOOK_SECRET is shown at the end of setup output (also in .env).

Optional: extra workflows

The core agent and all background workflows are activated automatically. These optional workflows can be activated in the n8n UI if you need them:

Workflow Purpose
MCP Builder Builds custom MCP skills on demand
MCP: Weather Example skill — weather via Open-Meteo (no API key needed)
WorkflowBuilder Builds general n8n automations (requires extra setup)

Secure your Telegram bot

By default, your Telegram bot accepts messages from anyone who finds it. To restrict it to your chat only:

  1. Open the n8n-claw Agent workflow in n8n
  2. Click the Telegram Trigger node
  3. Under Additional Fields, add Allowed Chat IDs
  4. Enter your Telegram Chat ID (the one from setup)
  5. Save the workflow

This ensures only you can talk to your agent. Without this, anyone on Telegram could message your bot and access the agent's capabilities.

Services & URLs

After setup, these services run:

Service URL Purpose
n8n http://YOUR-IP:5678 Workflow editor
Supabase Studio http://localhost:3001 (via SSH tunnel) Database admin UI
Webhook API https://YOUR-DOMAIN/webhook/agent Agent HTTP endpoint (POST, requires X-API-Key header)
Webhook Adapter https://YOUR-DOMAIN/webhook/adapter Multi-system adapter endpoint (POST)
Custom Webhook https://YOUR-DOMAIN/webhook/custom Easy-to-customize adapter (Set node, no code)
SearXNG http://localhost:8888 (Docker-internal) Self-hosted web search engine
Crawl4AI Docker-internal only Web reader — JS rendering to clean markdown
Email Bridge http://localhost:3100 (Docker-internal) IMAP/SMTP email REST API (for Email skill)
File Bridge http://localhost:3200 (Docker-internal) Temporary file storage for binary passthrough between tools
PostgREST API http://kong:8000 (Docker-internal only) REST API for PostgreSQL

Accessing Supabase Studio

Supabase Studio is bound to localhost only (not publicly exposed). To access it from your browser, open an SSH tunnel:

ssh -L 3001:localhost:3001 user@YOUR-VPS-IP

Then open http://localhost:3001 in your browser. The tunnel stays open as long as the SSH session runs.

Connect Claude Desktop, ChatGPT, Claude Code, Lovable & Cursor

n8n-claw can be used directly from Claude Desktop, ChatGPT, Claude Code, Lovable, Cursor, and other MCP-compatible tools — using n8n's built-in Instance-Level MCP Server. No extra workflows or code needed.

Once connected, your MCP client can chat with the agent (with full access to memory, web search, skills, reminders, and Telegram), trigger other workflows, and even create new ones.

Setup

1. Enable Instance-Level MCP in n8n

Navigate to Settings (gear icon) > Instance-level MCP and toggle Enable MCP access.

2. Expose the agent workflow

Click Enable workflows, select the n8n-claw Agent workflow, then click Enable. Add a good description to help MCP clients understand what the workflow does.

3. Connect your MCP client

  1. On the Instance-level MCP page, click Connection details and copy the OAuth URL
  2. In Claude Desktop, go to File > Settings > Connectors > Add custom connector
  3. Enter a name (e.g. your agent's name) and paste the OAuth URL, then click Add
  4. In the connectors overview, click Connect and authorize in the browser window that opens

That's it — Claude Desktop can now discover and use your agent.

  1. In ChatGPT, go to Settings > Apps > Advanced settings and enable Developer mode
  2. Go back and click Create new app
  3. Enter a name (e.g. your agent's name), paste your n8n MCP URL https://<your-n8n-domain>/mcp-server/http, select OAuth, accept the risk warning, and click Create

On the Instance-level MCP page, click Connection details > Access Token tab. Copy your token immediately — it will be masked on future visits.

claude mcp add --transport http n8n-claw https://<your-n8n-domain>/mcp-server/http \
  --header "Authorization: Bearer <YOUR_TOKEN>"

Or add to your .mcp.json:

{
  "mcpServers": {
    "n8n-claw": {
      "type": "http",
      "url": "https://<your-n8n-domain>/mcp-server/http",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}
  1. In Lovable, go to Settings > Connectors > Personal connectors and click New MCP server
  2. Enter a name (e.g. your agent's name), paste your n8n MCP URL https://<your-n8n-domain>/mcp-server/http, and select OAuth as authentication
  3. Click Add & authorize and confirm in the browser

Use the OAuth URL from Connection details if your client supports OAuth, or the Access Token with the HTTP endpoint https://<your-n8n-domain>/mcp-server/http. Refer to your client's MCP documentation for the exact configuration format.

Triggering the agent

MCP clients can discover and execute the agent workflow automatically. When triggered, the agent runs its full pipeline — personality, memory, conversation history, AI reasoning with all tools — and returns the response.

Conversations are isolated per source and session, so MCP usage won't interfere with Telegram chats.

Limitations

  • 5-minute timeout — MCP-triggered executions have a hard 5-minute limit
  • Text only — binary inputs (images, files) are not supported via MCP
  • No client scoping — all connected MCP clients see the same exposed workflows

Requires n8n v2.2+. Workflow creation/editing requires v2.13+. See n8n MCP docs for details.

Webhook API & External Integrations

n8n-claw exposes an HTTP API so external systems can talk to the agent — no Telegram required.

Direct Webhook API

Any system that can make HTTP requests can call the agent directly:

POST {{N8N_URL}}/webhook/agent
Header: X-API-Key: {{WEBHOOK_SECRET}}
Content-Type: application/json

{
  "message": "What is the weather in Berlin?",
  "user_id": "my-app-user-123",
  "session_id": "my-app:conv-456",
  "source": "my-app",
  "metadata": { "any": "data you want back" }
}

Response (200):

{
  "success": true,
  "response": "The weather in Berlin is...",
  "session_id": "my-app:conv-456",
  "source": "my-app",
  "metadata": { "any": "data you want back" }
}
Field Required Default Description
message yes — The user's message
user_id yes — Unique user identifier
session_id no api:{user_id} Conversation session ID (for history)
source no api Source identifier (appears in logs)
metadata no {} Arbitrary data — round-trips back in the response

The agent uses session_id and user_id (with source prefix) for conversation history and user profiles — same as Telegram, just with different prefixes.

Webhook Adapter (Slack, Teams, Discord, Paperclip)

For systems that need input/output mapping (different message formats, response routing), use the Webhook Adapter workflow. It translates between external formats and the agent's webhook API.

The adapter ships with these input paths:

Trigger Endpoint Default state Use case
Generic Webhook /webhook/adapter Active Paperclip, Discord bridge, API power-users (Code node with fallback chains)
Custom Webhook /webhook/custom Active Your own apps — simple Set node, easy to customize without code
Slack Trigger — Disabled Slack workspace integration
Teams Trigger — Disabled Microsoft Teams integration
Discord /webhook/adapter (via bot sidecar) Opt-in Discord servers — enabled via setup.sh prompt, uses the discord-bridge container

Each trigger has a mapper node that normalizes messages → calls /webhook/agent → routes the response back to the right system via metadata._responseChannel. Paperclip payloads are auto-detected and get a dedicated response branch that posts the agent's answer as a comment and marks the issue as done.

Enabling Slack

  1. Create a Slack App at api.slack.com/apps
  2. Add Bot Token Scopes under OAuth & Permissions: chat:write, channels:history, channels:read
  3. Install to workspace and copy the Bot Token (xoxb-...)
  4. In n8n: Create a Slack API credential (Bot Token + Signing Secret)
  5. Enable the Slack Trigger + Slack Reply nodes in the Webhook Adapter workflow
  6. Activate the Webhook Adapter workflow
  7. In Slack App settings: Add the Slack Trigger's webhook URL under Event Subscriptions
  8. Subscribe to bot events: message.channels (public channels), message.im (direct messages)
  9. Invite the bot to your Slack channel (/invite @YourBotName)

The Slack Trigger webhook URL changes when the adapter workflow is re-created (e.g. setup.sh --force). Update the Event Subscriptions URL in your Slack App after each reinstall.

Enabling Teams

  1. Register a Bot in Azure Portal (Bot Framework)
  2. Create App ID + Client Secret
  3. Set Messaging Endpoint to the Teams Trigger's webhook URL
  4. In n8n: Create a Microsoft Teams OAuth2 credential
  5. Enable the Teams Trigger + Teams Reply nodes in the Webhook Adapter workflow
  6. Activate the Webhook Adapter workflow

Enabling Discord

Unlike Slack and Teams, n8n does not ship a native Discord trigger. n8n-claw solves this with a small sidecar container (discord-bridge) that connects to Discord's Gateway as a bot and forwards messages to the adapter. The container is optional — it is only built and started if you enable Discord during setup.

  1. Create a Discord Application at discord.com/developers/applications
  2. Add a Bot, enable Message Content Intent under Bot settings
  3. Copy the Bot Token
  4. Invite the Bot to your server with bot + applications.commands scopes
  5. Run ./setup.sh (or ./setup.sh --force on an existing install) — when asked "Enable Discord as an additional chat interface?" answer y and paste the token
  6. Activate the Webhook Adapter workflow in n8n

That's it. No Discord credential in n8n itself — the bot token lives only inside the sidecar container, set via DISCORD_BOT_TOKEN in .env. The sidecar posts incoming messages to /webhook/adapter and receives replies via an internal POST /reply endpoint, so n8n never talks to Discord's API directly.

Users who do not enable Discord never see the extra container: discord-bridge uses a docker-compose profiles: ["discord"] marker, so it is not built or started unless COMPOSE_PROFILES=discord is set in .env (which setup.sh does for you).

Enabling Paperclip

Paperclip is an open-source agent orchestration platform. n8n-claw works as a Paperclip agent out of the box — no extra configuration in n8n needed.

The adapter auto-detects Paperclip's payload format (runId + context), fetches the issue title and description via the Paperclip API, and after the agent responds:

  • Posts the response as a comment on the Paperclip issue
  • Sets the issue status to done

Setup in Paperclip:

  1. Deploy Paperclip on the same server or network as n8n-claw
  2. Create a Company and an Agent with http adapter type
  3. Configure the agent's HTTP adapter: 
    {
  "url": "https://YOUR-DOMAIN/webhook/adapter",
  "method": "POST",
  "headers": {
    "X-API-Key": "YOUR_WEBHOOK_SECRET"
  },
  "payloadTemplate": {
    "source": "paperclip"
  }
}
  4. Generate an Agent API Key in Paperclip (used by n8n-claw to post comments back)
  5. Add placeholders to .env (or hardcode in the workflow):
    • PAPERCLIP_INTERNAL_URL — Paperclip's internal URL (e.g. http://paperclip:3100 if on same Docker network)
    • PAPERCLIP_AGENT_KEY — the agent API key from step 4
  6. Create an issue in Paperclip and assign it to the agent — the heartbeat will trigger the workflow automatically

Docker networking: If Paperclip runs on the same server, connect it to n8n-claw's Docker network (n8n-claw_n8n-claw-net) and use the container DNS name (paperclip:3100) instead of localhost.

Adding a Custom Integration

Easiest way — use the Custom Webhook (no code):

  1. Open the Map Custom Input Set node in the Webhook Adapter workflow
  2. Adjust the field mappings to match your app's JSON structure:
    • message → the field containing the user's text (e.g. $json.body.text)
    • user_id → the sender identifier (e.g. $json.body.username)
    • session_id → unique conversation ID
    • source → your app's name
  3. Send a POST to /webhook/custom with X-API-Key header

Advanced — add a new trigger (for systems with custom response routing):

  1. Add a new Trigger node in the Webhook Adapter workflow
  2. Add a new Map node (Code node) that outputs: { message, user_id, session_id, source, metadata: { _responseChannel: "your-system" } }
  3. Add a matching output in the Route Response switch node
  4. Add a Reply node for your system

The _responseChannel value in metadata tells the adapter where to route the agent's response.

MCP Skills Library

43 pre-built skills available from the skill catalog — install with a single chat command, no coding required.

"What skills are available?" "Install weather-openmeteo" "Remove weather-openmeteo"

The Library Manager fetches skill templates from GitHub, imports the workflows into n8n, and registers the new MCP server automatically.

Skills come in two flavors:

  • Native — n8n wraps a REST API as an MCP server (default pattern, most skills).
  • Bridge — registers an existing external MCP server (e.g. DeepWiki, Zapier, a self-hosted Claude Code MCP) directly into the agent by URL + optional bearer/header auth. No workflows imported, no wrapper code. Supported since v1.3.0. See the Bridge Templates guide.
Category Examples
Analytics Google Analytics
Communication Gmail, Email (IMAP/SMTP), OpenClaw
Creativity Google Media Generation (Nano Banana Pro, Veo 3.1)
Entertainment TMDB Movies, Recipes, Trivia
Finance KontoFlux (Open Banking), Exchange Rates, Crypto Prices
Knowledge Wikipedia, OpenFoodFacts, OpenWebUI Knowledge
Language DeepL Translate, Dictionary
Marketing Google Ads
Meetings Vexa Meetings
Network Website Check, IP Geolocation
News Hacker News, NewsAPI
Productivity Todoist, Notion, GitHub, Google Calendar, Google Drive, Nextcloud Files, Seafile, CalDAV, Vikunja, NocoDB CRM
Reference Country Info, Public Holidays, Timezone / World Clock
Transport Deutsche Bahn, Route Planner, Wiener Linien
Utilities PDF Tools, QR Code

See the full catalog at n8n-claw-templates.

Skills with API keys: Some skills require an API key (e.g. NewsAPI). When you install one, the agent sends you a secure one-time link via Telegram. Click it, enter your key — done. The key is stored in the database and the skill reads it at runtime. Links expire after 10 minutes and can only be used once.

"Install news-newsapi" → Agent sends a link to enter your NewsAPI key → Enter key in the form → skill works immediately

You can also regenerate a credential link later:

"Add credential for news-newsapi"

Want to create your own skills? See the template contribution guide.

Security notice — Skill credentials are stored in plain text

API keys entered via the credential form are currently stored unencrypted in the template_credentials table in PostgreSQL. This means:

  • Anyone with access to the database can read all stored API keys
  • Supabase Studio (localhost:3001, accessible via SSH tunnel) shows credentials in plain text
  • A compromised VPS exposes all stored API keys

What an attacker would need: Neither the database nor the API are reachable from the internet. PostgREST runs on a Docker-internal network only, and PostgreSQL (port 5432) is bound to 127.0.0.1. To read credentials, an attacker would need SSH access to your VPS — there is no remote network path.

Mitigation: Secure SSH access (key-based auth, no root password, fail2ban), and use API keys with minimal permissions where possible.

Encryption at rest for skill credentials is planned and in progress.

Google Services (OAuth2)

Google Skills (Gmail, Google Calendar, Google Analytics, Google Ads) use OAuth2 for authentication — the agent handles the entire flow via Telegram, no n8n UI needed.

All Google skills share a single set of OAuth credentials (client_id / client_secret). You set them up once, and every additional Google skill reuses them automatically. If a new skill needs extra permissions, the agent generates a new consent link with the expanded scopes.

Setup

  1. Google Cloud Console — console.cloud.google.com

    • Create a project (or use an existing one)
    • Enable the APIs you need: Gmail API, Google Calendar API, Google Analytics Data API, Google Ads API
    • Go to APIs & Services → OAuth consent screen:
      • User Type: External (or Internal for Google Workspace)
      • Add your email as a Test User
    • Go to APIs & Services → Credentials → Create Credentials → OAuth Client ID:
      • Type: Web application
      • Authorized redirect URI: https://YOUR-N8N-DOMAIN/webhook/oauth-callback
      • Copy the Client ID and Client Secret

  2. Install a Google skill — ask your agent:

    "Install the Gmail skill"

  3. Enter credentials — the agent sends two secure form links (Client ID + Client Secret). Click each, paste the value, submit.

  4. Authorize — the agent generates a Google consent link. Click it, sign in with your Google account, grant permissions. The browser shows "Authorization successful" and the agent confirms via Telegram.

  5. Done — the skill is ready to use.

Available Google Skills

Skill Tools Scopes
Gmail search, read, send, create draft, list labels gmail.readonly, gmail.modify, gmail.send
Google Calendar list/create/update/delete events, list calendars calendar, calendar.readonly
Google Analytics run reports, list properties, realtime data analytics.readonly
Google Ads (Beta) list campaigns, ad groups, stats, performance adwords

Google Ads requires an additional Developer Token and Customer ID (entered via separate credential forms).

Scope Expansion

When you install a second Google skill (e.g. Calendar after Gmail), the agent checks if the existing token already covers the required scopes. If not, it generates a new consent link that requests all scopes at once (existing + new). Your previously stored refresh token is replaced with one that covers all permissions.

Important Notes

  • Testing mode: Google OAuth apps in "Testing" status have refresh tokens that expire after 7 days. For permanent use, publish the app as "Internal" (Google Workspace) — no verification needed.
  • Token refresh: Access tokens are refreshed automatically (5-minute buffer before expiry).
  • Shared credentials: All Google skills share the same client_id, client_secret, and tokens under the google-oauth namespace. You only authenticate once.

Expert Agents

Delegate complex tasks to specialized sub-agents. Each expert has its own AI agent with a focused persona, tools (web search, HTTP requests, web reader, MCP), and works independently — then the main agent rephrases the result in its own tone.

Three experts are included by default:

Agent Speciality
Research Expert Web research, fact-checking, source evaluation, structured summaries
Content Creator Copywriting, social media posts, blog articles, marketing copy
Data Analyst Data analysis, pattern recognition, KPI interpretation, structured reports

Using expert agents:

"Research the best hiking trails in Tyrol with sources" "Write an Instagram post about our new product launch" "Analyze these numbers and give me a summary"

The agent automatically picks the right expert based on your request — or you can ask explicitly:

"Let the research expert look into this" "Delegate this to the content creator"

Managing agents:

"What expert agents do I have?" "Install the data analyst" "Remove the content creator"

Install more experts from the agent catalog or ask the community to contribute new ones.

100+ more experts available from the agent catalog across 12 categories: Analytics, Communications, Creative, Development, Education, HR, Leisure, Marketing, Operations, Product, Research, and Sales.

Many agents pair with MCP Skills for enhanced capabilities — for example, the Data Analyst works with Google Analytics, or the Code Reviewer integrates with GitHub.

Status updates: During long-running expert tasks, the agent sends you Telegram progress updates so you know what's happening (e.g. "Starting research expert...").

OpenClaw Integration

Connect n8n-claw to an OpenClaw instance and unlock a completely new class of capabilities. OpenClaw is an autonomous AI agent with full access to a Linux system — it can write code, build websites, deploy applications, manage files, run shell commands, and work on complex multi-step software projects.

With the OpenClaw skill installed, n8n-claw can delegate tasks to OpenClaw and get the results back:

"Ask OpenClaw to build a landing page for our new product" "Let OpenClaw create a Python script that monitors our server uptime" "Send this to OpenClaw: refactor the auth module and write tests"

How it works:

  • n8n-claw sends messages to OpenClaw's Gateway API (OpenAI-compatible)
  • Conversations are persistent — OpenClaw remembers context across messages via session keys
  • n8n-claw identifies itself with a configurable caller ID so OpenClaw knows who's talking

Setup:

  1. Install the OpenClaw skill: "Install openclaw"
  2. Enter your credentials via the secure form:
    • Gateway URL — http://<your-openclaw-ip>:18789. To find the port, run on the OpenClaw server: 
      grep -A2 'gateway:' ~/openclaw/config.yaml | grep port
    • API Token — run on the OpenClaw server: 
      grep -A2 'gateway:' ~/openclaw/config.yaml | grep api_key
    • Caller ID — a name that identifies your n8n-claw instance (e.g. "Greg (n8n-claw)")
  3. Make sure OpenClaw's gateway is reachable from your n8n-claw server. Check the bind setting: 
    grep -A2 'gateway:' ~/openclaw/config.yaml | grep bind
    If it says "loopback", change it to "lan" and restart OpenClaw: 
    nano ~/openclaw/config.yaml   # change bind: "loopback" → bind: "lan"
  4. Start delegating tasks

This turns n8n-claw from a workflow-based agent into a bridge to a full autonomous coding agent — combining n8n-claw's strengths (memory, reminders, task management, Telegram interface, MCP skills) with OpenClaw's ability to execute arbitrary code and build software.

Building custom MCP Skills

For APIs not covered by the skill catalog, ask your agent to build one from scratch:

"Build me an MCP server for the OpenLibrary API — look up books by ISBN"

The MCP Builder will:

  1. Search for API documentation automatically (via SearXNG + Crawl4AI)
  2. Generate working tool code
  3. Deploy two new n8n workflows (MCP trigger + sub-workflow)
  4. Register the server in the database
  5. Update the agent so it knows about the new tool

Memory

The agent has a multi-layered memory system — it remembers things you tell it and learns from your conversations over time.

Automatic memory: The agent decides on its own what's worth remembering from your conversations (preferences, facts about you, decisions). No action needed.

Manual memory: You can also explicitly ask it to remember something:

"Remember that I prefer morning meetings before 10am" "Remember that I take my coffee black"

Memory search: When relevant, the agent searches its memory to give you contextual answers. It uses hybrid search — three independent search strategies fused via Reciprocal Rank Fusion (RRF):

  • Semantic search — finds memories by meaning using vector embeddings (requires an embedding API key, configured during setup)
  • Full-text search — matches exact words with accent/umlaut normalization (München matches muenchen)
  • Entity match — boosts memories linked to the person, company, or project you're asking about

If the embedding API is temporarily unavailable, the agent gracefully falls back to full-text + entity search — no silent failures.

Time decay gives recent memories a natural edge. Old memories aren't deleted, but newer ones rank higher when competing for the same query. Category exemptions ensure contacts, preferences, and decisions never decay.

"What do you know about my coffee preferences?" "What did we discuss about the server migration?"

Memory update & delete: The agent can correct or remove stored memories — no more contradictory entries piling up:

"Actually, I prefer tea now" — updates the existing coffee preference instead of creating a duplicate "Forget that I like early meetings" — deletes the entry completely

Tags & entity tracking: Every memory is automatically tagged with English lowercase keywords and linked to named entities (people, companies, projects, etc.). This makes filtering and cross-referencing memories much more effective.

Auto-expiry: Memories expire automatically based on their type and importance. Contact info, preferences, and decisions never expire. General memories expire after 90–180 days. This keeps the memory clean without manual maintenance.

Memory Consolidation runs automatically every night at 3am. It summarizes the day's conversations into concise long-term memories with vector embeddings, extracts tags and entity names, and cleans up expired entries. Requires an embedding API key (OpenAI, Voyage AI, or Ollama — configured during setup).

Insights — pattern extraction (v1.5.0): The same nightly run does a second pass that extracts behavior patterns, communication styles, and recurring stressors into category='insight' memories. New patterns get tagged new, reinforced, or contradicted against the last 7 days. Outdated insights are flagged metadata.outdated=true instead of being deleted — temporal validity, not destructive overwrite. The top 3 active insights are silently loaded into the system prompt on every turn so the agent's behavior shapes itself around how you actually work.

Open Loops (v1.5.0): Half-finished thoughts ("ich muss noch X prüfen", "vergiss nicht Y") are captured as category='open_loop' memories. The Heartbeat checks once every 24h for unresolved loops older than 3 days and proactively asks: "A few days ago you wanted to Y — did that happen?" Closed loops keep the original content as audit trail (only metadata.closed=true is added).

Knowledge Graph

The agent automatically builds a knowledge graph of people, companies, projects, events, and their relationships — no explicit commands needed.

Automatic entity tracking: When you mention a person, company, project, or any named entity, the agent silently creates it in the knowledge graph and links it to related entities.

"Stefan Huber is the CEO of destination.one" — creates entities for Stefan Huber (person) and destination.one (company), plus a "manages" relationship

Relationship mapping: The agent tracks how entities relate to each other — who works where, who founded what, which products belong to which company.

Graph traversal: Ask about someone's connections and the agent traverses the graph to show the full network:

"What connections does Stefan Huber have?"

The agent shows all linked entities across multiple hops — companies, co-founders, products, events.

Linked to memory: Entities in the knowledge graph are automatically linked to related memories, giving the agen