DocumentationGitHubTwitterTry PlaygroundOpenMoltOpenMoltThe Programmatic Way to Build AI AgentsOpenMolt lets you build programmatic AI agents in Node.js that think, plan, and act using tools, integrations, and memory — directly from your codebase.Quick StartDocumentationPlayground
Get StartedGet Started in MinutesInstall the package and create your first AI agent with a few lines of code.
Install
$npm install openmolt
Hello World
import OpenMolt from 'openmolt';

const om = new OpenMolt({
  llmProviders: {
    openai: { apiKey: process.env.OPENMOLT_OPENAI_API_KEY },
  },
});

const agent = om.createAgent({
  name: 'Comedian',
  model: 'openai:gpt-4o-mini',
  instructions: 'You are a witty stand-up comedian.',
});

const result = await agent.run('Tell me a joke!');
console.log(result);
CapabilitiesEverything You NeedA complete toolkit for building production-grade autonomous AI agents.🔐Secure by DesignAgents access only the scopes you grant. API credentials never leave your server. The LLM only sees tool names, never raw credentials.🤖Multi-Provider LLMUse OpenAI GPT-4o, Anthropic Claude, or Google Gemini with a unified model string format. Switch providers without changing your code.🔌30+ IntegrationsGmail, Slack, GitHub, Notion, Stripe, Discord, S3 and more — all ready to use out of the box with zero configuration.📋Structured OutputPass a Zod schema and get back a validated, typed object. No more parsing or validating LLM responses manually.📅SchedulingSchedule agents with interval or cron-style daily schedules. Perfect for recurring reports, automated workflows, and monitoring tasks.🔄Event-DrivenHook into every step of the reasoning loop. Observe tool calls, plan updates, LLM outputs, and results in real-time.🧠MemoryLong-term and short-term memory stores with onUpdate callbacks. Agents can learn and remember across runs.🛠️Declarative ToolsDefine integrations as data — endpoint, auth template, and schema. No boilerplate HTTP code required.Integrations30+ Built-in IntegrationsConnect your agents to the tools your business already uses.
NotionNotionFal.aiFal.aiGoogle CalendarGoogle CalendarGmailGmailGoogle DriveGoogle DriveGoogle SheetsGoogle SheetsMicrosoft OutlookMicrosoft OutlookGemini Media ModelsGemini Media ModelsOpenAI Media ModelsOpenAI Media ModelsDiscordDiscordSlackSlackTelegramTelegramWhatsAppWhatsAppXXInstagramInstagramTwilioTwilioAirtableAirtableTikTokTikTokYouTubeYouTubeAmazon S3Amazon S3ShopifyShopifyStripeStripeEtsyEtsyGitHubGitHubDropboxDropboxGoogle AdsGoogle AdsMeta AdsMeta AdsBrowser UseBrowser UseHTTP RequestHTTP RequestNotionNotionFal.aiFal.aiGoogle CalendarGoogle CalendarGmailGmailGoogle DriveGoogle DriveGoogle SheetsGoogle SheetsMicrosoft OutlookMicrosoft OutlookGemini Media ModelsGemini Media ModelsOpenAI Media ModelsOpenAI Media ModelsDiscordDiscordSlackSlackTelegramTelegramWhatsAppWhatsAppXXInstagramInstagramTwilioTwilioAirtableAirtableTikTokTikTokYouTubeYouTubeAmazon S3Amazon S3ShopifyShopifyStripeStripeEtsyEtsyGitHubGitHubDropboxDropboxGoogle AdsGoogle AdsMeta AdsMeta AdsBrowser UseBrowser UseHTTP RequestHTTP Request
Why OpenMoltBuilt for ProductionDesigned with security, flexibility, and reliability at the core.🔒

Zero-Trust Security

OpenMolt uses a scope-based permission model. Your API credentials are stored server-side and rendered into HTTP requests via Liquid templates — the LLM only receives the results of tool calls, never your raw API keys or tokens. Grant only the scopes each agent needs.

⚙️

Fully Configurable Agents

Every aspect of an agent is configurable: instructions (or load from a file), model provider, model config (temperature, thinking mode, token limits), output schema, max steps, and per-integration scope restrictions. Build exactly the agent you need.

💾

Persistent Memory

Agents maintain long-term and short-term memory stores. Provide an onUpdate callback to persist memory to a database or file. Agents can update their memory mid-run and carry context across multiple sessions.

Scheduling & Automation

Schedule agents to run on an interval (e.g., every 20 minutes) or on a cron-style daily schedule with timezone support. Perfect for daily reports, monitoring, automated content publishing, and more.

Use CasesWhat Will You Build?From automation to content pipelines — agents that fit your workflow.Scheduling

Daily Reporting

Schedule a Gemini agent to pull metrics from Stripe every morning, generate a summary, and post it to your Slack channel — automatically.

Multi-step

Content Pipeline

Describe your content strategy in natural language. An agent writes the blog post, generates images with DALL-E, and saves everything to disk.

Gmail

Email Management

Automatically draft replies to incoming emails based on your guidelines. Review drafts in Gmail before sending — no more starting from scratch.

Dev Tools

GitHub Automation

Triage issues, auto-label PRs, post release notes to Slack, and generate changelogs — all triggered by your existing CI/CD pipeline.

Commerce

E-Commerce Ops

Monitor Shopify orders, update inventory in Airtable, send order confirmations via Twilio, and report daily revenue to a Notion dashboard.

Analytics

Customer Research

Scrape product pages with browser-use, analyze competitors with web search, compile findings into a structured Notion database.