Stars
Forks
Watchers
Developer links
Botpress
Build, deploy, and monitor chatbots and LLM-powered agents on one open-source conversational AI platform: Botpress. Its Studio is a visual development environment: a drag-and-drop canvas arranges conversation logic with nodes for messages, questions, choices, and actions, while a built-in emulator simulates conversations for debugging before anything goes live. Agents ground their answers in a knowledge base assembled from uploaded documents, ingested websites, and past conversations via retrieval-augmented generation, and the LLM layer connects to multiple model providers - GPT-4, Claude, Mistral - with a configurable model strategy. An autonomous engine handles reasoning, tool orchestration, persistent memory across sessions, and sandboxed code execution, and custom code actions in TypeScript extend agents past prebuilt workflows. Over 100 integrations deploy the same bot to WhatsApp, Telegram, Slack, Microsoft Teams, and web chat, and connect it to HubSpot, Zendesk, Zapier, and arbitrary APIs and webhooks. Human handoff, conversation analytics, and quality monitoring cover production operation. Originating in 2017 from a Montreal team, the community edition is developed openly on GitHub.
Benefits
- Enterprise-Grade Bots Without Enterprise Budgets
- LLM-powered conversation, RAG, and autonomous behaviors that enterprise chatbot vendors gate behind sales calls, available open-source and self-hostable.
- Answers Grounded in Your Content
- Retrieval-augmented generation over uploaded files and ingested websites keeps responses accurate to your documentation instead of hallucinated.
- Build Once, Deploy Everywhere
- The same agent serves WhatsApp, Telegram, Slack, Teams, and embedded web chat, so channel coverage does not multiply build effort.
- Deflect Tickets, Keep the Escape Hatch
- Agents resolve routine support and lead-qualification traffic autonomously, with human handoff built in for conversations that need a person.
Features
- Visual Agent Studio
- Drag-and-drop canvas for conversation logic with message, question, choice, and action nodes, plus an instant conversation emulator for testing.
- RAG Knowledge Bases
- Ground agents in uploaded documents, ingested websites, and prior conversations for accurate, cited answers.
- Multi-LLM Strategy
- Connect GPT-4, Claude, Mistral, and other models, and configure which model handles which task.
- Autonomous Engine
- LLM reasoning with tool orchestration, persistent cross-session memory, and sandboxed code execution.
- 100+ Integrations
- WhatsApp, Telegram, Slack, Teams, HubSpot, Zendesk, Zapier, Make, plus custom APIs and webhooks.
- Custom Code and Analytics
- TypeScript code actions for bespoke logic, with conversation analytics and quality monitoring in production.