Open-source, inspectable framework for building an AI Agent Twin that distills your knowledge, memories and decisions into a grounded personal assistant.
SenteLabsAI/OpenExecutive
Self-hosted AI executive team: one executive persona backed by specialist agents for strategy, finance, HR, legal, ops, marketing, product and sales, built on Claude.
- Stars
- 5,754
- Forks
- 624
- Open issues
- 9
- Last commit
- 6 hours ago
What is it?
Open Executive is a self-hosted AI assistant for founders and managers that answers business questions with one consistent executive voice. A central orchestrator routes each question to specialist agents covering strategy, finance, HR, legal, operations, marketing, product, sales and board communications, and combines their answers into a single response.
Each specialist retrieves context from a built-in set of management knowledge documents and from company documents the user uploads, stored in a local ChromaDB vector index. Synced sources such as Google Drive, OneDrive, Confluence and Notion are kept separate from uploaded documents and labelled as unreviewed. An episodic memory in SQLite records decisions and initiatives so later sessions can build on earlier advice, and a built-in scheduler can surface follow-ups.
The app is built with a FastAPI backend and a Next.js 15 web UI, and it works with Anthropic Claude models or, optionally, OpenAI-compatible local servers such as Ollama and vLLM. Chat access is available through the web app, Slack, Discord, Telegram, Google Chat and email, and it can run as an MCP server for other AI clients.
Key features
- 01Nine specialist agents (strategy, finance, HR, legal, operations, marketing, product, sales, board) behind one executive persona
- 02Retrieval over built-in management knowledge and uploaded company documents via ChromaDB
- 03Episodic memory of past decisions and initiatives in SQLite
- 04Integrations with Slack, Discord, Telegram, Google Chat, Gmail and Outlook, Notion and Confluence
- 05Optional MCP server endpoint and MCP client gateway for external tools
- 06Support for Claude models and OpenAI-compatible local model servers
Use cases
- A founder wanting an AI sounding board for fundraising, pricing or hiring decisions grounded in company documents
- A manager drafting replies or board updates that they review before sending
- A team that wants to query its Confluence or Notion knowledge base from Slack or Discord
- An engineering group exposing company context to coding agents through MCP
Quick start
- 1
Clone the repository
git clone https://github.com/SenteLabsAI/OpenExecutive.git - 2
Enter the project folder
cd OpenExecutive - 3
Install backend and web app dependencies
make install - 4
Add your Anthropic API key to the .env file, then start everything
make dev
Things to know
- Requires a paid Anthropic API key to run the agents.
- The first install is heavy: it pulls ChromaDB and PyTorch and downloads an embedding model, so the first start takes several minutes.
- On Windows, make must be run from Git Bash or WSL rather than PowerShell or cmd.
- The API must run as a single instance because the scheduler is not safe to scale horizontally.
In collections
Topics
FAQ
- What is OpenExecutive?
- Self-hosted AI executive team: one executive persona backed by specialist agents for strategy, finance, HR, legal, ops, marketing, product and sales, built on Claude. Open Executive is a self-hosted AI assistant for founders and managers that answers business questions with one consistent executive voice. A central orchestrator routes each question to specialist agents covering strategy, finance, HR, legal, operations, marketing, product, sales and board communications, and combines their answers into a single response.
- Is OpenExecutive free to use? What license does it have?
- OpenExecutive is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is OpenExecutive still maintained?
- Actively maintained. The last commit to OpenExecutive was on Nov 6, 2026.
- What can I use OpenExecutive for?
- A founder wanting an AI sounding board for fundraising, pricing or hiring decisions grounded in company documents A manager drafting replies or board updates that they review before sending A team that wants to query its Confluence or Notion knowledge base from Slack or Discord An engineering group exposing company context to coding agents through MCP
- How do I install OpenExecutive?
- Clone the repository: git clone https://github.com/SenteLabsAI/OpenExecutive.git Enter the project folder: cd OpenExecutive Install backend and web app dependencies: make install Add your Anthropic API key to the .env file, then start everything: make dev
- Where can I get OpenExecutive?
- The source code and installation instructions are on GitHub: https://github.com/SenteLabsAI/OpenExecutive
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source Next.js template for AI-generated apps that run generated code in E2B sandboxes, similar to Claude Artifacts or v0.
Self-hosted AI operating system that runs a workforce of AI agents on your own machine, with any model, 1,000+ tool integrations and a Knowledge Graph.
An agent-native, self-hostable AI learning workspace for personalized tutoring, Q&A, quizzes, research and visualization, built on Python and Next.js.
Multi-agent LLM pipeline that turns a research paper or topic into a cited scorecard on technology readiness, patents, market and risks.
AI-powered conversational search engine that answers questions with live web results, supporting OpenAI, Anthropic, Gemini and Vertex AI models.