{"name":"OpenExecutive: Build a Virtual Executive Team with Claude","description":"OpenExecutive uses Anthropic's Claude to power a virtual executive team with one consistent voice, specialist agents, and company-specific knowledge. It brings advice and workflows to a web app and workplace integrations, for teams willing to self-host and configure access.","github":"https://github.com/SenteLabsAI/OpenExecutive","url":"https://osrepos.com/repo/sentelabsai-openexecutive","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/sentelabsai-openexecutive","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/sentelabsai-openexecutive.md","json":"https://osrepos.com/repo/sentelabsai-openexecutive.json","topics":["python","ai-agents","web-app","rag","executive-assistant","episodic-memory","workplace-integrations"],"keywords":["python","ai-agents","web-app","rag","executive-assistant","episodic-memory","workplace-integrations"],"stars":null,"summary":"OpenExecutive uses Anthropic's Claude to power a virtual executive team with one consistent voice, specialist agents, and company-specific knowledge. It brings advice and workflows to a web app and workplace integrations, for teams willing to self-host and configure access.","content":"## Overview\n\nOpenExecutive is a self-hostable virtual executive team built on Anthropic's Claude, with a FastAPI backend and Next.js web app. It aims to give a company one consistent executive voice for questions and follow-through, backed by specialist agents and context from company documents and past decisions. It can also meet users in tools such as Slack, Discord, Telegram, Google Chat, email, and MCP-compatible clients.\n\nThe project is aimed at leaders and teams that want company-specific strategic and operational assistance, rather than a general-purpose chatbot. Its governance controls, approval steps, and optional “Act as me” email drafting are intended to keep people involved in consequential actions.\n\n## Key Features\n\n- Routes questions through an executive persona to specialist agents covering strategy, finance, people, legal, operations, marketing, product, sales, and board communications.\n- Retrieves context from built-in domain knowledge and uploaded company documents using ChromaDB.\n- Stores episodic decisions and initiatives in SQLite to inform later conversations.\n- Offers a Next.js web UI, CLI, chat integrations, and an MCP server endpoint.\n- Connects optional company services and knowledge sources, including Google Workspace, Microsoft 365, Notion, Confluence, and Drive.\n- Supports scheduled follow-ups, proactive alerts, and per-person memory controls.\n- Can route models through Anthropic, OpenRouter, or an OpenAI-compatible endpoint, including local model servers.\n\n## Use Cases\n\n- A founder can get company-aware input on strategy, cash flow, hiring, or product priorities without briefing a new assistant each time.\n- A leadership team can consult one executive interface across Slack or its web app, while using company documents as supporting context.\n- A busy leader can draft email in their own voice for review and sending, keeping the final decision with the person.\n- An organization can expose company context and specialist consultation to MCP clients, with access controlled by the deployment's authentication setup.\n\n## Our Take\n\nOpenExecutive is an ambitious, actively changing executive-assistant platform, but its young age and heavy contributor concentration make it worth piloting before relying on it for important workflows.\n\n**Good fit if:**\n- You want a Claude-based executive assistant grounded in company documents and persistent decision context.\n- You can operate the FastAPI and Next.js stack, configure integrations, and keep the API to a single instance for its scheduler.\n- You value an Apache-2.0 project with a CI workflow and are comfortable reviewing its fast-moving changes.\n\n**Look elsewhere if:**\n- You need a mature project with a longer operating history or a contributor base that is not concentrated around one person.\n- Your deployment requires multiple API replicas, since the README warns the scheduler is not safe to run across processes.\n- You need evidence of recent issue closure: the measured data reports no issues closed in the last 90 days, despite active commits and merged pull requests.\n\n## Project Health\n\n| Signal | Value |\n|---|---|\n| Status | **New**: less than six months old and changing fast |\n| Last commit | 2026-10-19 (today) |\n| Commits, last 90 days | 100+ |\n| Releases, last 12 months | 19 (latest v0.6.1, 2026-10-18) |\n| Contributors | 17 (top contributor: 82% of commits) |\n| Issues closed, last 90 days | 0+ |\n| Pull requests merged, last 90 days | 99 (typically merged in 0 days) |\n| Project age | 4 months |\n\nChecked on 2026-10-20 with the GitHub API.\n\n## Project Facts\n\n- Language: Python\n- License: Apache-2.0\n- Stars: 5.6k\n- Forks: 626\n- Topics: ai, anthropic, claude, fastapi, llm, multi-agent, nextjs, python\n- Website: https://openexecutive.ai\n- Archived: no\n\n## What You Need\n\nDetected in the repository:\n\n- Python (main language on GitHub)\n- Automated checks on GitHub Actions\n\n## Getting Started\n\n```bash\ngit clone https://github.com/SenteLabsAI/OpenExecutive.git\ncd OpenExecutive\nmake install\ncp .env.example .env\n# Add ANTHROPIC_API_KEY to .env\nmake dev\n```\n\nOpen `http://localhost:3000` to use the app. See the [README](https://github.com/SenteLabsAI/OpenExecutive#readme) for authentication, integration, and deployment instructions.\n\n## License in Plain Words\n\n**Apache-2.0** (permissive).\n\n- Commercial use: yes\n- Modify and redistribute: yes\n- You must keep: the license, the NOTICE file and a note of your changes\n- Share your changes: no\n- Includes an explicit patent grant from the contributors\n\nA summary, not legal advice: the LICENSE file is what applies.\n\n## Alternatives\n\n- [MaxKB](https://osrepos.com/repo/1panel-dev-maxkb): MaxKB is a general platform for building knowledge-grounded agents and workflows, rather than a ready-made virtual executive team with a consistent voice.\n\n| Project | Language | License | Stars | Status |\n|---|---|---|---|---|\n| **OpenExecutive** | Python | Apache-2.0 | 5.6k | New |\n| [MaxKB](https://osrepos.com/repo/1panel-dev-maxkb) | Python | GPL-3.0 | 22.9k | Active |\n\n## Considerations\n\n- This is a new project that is changing quickly. Recent activity and releases are strong, but the measured contributor data shows that most contributions come from one person; the measured data also reports no issues closed in the last 90 days.\n- The basic setup uses Python 3.11 or later and Node 22.6 or later. The README says first startup downloads ChromaDB-related dependencies and an embedding model, so initial setup takes longer than subsequent starts.\n- Production deployment requires attention to authentication, shared secrets, persistent storage, and allowed origins. The scheduler requires a single API instance unless it is separately gated.\n- Anthropic is the default model provider and needs an API key unless you configure an alternative supported backend. The README notes that web search and some Claude-specific capabilities are unavailable with local models.\n- The Apache-2.0 license permits commercial use and requires attribution.","metrics":{"detailViews":3,"githubClicks":0},"dates":{"published":null,"modified":"2026-10-20T06:42:27.000Z"}}