An AI system that acts as your company’s virtual executive team — a senior advisor with Harvard MBA-level knowledge, customized for your specific business.
A walkthrough of Open Executive in action —watch on YouTube.
Developed bysentelabs.aiOpen Executive provides a single coherent executive voice backed by eight specialist AI agents:
All responses come from one consistent executive voice. The internal agent architecture is never exposed to the user. Beyond Q&A, the system maintains episodic memory of past decisions and initiatives across sessions, and a built-in scheduler can proactively surface follow-ups and time-sensitive actions.
Knowledge— Two retrieval layers per specialist call: (1) built-in MBA-level Markdown (knowledge/builtin/, git-tracked) seeded into ChromaDB at startup, and (2) your uploaded company documents chunked and stored in a separatecompany_docscollection. RAG context is injected into the user turn, never the cached system prompt.
Episodic memory— After every response, a backgroundclaude-haiku-4-5pass extracts key decisions, initiatives, and advice into SQLite. The next session opens with ablock so the Executive remembers what it recommended last month.
Scheduler— A built-in job runner claims due actions viaUPDATE … RETURNINGto prevent double-firing. The API must run as a single instance; do not horizontally scale it without gating the scheduler first.
Prompt caching— The system prompt is structured so the Executive persona, company profile, and knowledge index are cached separately (up to 85% cache hit rate after the first few turns). No dynamic content ever goes in a cached block.
Seedocs/architecture.mdfor the full design.
Openhttp://localhost:3000to start chatting with your executive. The API runs on port 8000 and the UI on 3000.
First run:requires Python 3.11+ and Node 22+. The initialuv syncpulls heavy
ML dependencies (ChromaDB + sentence-transformers/PyTorch), and the first boot
downloads a small embedding model (~90 MB) to build the local vector index — so the
firstmake devtakes a few minutes before the app is ready. Subsequent starts are fast.
For iterating on bot-only code without restarting the API,make discordruns the bot as a standalone process against the same local DB.