CEO fired developers to make room for AI. Developers create open source AI CEO

SenteLabs AI released Open Executive, an open-source AI system that simulates a virtual executive team with eight specialist agents, including a Chief Strategy Officer and Chief Financial Officer, built on Anthropic's Claude models. The system, available under Apache 2.0, provides a unified executive voice, episodic memory, and a scheduler, aiming to replace human executives in decision-making processes.

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 https://youtu.be/O g97xxVTMk . Developed by sentelabs.ai https://sentelabs.ai Open Executive provides a single coherent executive voice backed by eight specialist AI agents: Chief Strategy Officer — competitive analysis, M&A, market positioning, OKRs Chief Financial Officer — financial modeling, fundraising, unit economics, cash flow Chief HR/People Officer — hiring, compensation, performance, culture General Counsel — contracts, IP, employment law basics, compliance Chief Operating Officer — process design, vendor management, operational scaling Chief Marketing Officer — GTM strategy, brand, communications, PR Chief Product Officer — roadmap, prioritization, product strategy Board Communications Director — board decks, investor relations, governance 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. User message ↓ Executive Orchestrator claude-sonnet-4-6 ↓ tool use → parallel specialist calls CSO / CFO / CHRO / GC / COO / CMO / CPO / Board ↓ each specialist retrieves relevant context from ChromaDB Built-in MBA knowledge + Your company documents ↓ Synthesized executive response 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 separate company docs collection. RAG context is injected into the user turn, never the cached system prompt. Episodic memory — After every response, a background claude-haiku-4-5 pass extracts key decisions, initiatives, and advice into SQLite. The next session opens with a <past decisions block so the Executive remembers what it recommended last month. Scheduler — A built-in job runner claims due actions via UPDATE … RETURNING to 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. See docs/architecture.md /SenteLabsAI/OpenExecutive/blob/main/docs/architecture.md for the full design. | Layer | Choice | |---|---| | LLM backbone | Anthropic Claude API | | Default model | claude-sonnet-4-6 Executive + most specialists | | Deep reasoning | claude-opus-4-7 CSO, CFO, GC, Board — with extended thinking | | Backend | Python 3.11 + FastAPI | | Package manager | uv | | Vector store | ChromaDB local, embedded | | Episodic memory | SQLite | | Web UI | Next.js 15 App Router + Tailwind | | License | Apache 2.0 | openexecutive/ ├── packages/ │ ├── core/ │ │ └── openexecutive/ │ │ ├── orchestrator/ Executive persona + routing loop │ │ ├── agents/ 8 specialist agents │ │ ├── knowledge/ ChromaDB store + RAG pipeline │ │ ├── memory/ Company profile + episodic memory │ │ ├── onboarding/ Wizard state machine + profile builder │ │ ├── prompts/ Persona + domain prompts + cache manager │ │ ├── api/ FastAPI app + routes │ │ ├── integrations/ Slack, Email, Telegram, Google Chat, Discord │ │ ├── scheduler/ Background job runner single-instance │ │ ├── alerts/ Proactive alert system │ │ ├── audit/ Audit logging │ │ ├── architecture/ Internal architecture utilities │ │ ├── workflows/ Multi-step workflow definitions │ │ └── cli.py Click CLI │ └── ui/ Next.js 15 web UI ├── evals/ Eval scenarios + LLM-as-judge runner ├── fixtures/ Demo company fixtures profiles, docs, rosters ├── scripts/ Operator scripts Fly secrets, Google auth ├── docker/ Dockerfile s + docker-compose.yml ├── fly.api.toml / fly.ui.toml Fly.io configs — dev API + UI apps ├── fly.api.qa.toml / fly.ui.qa.toml Fly.io configs — QA API + UI apps ├── fly.honcho.toml Fly.io config — Honcho memory app optional └── docs/ Architecture + deployment docs Clone the repo git clone https://github.com/SenteLabsAI/OpenExecutive.git cd OpenExecutive Set your Anthropic API key cp .env.example .env Edit .env and add ANTHROPIC API KEY=sk-ant-... Start everything make dev Open http://localhost:3000 http://localhost:3000 to 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 initial uv sync pulls 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 first make dev takes a few minutes before the app is ready. Subsequent starts are fast. For contributors not using make: cd packages/core uv sync source .venv/bin/activate uvicorn openexecutive.api.main:app --reload --port 8000 In a second terminal cd packages/ui && npm install && npm run dev - Create a Discord application at https://discord.com/developers/applications https://discord.com/developers/applications - Enable the Message Content privileged intent Bot → Privileged Gateway Intents - Invite the bot with bot + applications.commands scopes - Set env vars in .env : DISCORD BOT TOKEN , DISCORD APP ID , DISCORD GUILD IDS - Run the API normally — the bot starts as part of the FastAPI lifespan when DISCORD BOT TOKEN is set: make dev The bot is embedded in the API process alongside the email poller, scheduler, and resumer so it shares the same SQLite database and ChromaDB vector store under /data in production. Skip the token to disable. For iterating on bot-only code without restarting the API, make discord runs the bot as a standalone process against the same local DB. Users can DM the bot, @mention it in a channel replies in a thread , or use /ask and /today slash commands. Slash commands sync to DISCORD GUILD IDS instantly on startup; leave blank for global registration up to 1-hour propagation delay . Just set the secrets on the existing API app — no new Fly app required: flyctl secrets set -a openexec-api-dev \ DISCORD BOT TOKEN=... \ DISCORD APP ID=... \ DISCORD GUILD IDS=... Discord user access is managed via the /people UI — add a Person row with discord user id set. The machine restarts and the bot starts on the next lifespan boot. To disable in prod: flyctl secrets unset -a openexec-api-dev DISCORD BOT TOKEN . The first time you visit the app, you'll be guided through a wizard to set up your company profile: - Company basics name, industry, stage, team size - Business model and revenue - Competitive landscape - Strategic priorities - Culture and values - Optional: financial position, document upload After onboarding, the Executive will reference your specific company context in every response. | Interface | How to Use | |---|---| Web UI | http://localhost:3000 | Slack | Mention @OpenExecutive or DM the app | Email | CC or email the configured address IMAP/SMTP poller | Telegram | Message the configured bot | Google Chat | Mention the app in a space | Discord | DM the bot, @mention it in a channel, or use /ask / /today slash commands | CLI | openexecutive chat | Upload your pitch deck, financial model, strategy docs, or any company documents via the web UI or API. The Executive will reference them when relevant. Via CLI openexecutive upload deck.pdf model.xlsx strategy.md Via API curl -X POST http://localhost:8000/documents \ -F "file=@deck.pdf" \ -F "domain=strategy" Two environments, each a separate set of Fly apps, driven by branch: | Environment | Trigger | Workflow | Apps | |---|---|---|---| dev | push/merge to main continuous | .github/workflows/deploy.yml | openexec-api-dev , openexec-ui-dev | qa | push/merge to qa deliberate promotion | .github/workflows/deploy-qa.yml | openexec-api-qa , openexec-ui-qa | Both workflows use dorny/paths-filter to deploy only the changed app API, UI, or both . QA is a stable twin of dev — same image and runtime, only the app name differs fly.api.qa.toml / fly.ui.qa.toml — so it lags main and stays vetted. An optional Honcho memory app fly.honcho.toml deploys independently. | App | Purpose | State | |---|---|---| openexec-api-{dev,qa} | FastAPI + scheduler | Persistent volume executive data at /data | openexec-ui-{dev,qa} | Next.js 15 | Stateless | openexec-honcho-dev | Honcho per-person memory optional | Postgres-backed | : The scheduler claims rows via⚠️ Single-instance only UPDATE … RETURNING . Running two API machines would double-fire scheduled actions. max machines running = 1 is set in fly.api.toml / fly.api.qa.toml — do not override it. Deploys authenticate with per-app Fly deploy tokens stored as repo or org Actions secrets. Generate each with flyctl tokens create deploy -a <app -x 999999h : | Secret | App | Used by | |---|---|---| FLY API TOKEN API | openexec-api-dev | dev | FLY API TOKEN UI | openexec-ui-dev | dev | FLY API TOKEN HONCHO | openexec-honcho-dev | dev honcho job | FLY API TOKEN API QA | openexec-api-qa | qa | FLY API TOKEN UI QA | openexec-ui-qa | qa | Per-app runtime secrets ANTHROPIC API KEY , BACKEND SHARED SECRET , the AUTH set, integration tokens are set directly on each Fly app — see scripts/fly-secrets.sh.example . 1. Create apps and volume flyctl apps create openexec-api-dev flyctl apps create openexec-ui-dev flyctl volumes create executive data --region iad --size 1 -a openexec-api-dev 2. Set the required secret flyctl secrets set -a openexec-api-dev ANTHROPIC API KEY=sk-ant-... 3. Create deploy tokens and add as GitHub secrets FLY API TOKEN API and FLY API TOKEN UI flyctl tokens create deploy -a openexec-api-dev -x 999999h flyctl tokens create deploy -a openexec-ui-dev -x 999999h 4. First deploy gh workflow run "Deploy dev " -f target=both QA bootstraps the same way against the -qa app names push to the qa branch, or gh workflow run "Deploy qa " . See docs/deployment.md /SenteLabsAI/OpenExecutive/blob/main/docs/deployment.md for the full runbook operations, rollback, common failure modes, why .flycast isn't used . The deployed UI is gated behind Google sign-in with an email allow-list, and the public API is protected by a shared-secret header between the UI proxy and the FastAPI backend. See docs/auth.md /SenteLabsAI/OpenExecutive/blob/main/docs/auth.md for the full setup Google Cloud Console steps, required Fly secrets, adding/removing users, rotating secrets, and a debugging table . All settings via environment variables. Minimum required: ANTHROPIC API KEY — unless you configure a local or OpenRouter backend instead see Running on Local Models running-on-local-models . At least one provider must be set or the app refuses to start. | Variable | Required | Default | Description | |---|---|---|---| ANTHROPIC API KEY | Yes¹ | — | Anthropic API key | DEFAULT MODEL | No | claude-sonnet-4-6 | Executive + most specialists | DEEP REASONING MODEL | No | claude-opus-4-7 | CSO, CFO, GC, Board | VECTOR STORE PATH | No | ./chroma db | ChromaDB directory | EPISODIC DB PATH | No | ./episodic memory.db | SQLite for episodic memory | COMPANY PROFILE PATH | No | ./company/profile.yaml | Company profile | ENABLE CACHING | No | true | Anthropic prompt caching | ROUTING MODEL | No | claude-haiku-4-5-20251001 | Model for intent routing | SLACK BOT TOKEN | No | — | Slack bot OAuth token | SLACK APP TOKEN | No | — | Slack socket mode token | EXEC EMAIL ADDRESS | No | — | Executive Gmail address Gmail MCP OAuth | EMAIL POLL INTERVAL SECONDS | No | 60 | How often to poll for new email | TELEGRAM BOT TOKEN | No | — | Telegram bot token from @BotFather | TELEGRAM WEBHOOK SECRET | No | — | Random string for webhook validation | DISCORD BOT TOKEN | No | — | Discord bot token Developer Portal → Bot tab | DISCORD APP ID | No | — | Discord application ID General Information tab | DISCORD GUILD IDS | No | — | Comma-separated guild IDs for dev slash-command registration | DISCORD NOTIFY CHANNEL ID | No | — | Default channel ID for outbound notifications | GOOGLE CHAT PROJECT NUMBER | No | — | GCP project number for Google Chat | GOOGLE CHAT SERVICE ACCOUNT FILE | No | — | Path to service account JSON key | GOOGLE OAUTH CLIENT ID | No | — | Google OAuth client ID Gmail MCP | GOOGLE OAUTH CLIENT SECRET | No | — | Google OAuth client secret Gmail MCP | OPENROUTER ENABLED | No | false | Route Claude calls through OpenRouter and unlock non-Anthropic models per-agent in the Council UI | OPENROUTER API KEY | No | — | Required when OPENROUTER ENABLED=true | LOCAL MODELS ENABLED | No | false | Route selected slugs to a local OpenAI-compatible server Ollama, LM Studio, vLLM, llama.cpp | LOCAL BASE URL | No | — | Local server URL incl. version path, e.g. http://localhost:11434/v1 . Required when LOCAL MODELS ENABLED=true | LOCAL API KEY | No | — | Optional bearer token vLLM / gateways ; Ollama & LM Studio need none | LOCAL MODELS | No | — | Comma-separated local model slugs to surface in the Council UI and route locally, e.g. llama3.3,qwen2.5 | LOCAL TIMEOUT S | No | 300 | Per-call timeout for local generation, in seconds | HONCHO ENABLED | No | false | Per-person memory layer | HONCHO API KEY HONCHO ENABLED=true HONCHO BASE URL See .env.example /SenteLabsAI/OpenExecutive/blob/main/.env.example for the full list. ¹ ANTHROPIC API KEY is required only when you serve Claude models directly. It can be omitted entirely if you run on local models LOCAL MODELS ENABLED or route through OpenRouter OPENROUTER ENABLED . Open Executive can run against any OpenAI-compatible local server — Ollama, LM Studio, vLLM, or llama.cpp — instead of or alongside the Anthropic API. Local model slugs route to your server through the same provider abstraction the hosted models use; no agent or orchestrator code changes. 1. Pull a capable, tool-use-friendly model example: Ollama ollama pull llama3.3 2. In .env — point at the local server and list the slugs to expose LOCAL MODELS ENABLED=true LOCAL BASE URL=http://localhost:11434/v1 Ollama default LOCAL MODELS=llama3.3 3. Optional run with NO Anthropic key — make local the default everywhere DEFAULT MODEL=llama3.3 DEEP REASONING MODEL=llama3.3 ROUTING MODEL=llama3.3 ...and leave ANTHROPIC API KEY unset The listed slugs appear in the Council UI model dropdown, so you can also run a hybrid setup — keep the Executive on Claude while flipping individual specialists to a local model per-agent. Caveats. Server-side web search ENABLE WEB SEARCH and Anthropic prompt caching / extended thinking have no local equivalent and are automatically disabled for local models. Multi-agent routing leans heavily on tool use, so pick a model that's strong at it e.g. Llama 3.3 70B, Qwen2.5 — small models may route poorly. LOCAL API KEY is only needed if your server vLLM, or a gateway requires a bearer token; Ollama and LM Studio need none. - Create packages/core/openexecutive/agents/your agent.py extending BaseAgent - Add a system prompt constant in packages/core/openexecutive/prompts/domain prompts.py - Register in packages/core/openexecutive/orchestrator/router.py — add to SPECIALIST REGISTRY and the specialist enum in SPECIALIST TOOLS - Add domain alias to DOMAIN ALIASES in packages/core/openexecutive/knowledge/retriever.py - Add knowledge docs to knowledge/builtin/your domain/ - Add at least 2 eval scenarios to evals/scenarios/ - Submit a PR — CI requires all of the above make dev Start FastAPI + Next.js make test Run Python tests make eval Run eval suite make lint Run ruff + mypy make docker Build and run Docker stack Unit tests only no API calls required pytest packages/core/tests/unit/ -v evals/ contains 29 scenarios covering all 8 domains, scored by claude-opus-4-7 as an LLM-as-judge. Each scenario defines a query, simulated company context, expected topics, required specialist routing, and a domain-specific rubric. Five scoring dimensions persona coherence, domain accuracy, company context utilization, routing quality, actionability are each rated 1–5. The CI gate requires ≥ 3.5/5 average; any dimension dropping 10% vs main fails the PR. Everything in company/ is gitignored — the profile YAML, uploaded documents, and the ChromaDB vector store. None of this leaves your local machine or your own Fly volume in cloud deployments except as part of prompts sent to the Anthropic API. Anthropic does not train on API data. See .github/CONTRIBUTING.md /SenteLabsAI/OpenExecutive/blob/main/.github/CONTRIBUTING.md . All PRs must include: - Working implementation no stubs - Tests for new behavior - Eval scenarios for new agents or prompt changes Apache 2.0 — free to use commercially, requires attribution.