We build Oto — a B2B automation toolkit that gives AI assistants real tools: company & people intelligence, prospecting, CRM, messaging, French open data, and a structured knowledge base. Everything is exposed over the Model Context Protocol (MCP), so it works across Claude, ChatGPT and other LLMs.
The platform is composed, not monolithic (and largely open source — the product core included).
| Repo | What |
|---|---|
oto-backend |
The backend — encrypted credential vault, orgs, doctrine, monitoring. MCP (mcp.oto.ninja/mcp) + REST. The center of the platform. |
oto-dashboard |
Product dashboard for the backend (Vue 3 + shadcn-vue + Tailwind, Logto PKCE). |
oto |
Architecture doctrine — ADRs + overview |
oto-core |
Connector library (oto.tools) |
oto-cli |
Business-automation CLI, for humans and agents |
oto-plugin |
Claude Code plugin — auto-configured MCP connector |
france-opendata |
French public-data clients (Sirene, INPI, BODACC, DVF…) |
otomata-calllog |
Normalized MCP tool-call journal |
o-browser |
Python browser automation (Patchright / remote CDP) |
memento |
Structured, sourced knowledge substrate for agents (MCP) · Apache-2.0 |
scout |
White-label shell for lead-enrichment platforms |