RagLeapShort answer: run RagLeap Core, upload your listing sheets, brochures and FAQs, and use the built-in real_estate_agent role. For managing rented properties there is property_management_agent, and for shared offices coworking_space_agent. This is an open-source (MIT) system you run yourself. The steps are in the general setup guide; this page covers what is specific to property.
Which roles apply?
Three of the 46 built-in roles: real_estate_agent, property_management_agent and coworking_space_agent. Others you may combine: sales, support, secretary and b2b_lead_qualifier. The role names are the identifiers in the code (defaults.py at v0.11.0).
What would you upload?
Whatever your staff answer from today, for example listing sheets, price lists, brochures, lease terms and viewing instructions, as PDF, Word, Excel or other supported files, or a public web page by address. The assistant answers from those documents and cites the source. It knows only what you load.
What does the default setup do for enquiries?
The starter memory in the code includes two rules: when a question cannot be answered from the available information, the assistant says it will check and get back; and when a potential customer shows interest, it captures name, contact number and requirement. You can read them in defaults.py and change them.
How do enquiries arrive?
Through WhatsApp, Telegram, Discord or a voice line (Twilio). A website chat widget is planned, not built. Language detection runs across every channel; short messages in closely related languages can be misdetected.
What should you check first?
- Autonomy is
offby default. Insemithe assistant asks before acting;fullis opt-in. Keep it off until you have read real conversations. - Your documents and each conversation go to the AI provider you configure (a local Ollama model is the alternative).
- Single-tenant: one deployment, one agency, one document set. No named users or roles yet, and no independent security review yet.
- The README lists connectors for CRMs such as HubSpot and Salesforce, but its known limitations say sync runs only on demand and synced data is not yet injected into chat answers automatically. The README is not consistent on this, so test it before relying on it.
- No results for real estate are claimed. Test with your own documents and questions.
Sources
The v0.11.0 README, defaults.py and the AI employees documentation.