diff --git a/README.md b/README.md index e621ffef..c86c8559 100644 --- a/README.md +++ b/README.md @@ -110,15 +110,15 @@ three rows are why teams choose it; the rest is the groundwork done properly. | Capability | What you get | |---|---| -| ๐Ÿ›ก๏ธ **Privacy Shield** | Raw tool results stay behind a data-plane boundary; the LLM sees only an identity-free digest. `guarded` by default, with `bypass`/`per_tool` opt-in and an org-wide clamp (`OMADIA_PRIVACY_FORCE_GUARDED`). Real data can run through omadia without running through the model. | -| โœ… **Answer verification** | A verifier checks each answer's claims against the run's own sources and records a verdict (`approved` / `approved_with_disclaimer`) before it reaches the channel. | -| ๐Ÿงฎ **Computed, not guessed** | Office and Excel output comes from a real spreadsheet engine, server-side, over real rows (`datasetId`). The figures are calculated by that engine rather than produced by the model. | -| ๐Ÿงพ **A receipt for every action** | Every agent run carries a full per-run trace and call-stack viewer: every step, tool call, and decision, replayable. | -| ๐Ÿ‘ฅ **Multiplayer by design** | Agents run in your team's shared channels (Slack, Teams, Telegram, Discord), so several people work with them in one context, not a private one-on-one chatbot. | -| ๐Ÿค– **Agent teams, not one chatbot** | An orchestrator routes each turn to the right specialist plugin agent. Channels, integrations, tools, and capability providers sit behind one stable API. | -| ๐Ÿ”’ **Self-hosted and yours** | One `docker compose up` on a single machine. Your Postgres, your LLM key, all of the data on your own infrastructure. GDPR-aware and made in the EU. | -| ๐Ÿงฉ **Signed plugin distribution** | Plugins ship as verifiable signed packages. The platform never pulls arbitrary npm at runtime. | -| ๐Ÿ”Œ **Enterprise integrations** | Microsoft 365, Odoo, Confluence, Teams, and Telegram, with the LLM provider a swappable plugin. | +| ๐Ÿ›ก๏ธ **Privacy Shield** | Raw tool results stay behind a data-plane boundary; the LLM sees only an identity-free digest. `guarded` by default, with `bypass`/`per_tool` opt-in and an org-wide clamp (`OMADIA_PRIVACY_FORCE_GUARDED`). Real data can run through omadia without running through the model. | +| โœ… **Answer verification** | A verifier checks each answer's claims against the run's own sources and records a verdict (`approved` / `approved_with_disclaimer`) before it reaches the channel. | +| ๐Ÿงฎ **Computed, not guessed** | Office and Excel output comes from a real spreadsheet engine, server-side, over real rows (`datasetId`). The figures are calculated by that engine rather than produced by the model. | +| ๐Ÿงพ **A receipt for every action** | Every agent run carries a full per-run trace and call-stack viewer: every step, tool call, and decision, replayable. | +| ๐Ÿ‘ฅ **Multiplayer by design** | Agents run in your team's shared channels (Slack, Teams, Telegram, Discord), so several people work with them in one context, not a private one-on-one chatbot. | +| ๐Ÿค– **Agent teams, not one chatbot** | An orchestrator routes each turn to the right specialist plugin agent. Channels, integrations, tools, and capability providers sit behind one stable API. | +| ๐Ÿ”’ **Self-hosted and yours** | One `docker compose up` on a single machine. Your Postgres, your LLM key, all of the data on your own infrastructure. GDPR-aware and made in the EU. | +| ๐Ÿงฉ **Signed plugin distribution** | Plugins ship as verifiable signed packages. The platform never pulls arbitrary npm at runtime. | +| ๐Ÿ”Œ **Enterprise integrations** | Microsoft 365, Odoo, Confluence, Teams, and Telegram, with the LLM provider a swappable plugin. | ## What's in the box