Built-in tools
OtoDock ships with a set of tools out of the box. Some are core — on by default for every agent, powering the platform's own features (a manager can still turn one off for a specific agent) — and some are optional, ready to enable per agent. This is in addition to the service integrations and the community catalog.
Core tools — on by default
These power the features described elsewhere in these docs and are added to every agent automatically. An admin can't remove them platform-wide, but a manager can turn any of them off for a specific agent:
| Tool | What it does |
|---|---|
| Memory | Long-term notes an agent keeps across conversations. See Memory. |
| Tasks | Schedule work — recurring, one-off, and trigger-fired. See Tasks. |
| Delegation | Hand work to other agents and monitor the workers. See Delegation. |
| Triggers | React to external events. See Triggers. |
| Notifications | Alert you in the dashboard and on your devices. See Notifications. |
| Meetings | Bring several agents together to collaborate. See Meetings. |
| Display | Show images, audio, video, links, and downloadable files inline in chat, and build and run the apps an agent makes for you. |
| Checks | List, attach, and run the checks that review an agent's work, and write new ones from a manager's chat. |
| Files & documents | Read and write Word, Excel, PowerPoint, and PDF files, convert between formats, edit and analyze images, and open documents in a window beside the chat. |
| Agent self-configuration | Lets an agent inspect and adjust its own settings — persona, knowledge libraries, department (manager sessions only, each change approved in chat). |
| Catalog browser | Lets an agent browse the community catalog, enable tools it's allowed to, and file requests for the rest. |
| Agent creation | Lets an agent interview you and build a new agent (creator and admin chats only). |
Optional tools — ready to enable
These ship with the platform and can be turned on per agent:
| Tool | What it does |
|---|---|
| Image generation | Create images from a text prompt. |
| Image search | Find images on the web, including reverse image search. |
| Video generation | Generate video clips, transitions between clips, and AI edits of existing footage. |
| Music generation | Create music tracks and sound effects from a text prompt. |
| SSH hosts | Reach the servers an admin has configured, straight from the agent's shell. It's left out of viewers' and contributors' chats. |
| Text-to-speech | Generate voice-over audio files from text, in the platform's configured voices. |
| Transcription | Turn audio and video into text, with timing and subtitles. |
| Browser control | Drive a web browser on a remote machine: a dedicated per-agent profile, or the very browser you're signed into (own-browser mode).* |
| Computer control | Control a machine's screen, keyboard, and mouse.* |
| Outbound phone calls | Let an agent place phone calls. See Phone Calls. |
* Browser and computer control are device-control tools — they run only on a remote machine where you've granted the capability, never on the server sandbox.
Text-to-speech, transcription, and outbound phone calls depend on configured speech providers — they stay hidden platform-wide until an admin connects the relevant speech-to-text or text-to-speech provider under Setup → Audio. If you're hunting for them on a fresh install, that's why they're not in the list yet.
Connecting services and adding more
Beyond these, agents connect to services like GitHub and Notion (Integrations), and you can install additional tools from the community catalog or build your own.
Next steps
- Using Tools → — how tools are authorized and enabled.
- Integrations → — connect external accounts.
- Community Catalog → — browse and install more.