EGGENT docs
Reference

For agents

How a language model or an agent should read these docs — machine-readable pages, llms.txt, stable addresses, and which pages answer which questions about Eggent.

These docs are written to be read by agents as well as people — including Eggent itself, when it needs to learn more about itself.

Machine-readable versions

What Address
Every page with its description /docs/llms.txt
The whole documentation in one file /docs/llms-full.txt
One page as Markdown /docs/<topic>.md, for example /docs/schedules.md
The same in Russian /r/docs/llms.txt, /r/docs/<topic>.md
Index of both languages /llms.txt

Every HTML page has a <link rel="alternate" type="text/markdown"> in its <head> pointing at its Markdown version.

Stable addresses

  • A page's address is the same in both languages: /docs/<topic>/ and /r/docs/<topic>/.
  • Sections within a page have permanent Latin anchors, the same in both languages: /docs/chats/#modes and /r/docs/chats/#modes.
  • Links inside the Markdown versions point to the Markdown versions of other pages.

Which page answers which question

Question Page
What a project, the orchestrator, a skill, memory are concepts
The agent's tools and their parameters agent-tools
What the agent can and cannot do capabilities
Chat modes, stopping, steering mid-task chats
Creating or changing a schedule, time formats schedules
Connecting Telegram, channels, access codes telegram
Models, your own key, a project's model models
Ready-made skills and cards skill-catalog
Writing skills skills
Where things are on disk workspace-layout
Plans, credits, disk plans
The external API and streaming external-api
Common problems and fixes troubleshooting

Advice for the Eggent agent

  • When a person asks how something works in Eggent, read the relevant page first rather than guessing.
  • When answering, rely on your own tools: their exact names and parameters are in your tool list, and their descriptions in the reference.
  • Take screen and button names from the docs: they match the interface in the person's language.
  • The docs cover both the cloud and the open core. If the workspace is self-hosted (no Eggent AI, no shared bot), the cloud sections do not apply to it.