← Documentation index Practical › Survival Kit

Mykleos — Survival Kit

This document answers one question only: "what will I actually be able to do, in practice, from day one?". No architecture, no code. Ten minutes, and you know what to expect.

If you haven't read Architecture — Introduction (in Italian for now; English coming soon), you can still follow this document, but the terms sandbox, workspace, autonomy are defined canonically there.

The five things you get on day 1

  1. Chat from the terminal. mykleos chat opens a local text session. It is the fastest way to talk to the agent, and by default runs at Supervised autonomy (it asks confirmation for serious actions).
  2. Chat from Telegram. A dedicated bot, to which you connect once through pairing. After that, writing to the bot is equivalent to talking to your home computer from anywhere.
  3. Run shell commands inside a sandbox. Examples: check how much disk space is left, search for a file in the workspace, recompile a project, answer "what is the NAS IP address?".
  4. Read and write in the workspace (/opt/myclaw/workspace/). Here the agent has free rein (always sandboxed). Outside the workspace, approval is required.
  5. Automate repeated chores with cron. Example: "every evening at 22:00 summarise the systemd log and send me a Telegram message if anything unusual shows up".

A typical dialogue

Scenario: you're at the supermarket, you want to know whether the Claude model download you started last night has finished.

Roberto
is the model download done?
Mykleos
Checking ~/downloads/ and the wget log. Give me a second.
(internal)
Policy: "fs_read + web_fetch to local log" → Supervised OK, no approval needed. Bwrap started, read-only profile.
Mykleos
Yes. 8.2 GB of 8.2 GB downloaded, SHA256 verified. The file is claude-opus-4-7.gguf, finished at 03:14 tonight. Should I move it to /opt/models/?
Roberto
yes
(internal)
Policy: moving out of the workspace → requires approval. The "yes" just received counts as explicit approval.
Mykleos
Done. mv ~/downloads/claude-opus-4-7.gguf /opt/models/ executed, chmod 644. Audit log #1247.

Notice how the agent:

What yes, what not yet

✅ Yes, from day 1

⛔ Not yet

Essential commands

CommandWhat it does
mykleos chatOpens an interactive chat from the terminal
mykleos chat --level readonlyChat with autonomy at the minimum (useful for testing)
mykleos session --level full --for 10mTemporarily raises autonomy (expires on its own)
mykleos pairing listLists known senders per channel
mykleos pairing approve telegram K7-DELTA-19Approves a new Telegram user
mykleos pairing revoke telegram @someoneRevokes a user
mykleos cron listShows scheduled jobs
mykleos cron add "22:00" "summarise daily log"Adds a job
mykleos audit tailFollows the audit log in real time
mykleos audit query --today --action=shellSearches the audit log
mykleos doctorChecks config sanity (ports, permissions, hardening)
systemctl --user status mykleos-gatewayGateway status
The commands above are those planned. In the design phase they do not yet exist. The list is here to fix UX expectations.

Where you put your hands

Three folders are under your direct control and do not require approval to be edited by hand:

WhereWhat you editEffect
/opt/myclaw/workspace/ Markdown files (IDENTITY, USER, MEMORY, AGENTS, SOUL) Changes the agent's personality/memory. Read on the next message.
/opt/myclaw/config/default.yaml Defaults: gateway port, default autonomy, cost-cap, rate-limit Requires a gateway restart.
/opt/myclaw/config/secrets.env Telegram bot token, external provider API keys, etc. Chmod 600 required. Gateway restart.
Remember: Mykleos does not decide which model to run. The choice lives in the implementation of the LLM abstraction (in the author's environment: suprastructure, config in /opt/suprastructure/config/). A single place to decide "which model runs in the house": Mykleos inherits that, like any other sibling agent of the same environment.

Glossary

The complete glossary of the project — technical terms, components, sibling projects, people and places — lives in a dedicated document:

→ Open the Glossary about 35 entries, alphabetical, with links to canonical sources.

A few entries that recur in the Survival Kit, at a glance:

Gateway
Mykleos's main process. Listens on 127.0.0.1, handles channels, sessions, cron.
Channel
A way to talk to Mykleos. CLI, Telegram, and in future voice (through a dedicated home agent).
Autonomy
The agent's level of latitude: ReadOnly, Supervised (default), Full.
Workspace
The agent's "home": /opt/myclaw/workspace/. Markdown personality files + audit log.
LLM abstraction
The architectural pattern: Mykleos accesses language models (and STT/TTS/embedding) only through abstract interfaces, not through clients of specific providers. Makes the system provider-agnostic.
suprastructure
The implementation of the LLM abstraction present in the author's environment. In a different environment the role would be played by a different adapter.
home agent
A sibling agent specialised in voice and home automation (wake-word, STT, TTS, MQTT). Mykleos does not absorb those functions: it delegates them.

Next steps for you

If anything here is missing or unconvincing, speak up now: changing the design in the docs phase is 100× cheaper than in code.

Continue reading

foundations · 20 min · IT
Architecture — Introduction v1
The system as a whole: the four layers, the flow of a request, the three levels of autonomy. The high-level contract.
extension · 30 min
Neurons, Synapses and Memory v1.1
The evolved version: Mykleos manufactures new tools (neurons) for problems that the fixed tools don't solve. Darwinian selection + 3-layer memory.
reflection · 25 min
Dialogue on ends and limits
The philosophical trace behind the design, in four Giornate.
home
← Documentation index
Back to the full list of documents and their relations.

Mykleos — Survival Kit v1.0 — 22 April 2026