Javis OS
Javis OS는 기업가를 돕는 에이전시 AI로, 업무를 지원하고 함께 성장합니다
Mila — open-source digital employee in Telegram, built on Claude Code. Bring your own Claude account or API key; she remembers your business and acts in your name only with your consent.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다.
README 전문 보기 ↗curl -fsSL https://raw.githubusercontent.com/shakhruz/mila-agent/main/install/get.sh | bash
Most open agents are universal assistants: powerful, if you tell them exactly what to do. Mila is built the other way round — a colleague with a job.
mila export / mila restore moves her to any machine.Customer: Hi! Is the two-bedroom by the sea still free? Can I see it on Saturday?
Mila: Hi! Yes, it's free 🙂 Saturday at 11:00 or 15:00 — which suits you? I'll book it and remind you an hour before.
Customer: 11, please.
Mila: Done ✅ I'll send the address and remind you on Saturday morning.
Next morning the owner gets one line: new client · viewing Saturday 11:00 · reminder set.
| Build one — free | Install Mila Agent yourself, on your computer or a server. | Quick start ↓ |
| Hire one | Ready-made Milas for a job — moderator, manager, SMM and more. The first one is free. | mila.market |
| Launch your own | MilaGPT Studio sets your Mila up with you and helps turn your expertise into a product. | milagpt.io/akselerator |
OpenClaw, NanoClaw and Hermes Agent are excellent open agents — universal assistants for a person. Mila takes a narrower job: a digital employee for a business, on Telegram.
| Mila | OpenClaw | NanoClaw | Hermes Agent | |
|---|---|---|---|---|
| What it is | digital employee for a business | universal personal agent | personal agent in containers | personal agent that grows with you |
| Engine | Claude Code | own agent loop, models as plugins | Claude Agent SDK | own agent loop, any model |
| Channels | Telegram: DMs, groups, your public bot (mila-telegram) | 20+ (WhatsApp, Telegram, Slack...) | many, each added by a skill | Telegram, Discord, Slack, WhatsApp... |
| Business skills out of the box |
Mila's honest minuses. Telegram only: no WhatsApp, Slack or Discord. It needs Claude Code, signed in with your own Claude plan or API key — Mila herself runs only on Claude (guests on other models through OpenRouter: in the hosted version today, open core — next release). She answers while your machine and the session run: a closed laptop means a silent Mila, so use an always-on computer or a server. macOS and Linux; Windows only through WSL. Channels in Claude Code are a research preview, so the launcher uses a development flag for now (see Quick start).
Facts about other projects: their READMEs and docs, checked 17.10.2026; approvals row re-checked 21.10.2026 against NanoClaw security and Hermes security - OpenClaw, NanoClaw, Hermes Agent. Something wrong or out of date? Open an issue - we fix it the same day.
Source: Claude Code — legal and compliance.
≈ 5 minutes.
You need:
claude --version), signed in with your own Claude plan (Pro, Max, Team or Enterprise) or your own Anthropic API key. On Team and Enterprise your organization admin must enable channels.@BotFather.~/.local/bin on your PATH — the mila launcher goes there (the installer tells you if it is missing: export PATH="$HOME/.local/bin:$PATH").mila onboard (step 3). Setting it by hand: MILA_OWNER_ID=<your id> ~/mila/install/install.sh.One command:
curl -fsSL https://raw.githubusercontent.com/shakhruz/mila-agent/main/install/get.sh | bash
It checks Claude Code, Bun and git, clones the kit to ~/mila, runs install/install.sh and installs the Telegram plugin mila-telegram (existing files are backed up as <file>.bak-YYYYMMDD-HHMMSS). Prefer to look first? curl -fsSL https://raw.githubusercontent.com/shakhruz/mila-agent/main/install/get.sh | MILA_INSTALL_ARGS=--dry-run bash — or clone and run ./install/install.sh --dry-run: it shows exactly what will be touched.
Then three steps, each checked before the next:
mila onboard
OWNER_ID). Mila sees that code as your first message when she starts — that's normal.Then start Mila with mila. mila onboard --check shows the three steps without changing anything; if the bot goes quiet, run
mila doctor. Prefer the plugin's own commands? /mila-telegram:configure <token> and /mila-telegram:access pair <code> still work.
Why mila starts Claude Code with --dangerously-load-development-channels. Channels are a research preview in
Claude Code: the plain --channels flag accepts only plugins on Anthropic's approved list, and mila-telegram is not on it
yet. The development flag lets this one plugin, named in the command, push messages into your session; it does not
skip permission prompts and does not load anything else. Messages still reach Mila only from people you paired or allowed.
If the plugin is accepted into Anthropic's plugin marketplace, mila will switch to plain --channels. Details:
Claude Code — channels.
When it works, mila doctor looks like this (yellow lines are hints, not errors):
Channel diagnosis · ~/.claude/channels/telegram
🟢 bot @your_mila_bot (Mila), source: ~/.claude/channels/telegram/.env
🟡 privacy mode on — in groups only mentions and replies reach Mila
🟢 private chats allowed 1, policy «allowlist»
🟢 daemon running, code: …/mila-telegram/receiver.ts
🟢 permissions telegram — 700, .env — 600, access.json — 600
🟢 channel in session plugin MCP server is running
Server install: see deploy/README.md.
A Mila belongs to her owner, 100%. Everything you taught her - instructions, skills, memory, crons, settings - exports to one archive, and this open core plus that archive brings her back on any machine.
mila export --out ~/mila-backups # archive without passwords and keys (a secret scanner runs on every file)
mila export verify <archive> # manifest + sha256 check
# on a clean machine, after install/install.sh or deploy/bootstrap.sh:
mila restore <archive> --dry-run # see what goes where
mila restore <archive> # existing files are never overwritten; differences go to ~/.claude/mila-restore/
The archive has manifest.json (format 1, sha256 of each file, core version) and RESTORE.md; secrets are never in it.
After the restore you re-enter by hand: the bot token, your Claude login, service keys (the checklist is printed).
Chat history and transcripts are exported only with --with-history (other people's data - keep it closed).
Details: skills/mila-export. To save the memory on a schedule, use mila backup (see above in the reference).
The send-guard hook blocks messages that would leak one conversation into another or expose server paths; if the guard itself fails, nothing is sent. See SECURITY.md.
MILAGPT is a small team led by Shakhruz Ashot Ashirov - founder of MILAGPT and AshotAI, 40 years in software, 28 of them in commercial development and online marketing (Disney, Apple, AT&T), and Farangiz Sharapova - co-founder of MILAGPT. A fleet of Milas works next to us every day: development, quality, content, clients - this repository is the core they run on.
Developers, join us. Build a skill, fix a hook, translate a skill to your language, tell us what broke. Every pull request is read by a person and by Mila Quality. Good contributors are invited to the core team. Start with CONTRIBUTING.md.
If Mila saves you time, star the repo — it helps other business owners find her. Built a skill or a role? Fork it, send a pull request, or publish your Mila on Mila Market and earn 75% of every sale.
Questions, ideas, show what your Mila does: GitHub Discussions · Bugs: Issues · Security: SECURITY.md · Contributing: CONTRIBUTING.md
Apache-2.0 · © 2026 MILAGPT Coop, Tashkent · "Mila", "MILAGPT" and the logo are trademarks — see TRADEMARKS.md. Claude and Claude Code are trademarks of Anthropic, PBC. Mila is an independent open-source project, not affiliated with, endorsed or sponsored by Anthropic.
| CRM of dialogs, promises and tasks, owner cards, weekly rhythm, mailings |
| general skills (ClawHub) |
| general skills |
| self-written skills |
| What waits for the owner's yes | partly: send-guard stops messages to chats the owner didn't connect, keys and internals; broadcasts from your bot and paid work above the limit wait for the owner's ✅ (bot-send, spend); ordinary replies in connected chats are not gated | exec approvals, Team preset | approval for credential use, self-modification and new chats; ordinary messages are not gated | approval for dangerous shell commands (fail-closed); no approval step for sending messages |
| Spending limits | yes (spend: forecast, approval above the limit) | no data | no data | usage limits per plan (Nous Portal) |
| Your Mila moves with you | mila export / mila restore | Markdown memory files | per-group folders | own memory store |
| License | Apache-2.0 | MIT | MIT | MIT |
| Price | free, open source; setup help — MilaGPT Studio | free, self-host only | free; enterprise on request | free; Nous Portal $0-200/month |