A personal assistant you install with one command. It runs on your own machine, keeps your to-dos and reminders, makes interactive pages on demand, and learns how you work through a folder of skills i
ProductivityGitHub @OpenAfterHoursOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Repository information has not been collected yet.
No updates detected yet. GitHub releases will appear here.
GitHub star growth between the latest completed 8-hour observations
DeepSeek Harness Remote can securely connect a phone or another computer to the computer where you run DeepSeek Harness, so you can continue your work anytime and anywhere, check progress anytime, and continue working.
AI translation
Open-source, local-first task manager that works offline, syncs every device, runs on a Raspberry Pi, and requires no subscription.
AI translation
Open-source, self-hosted webmail built on JMAP. Email, calendar, contacts, and files in one interface for Stalwart Mail Server.
Open Source Office suite for users used to MS Office - multi-platform, tuned for performance
A personal assistant you install with one command. Small Python core; channels, email and file formats are skills.
Taken from the repository README
Loading the full README.
Read the full README ↗A personal assistant you install with one command. It runs on your own machine, keeps your to-dos and reminders, makes interactive pages on demand, and learns how you work through a folder of skills it can edit itself. The core is under 2,860 lines of Python code, the cap CI enforces; everything else is a skill.
Status: phase 3 of the roadmap: the local core, terminal and web chat; Slack and Signal with group chats, approvals and rate limits; email (Outlook, Gmail, Titan) with a morning triage; email requests from people you list, for your free slots or a job you defined; Word, Excel and PowerPoint files; share links; and starting at login. The cloud arrives in phase 4.
Documentation: https://openafterhours.github.io/attache/.
uvx attache # first run asks your name, creates ~/.attache, then opens a chat
uv tool install attache # keep it
attache chat # terminal chat, plus the web page
attache run # web page, reminders and channels, no terminal chat
attache doctor # check your setup
attache skill mail login gmail # a skill's own setup step, run in your terminal
attache skill service install # start Attaché when you log in
attache skill tui # a full-screen terminal app (docs/terminal.md)
While a turn runs, the terminal shows what Attaché is doing: working…, each step with its
time, a line of Claude's thinking, and a footer with time and tokens. Ctrl+C stops a turn.
The terminal and the web page are one conversation. Attaché prints a link like
http://127.0.0.1:8765/#t=... when it starts; open that link to use the web page. The token in
it changes every run, so other programs on your machine can't drive your assistant.
The web workspace opens on Today: what is waiting for your answer, open to-dos, coming reminders and recent pages, under a message box. A sidebar switches between Today, Chat and owner-only Settings, and opens any page beside them, with a resizable divider; your drafts and open pages stay in place. Settings validates and previews changes before saving, preserves file-managed options, and shows when a restart is needed.
The optional analysis skill connects the same conversation to a Hailer notebook. Saved result pages appear in the workspace; the live notebook opens separately.
Attaché talks to models through four adapters, chosen in ~/.attache/attache.toml:
api | Use it for |
|---|---|
claude-cli | Claude Code (claude -p) on your own login. Your own chats only. |
anthropic | The Claude API, or any Anthropic-compatible base_url |
openai-chat | Ollama, LM Studio, vLLM, llama.cpp, OpenRouter, Groq, Azure |
openai-responses | OpenAI reasoning models with tools |
[routing]
own_chats = "claude" # your Claude login
group_chats = "claude-api" # an API key, per Anthropic's terms
[endpoints.claude]
api = "claude-cli"
model = "claude-sonnet-5-5"
[endpoints.claude-api]
api = "anthropic"
model = "claude-sonnet-5-5"
key_env = "ANTHROPIC_API_KEY"
~/.attache/skills/<name>/SKILL.md (Agent Skills
format). Only names and descriptions go into the prompt. The assistant edits skills when you
change how you work, and ~/.attache is a git repo, so attache skills log and
attache skills undo <name> show and reverse every change.~/.attache/artifacts/. The local web
server adds a small attache bridge so a page can read and write real data with live updates.
Pages run sandboxed: they can't reach the internet or anything outside the data they declare.uv run and talks to over JSON lines. Any chat app can be added the same way:
see docs/channels.md.@attache in an email to you. Attaché checks
the message really came from them (DMARC), then answers in the thread: free slots from your
diary, never what is in it (docs/diary.md), or a job you defined, run in the
background, with "done" or "failed" back to them and the details to you
(docs/jobs.md). Setup is in docs/channels.md.web skill searches (DuckDuckGo, or Brave with a key) and reads pages as
text, for you and your group chats, and reaches only the public internet, never your own
machine or network: see docs/web.md. The skill drives Edge or
Chrome with your sign-in to read the work sites you list, such as SharePoint and Power BI,
for you alone: see .The full design, with the research behind it, is in docs/proposal.html.
See CONTRIBUTING.md: bug fixes and simplifications go in the core, features go in skills.
MIT
browser[web] public_url set and Tailscale Funnel pointed at a second local
port, a group's page gets a link that works on anyone's phone, for that group's shared data
only: see docs/pages.md.claude -p on your own login, for your own chats only.
Attaché's tools reach it through an MCP endpoint on the local web server. It runs in a
working folder next to your home (~/.attache-claude), so nothing written into ~/.attache
can load as Claude Code project settings.