What is Taskuary and who is it for?

A personal AI assistant for your job that runs on your machine. Mail, chats and tickets become tasks, the coding agents you already use do the work, and nothing is sent until you approve it. It is open source with no subscription.

How is it different from hosted assistants?

The README compares it directly with Fyxer: Taskuary is free and open source, runs on your machine, and hands work to agents you already use rather than running its own hosted service.

Which agents can it drive?

Claude Code, Codex, Qwen Code, OpenCode, Kimi Code, Gemini, Cursor, Copilot, Muse Code and other coding CLIs. You connect a CLI once, give agents profiles with their own instructions, then follow sessions and answer questions from Taskuary.

Does it send anything without me?

No. The agent works inside the task card and drafts, but the prepared reply waits on the task until you read it, edit it if needed, and choose Approve & send.

What are the requirements?

Python 3.10+ per the badge, and the package is on PyPI as taskuary. The README recommends trying the browser demo first — one guided task with fictional data where nothing connects or sends.

Does Taskuary use Jev?

The README documents no Jev integration; the item appears here because it is listed in logicwr's awesome-jev collection. Its triage and agent work run through the connected coding CLIs and their models.

Is it stable enough for daily use?

It is early: currently v0.3.8.3, and the README warns breaking changes are still possible before 1.0. It does ship CI and an OpenSSF Scorecard badge, and the repository was pushed to on 2026-10-15.

Jev directory

CommunityJev Tools & CLIs

Taskuary

A local, open-source personal AI assistant for your job: mail, chats and tickets become tasks, agents you already use such as Claude Code, Codex and Gemini do the work, and nothing is sent until you approve. The current release is v0.3.8.3.

See highlights Open github.com

Stars: 140
Language: Python
License: MIT
Reading time: 2 min
Published by: Community
Author: ldbumble
Last verified: Oct 2026

ldbumble/taskuary

User repository on GitHub

View on GitHub

Your work, already underway. A personal AI assistant for your job: mail, chats and tickets become tasks, the agents you already use (Claude Code, Codex, Gemini) do the work, and nothing goes out until you approve. Open source, runs on your machine.

Forks: 54
Last pushed: Updated Oct 2026

Repo stats from the GitHub API, cached Oct 2026.Homepage

Tagscommunity catalog-import logicrw tasks assistant

Works forJev for Routing Jev for Tool calling Jev for Classification

Used inJev for Software & DevTools Jev for Customer Support

Languages: Python
Platforms: MCP CLI
Capabilities: Open sourceSelf-hostedRuns locally

Highlights

Mail, chats, issue trackers, alerts and reports land on one rail sorted into Urgent, On you, Agents working, Reports and FYI.
The agents you already use — Claude Code, Codex, Qwen Code, OpenCode, Kimi Code, Gemini, Cursor, Copilot, Muse Code — work inside the task card.
Nothing goes out until you review the prepared reply and choose Approve & send; you can edit it or regenerate it with AI first.
Compared with hosted assistants like Fyxer, the README pitches Taskuary as free, open source and running on your machine with no subscription.
Early software: currently v0.3.8.3, so breaking changes remain possible before 1.0.

Watch out

Copy reviewed against the repo README and GitHub metadata on 2026-10-15; the README documents no Jev integration, so the item is included for its appearance in logicwr's awesome-jev listing. It is pre-1.0 software, and the browser demo uses fictional data with scripted agent work.

Questions about this entry

Short answers drawn from the linked project or page.

From the Jev guides

Original write-ups on what this entry is for.

Jev at home: voice pipelines, Assist routing, and sentinels

Oct 16, 2026

How Home Assistant conversation agents, macOS voice pipelines, and an advisory sentinel put a fast typed decision in the loop — one call per utterance, thresholds in code, and a daily token budget.

Jev Tools & CLIs#home-assistant#voice#automation

Read article

Search visibility, audited by decisions

Oct 16, 2026

Jev-based SEO tools split the crawl from the call: deterministic crawlers count and parse, while typed judgments rank fixes, place internal links, score search results, and track AI-answer mentions — with costs and caveats attached.

Jev Tools & CLIs#seo#search-visibility#audits

Read article

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

From the Jev AI model community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Taskuary

Highlights

Questions about this entry

What is Taskuary and who is it for?

How is it different from hosted assistants?

Which agents can it drive?

Does it send anything without me?

What are the requirements?

Does Taskuary use Jev?

Is it stable enough for daily use?

More Jev resources like this

From the Jev guides

From the Jev AI model community