TESIGN
SAVED

EN · KO

  1. TESIGN / RADAR
  2. OpenWorker

OpenWorker

Desktop AI coworker for daily tasks

WHO USES ITDevelopers automating code and dependency security checks · Knowledge workers juggling tools · Teams designing agent governance

Install to use

Desktop AI coworker on your key or local Ollama; 25+ integrations, asks before acting.

★ 17.8k▲ +39 / 7dDaily star increases over 14 days. Hollow bars mean no data. The last day may be partial.2026-09-03 no data2026-09-04 +52026-09-05 +62026-09-06 +52026-09-07 +22026-09-08 no data2026-09-09 no data2026-09-10 no data2026-09-11 +22026-09-12 +42026-09-13 +62026-09-14 +22026-09-15 +222026-09-16 +3largest one-day increase in the 14 days+22last 14 days · stars per dayhollow = no data

17,832 stars · checked on GitHub GitHub check 30 h late · incl. +12 observed via GH Archive since then · 7-day +39 observed via GH Archive (as of )

BACK CATALOG

TESIGN TAKE

The weight of this project is not model choice but a governance design where the agent cannot grant itself new permissions, and the whole of it can be read in the repo; it is still open beta, already past 17k stars.

INSTALL

AT A GLANCE

LICENSE
MIT
USAGE
Use, change and redistribute, commercially too. Keep the notice.
LANGUAGE
Python
PLATFORM
macos · windows
ACTIVITY
last commit 13 days ago () · latest release v0.2.1 () · 6 releases
COMMUNITY
23 contributors · 506 open issues (incl. PRs) · made by: an individual
SOURCES
GitHub
OPEN SOURCE
YES
FIRST SEEN
CATEGORY
AI · PRODUCTIVITY

A summary, not legal advice.

WHY IT MATTERS

An open-source AI coworker for the desktop that aims to hand back finished work rather than answers — a code review with vulnerability fixes ready, a document, a Slack reply with the numbers, a triaged inbox — shipping specialist Security coworkers first. It runs on your own key for OpenAI, Anthropic, Google and others or fully local via Ollama, and connects 25+ tools such as GitHub, Slack, Jira, Notion, Gmail and Google Calendar plus anything over MCP. Sending a message, changing a calendar or running a command is approval-gated by default, a set of 'hard floor' operations stays human-only even in auto-approve mode, and every tool call is logged with its approval provenance.

BUILD FROM THIS

  • Run scheduled automations — a morning brief, a weekly report, a standing watch over a channel — with full transcripts, or a team workflow where mentioning @OpenWorker in Slack opens a session on your desktop and returns the answer as a thread reply. The engine sits on aisuite (Python), so it also serves as a reference implementation for building your own agent harness.

WHO IT'S FOR

Developers automating code and dependency security checks
reviews that combine scanners such as semgrep with model reasoning, fixes re-scanned before approval
Knowledge workers juggling tools
prep a customer call from CRM and inbox, handle calendar and Slack threads
Teams designing agent governance
a reference for approval ladders, hard floors and audit trails

START IN 5 MINUTES

# 1. Download for macOS (Apple Silicon, macOS 12+) at https://download.openworker.com/mac or Windows 10/11 x64 at https://download.openworker.com/windows, open the app, add a model key (or point it at Ollama), and ask for a task
# 2. From source (Python 3.10+, Node 20+, Rust toolchain; see the README for the server and UI steps that follow):
# git clone https://github.com/andrewyng/openworker
# cd openworker
# bash packaging/setup_dev_env.sh

CAVEATS

  • MIT licence. Open beta per the README — usable, still being polished.
  • The macOS build is Apple Silicon only (macOS 12+, signed and notarized, auto-updates); the Windows x64 build is not yet code-signed so SmartScreen warns, and the homepage still lists Windows as 'coming soon'. No Linux build in the README.
  • Model costs are on your own key (or local Ollama). The only cloud component is a small OAuth-brokering service for connectors; the app also works without sign-in using API keys. PRs outside the roadmap may not be approved.

RECEIPT

FIRST SEEN
AT SOURCE
KEPT
STAR DELTA
+9 ★ / 24h
CREATED → FIRST SEEN
55d
SOURCES
GitHub
◌ BACK CATALOG
Reconstructed from archive data, not a live discovery.

The same facts in machine-readable form — View as Markdown · JSON

SIMILAR TOOLS

Up to five from AI by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation.

IMAGENAME★ TOTAL▲ 7dLICENSEPLATFORMLAST PUSH
ECC README banner: headline 'The operating system for AI agent harnesses', harness chips, and skill, agent and command lists.
eccSkills, memory and security for agents★ 259k▲ +832MITpermissivewindows · macos · linux · cli
Hermes Agent landing: blue background, the headline 'The agent that grows with you' and an engraving-style winged figure.
Hermes AgentSelf-improving personal agent★ 246k▲ +375MITpermissivelinux · macos · windows · android · cli
DeepSeek Harness landing: blue background, the headline 'Everything is a plugin' and a quick-start box with the npx command.
DeepSeek HarnessPlugin agent harness for developers★ 225k▲ +1,356MITpermissiveweb · cli
The scripted demo panel on the openworker.com landing page (not a capture of the app itself): a Security coworker summarising '4 of 25 findings are real — fix branch ready', a diff pinning GitHub Actions to commit SHAs, and an approval prompt 'Open PR security/pin-actions? · Leaves this Mac → GitHub'
OpenWorkerDesktop AI coworker for daily tasksTHIS ENTRY★ 17.8k▲ +39MITpermissivemacos · windows
mattpocock/skillsCARD★ 261k▲ +872MITpermissive

TIMELINE

  1. Repository created
  2. FIRST SEEN BY TESIGN ◌ BACK CATALOG