- TESIGN / RADAR
- 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.
17,832 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.
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.shCAVEATS
- 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.
| IMAGE | NAME | ★ TOTAL | ▲ 7d | LICENSE | PLATFORM | LAST PUSH |
|---|---|---|---|---|---|---|
![]() | eccSkills, memory and security for agents | ★ 259k | ▲ +832 | MITpermissive | windows · macos · linux · cli | |
![]() | Hermes AgentSelf-improving personal agent | ★ 246k | ▲ +375 | MITpermissive | linux · macos · windows · android · cli | |
![]() | DeepSeek HarnessPlugin agent harness for developers | ★ 225k | ▲ +1,356 | MITpermissive | web · cli | |
![]() | OpenWorkerDesktop AI coworker for daily tasksTHIS ENTRY | ★ 17.8k | ▲ +39 | MITpermissive | macos · windows | |
| mattpocock/skillsCARD | ★ 261k | ▲ +872 | MITpermissive | — |
TIMELINE
- Repository created
- FIRST SEEN BY TESIGN ◌ BACK CATALOG






