openworker - open-source local-first ai coworker with security agents
About OpenWorker
Andrew Ng's open-source desktop agent that hands back finished work instead of chat. It runs on your machine, connects to the tools you already use, and checks in before anything consequential. The August 2026 release added three security coworkers: one drives semgrep and secret scans and triages findings by reachability rather than severity, one checks Terraform against the live cloud read-only and opens infrastructure pull requests, and one audits dependencies. Bring your own API key, or run a local model through Ollama and nothing leaves the machine.
OpenWorker interface preview
Key Capabilities
Returns finished files: documents, spreadsheets, reports and pull requests, not chat transcripts
Security coworker triages scanner findings by reachability, not severity, so you get the handful that matter
Cloud Posture reads live cloud config and lands every fix as a pull request, never applying changes directly
Checks in for approval before anything consequential; the agent cannot grant itself new permissions
Runs fully local through Ollama, in which case no conversation content leaves your machine
Over 25 integrations including GitHub, Slack, Jira, Notion and Linear, plus anything reachable over MCP
Standout Features
Reachability Triage
The security coworker drives semgrep and secret scans, then ranks findings by whether an attacker could actually reach the code, which is the difference between a report you act on and one you close.
Fixes Arrive as Pull Requests
Cloud access is read-only and nothing is applied directly. Terraform drift and dependency upgrades land as pull requests you review and merge.
Local-First by Architecture
Conversations, files, API keys and connector tokens stay on the device and are never stored on OpenWorker servers. With Ollama, no content leaves the machine at all.
Perfect for
Compare OpenWorker
Community Buzz
Community Buzz
No recent posts yet
We are monitoring X for fresh discussions about OpenWorker.
Similar Tools to OpenWorker
Orca
Open-source Agent Development Environment for running a fleet of AI coding agents at once. Every task gets its own git worktree, its own agent terminal, and its own browser tab, so you can fan one prompt across several agents, compare the diffs, and merge the winner. It drives roughly 30 CLI agents you already pay for, including Claude Code, Codex, OpenCode, Cursor and Copilot, and ships on macOS, Windows, Linux, iOS and Android.
Parallel Code
Free, open-source desktop app that dispatches AI coding agents in parallel, each in its own git worktree. It runs the real CLI agents you already trust (Claude Code, Codex, Gemini) side by side, then lets you review the diffs, merge the wins, and toss the rest.
Vibe Kanban
Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.
Hermes Agent
Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.
Hermes WebUI
Lightweight dark-themed browser interface for Hermes Agent with full parity to the CLI. Three-panel layout with sessions sidebar, chat, and workspace file browser. Community project that runs against any existing Hermes install.
Vibe80
Apache-2.0 web workspace that orchestrates Codex and Claude Code over your Git repositories in sandboxed parallel worktrees, with a PTY web terminal and a mobile companion app that picks up a session by QR code.
ready to try openworker?
go to the official site and judge OpenWorker yourself.
try openworker now