mrkeyoor.comAsk

different-ai/openworktested 01 Oct 2026commit 53f090c

openwork review

OpenWork installed 1,769 dependencies in our sandbox, but its source build and test commands both exited unsuccessfully.

  • Build failed
  • Tests failed
159 sto install
  • 1,769 packages
AI Toolsevaluationupdated 03 Nov 2026
+33stars / 7d

OpenWork is an OpenCode-based desktop app that lets AI agents work on files in a workspace, with a choice of model providers or local models. It also lets teams distribute skills and connected capabilities to existing agents through MCP, the protocol used to connect assistants to tools.

Verdict

OpenWork installed 1,769 dependencies in our sandbox, but its source build and test commands both exited unsuccessfully. It is worth evaluating for a desktop workspace or shared agent capabilities, provided you choose the relevant deployment and licensing route first. Our missing-Bun test failure leaves application behavior unverified, and the build tail is too short to diagnose. Try one real file task or authenticated capability before asking colleagues to depend on it.

We ran it

Lab card: what happened when we ran openwork
Lab card from our sandbox run
Screenshot of openwork (openworklabs.com)
openworklabs.com
Install✓ · 159s1769 packages · 2364 MB
Build✗ · 188s
Tests✗ · 7sran, no count parsed
Repo5690 files~1,022,900 lines of source · 149.9 MB · 42 CI workflows

Answers from our run

Does openwork build from source?

Dependencies installed in 159 seconds (1769 packages), and the build failed. We cloned commit 53f090c into a clean Debian container with 3 CPUs and no project-specific setup.

Do openwork's tests pass?

No. The project's own test command exited unsuccessfully after 7 seconds, and its output did not expose an individual test count.

Who should not use openwork?

Organizations requiring the entire team control plane under MIT: the README puts OpenWork Den under a separate source-available license with production subscription terms and exceptions.

What are the alternatives to openwork?

OpenCode, Ollama. OpenWork installed 1,769 dependencies in our sandbox, but its source build and test commands both exited unsuccessfully.

Setup2/5Our source checkout installed but the build failed.Editor’s note: Not assessed: installation was not reproduced in a supported environment; the measured source build and test commands failed.
Docs3/5The README explains desktop, MCP and Den routes, licensing and development profiles. Its contributor prerequisite list does not mention the Bun executable invoked by our recorded test command.
Community5/5Last push on 2026-11-03 and 24,521 stars.Editor’s note: Recent pushes and pull requests show activity, but we did not establish support responsiveness or maintainer capacity.
Maturity2/5Latest release v0.18.63 on 2026-10-26 (pre-1.0), repository created 2026-01-14 and its test suite did not pass in our sandbox.Editor’s note: Release notes document shipped work, but our run did not verify desktop tasks, connected capabilities or production reliability.

How we score

Discussed on

  1. hnShow HN: OpenWork – An open-source alternative to Claude Cowork231 points

Who it’s for

People who want a dedicated desktop workspace for agent tasks on macOS, Windows or Linux.
Teams that want colleagues to reuse assigned skills and connections from their existing agent clients.
Developers willing to investigate the source toolchain separately from evaluating the downloaded desktop app.

Who it’s NOT for

Organizations requiring the entire team control plane under MIT: the README puts OpenWork Den under a separate source-available license with production subscription terms and exceptions.
People expecting the hosted MCP route to work without an account: its documented flow requires browser sign-in and organization selection.
Contributors relying on Node and pnpm alone for the measured test command: our run stopped at a Bun invocation because that executable was missing.

Setup reality

In our October 1, 2026 sandbox run at 53f090c, installation succeeded in 159 seconds, recording 1,769 dependencies and 2,364 MB on disk. The build failed with exit 1 after 188 seconds. Tests failed with exit 1 after 7 seconds: the log says bun: not found. The build tail does not expose its underlying cause.

The README offers desktop downloads separately from contributor setup. Local desktop use needs no OpenWork account, but model access needs a chosen provider connection or local model service. The hosted MCP route requires sign-in and organization selection. Den's production licensing depends on organization size and use.

The sandbox configuration recorded 3 CPUs, 8 GB RAM and image lab-node:22. The build log identifies Node.js v24.19.0, so the label does not establish Node 22 execution. The current contributor README lists Node 24 and pnpm 11. Our source run did not verify a desktop launch or authenticated MCP action.

Local desktop use and team sharing have different terms

OpenWork's desktop app can work without an OpenWork account, while its hosted MCP connection asks you to sign in and choose an organization. Decide which route you need before treating OpenWork as one deployment. Someone trying an agent on local files has a different evaluation ahead of them from an administrator distributing capabilities across colleagues' tools.

The README describes a desktop workspace built on OpenCode, with provider connections and local models through Ollama. That makes it interesting if you want to choose the model while keeping a dedicated place for file-based work. We did not measure whether an agent completed a task correctly or how well any model followed instructions.

Shared capabilities can reach the agent you already use

The documented OpenWork MCP exposes capability search and execution, plus tools to list skills and read a selected SKILL.md. Its examples cover Codex, Claude Code and OpenCode. A team can therefore investigate distributing skills without requiring every colleague to adopt the desktop interface.

The practical question is what each person can discover and execute after signing in. Den documents assignments to organizations, teams and individuals, along with provider access and desktop policies. For an evaluation, choose one intended capability, assign it to a limited audience and check its behavior from the client those people use. This is a proposed trial, not an action completed in our sandbox.

The README's local-file language also deserves a careful reading. It supports local models as an option, alongside remote providers and connected services. A deployment decision still needs the chosen model's data handling and each connection's permissions. Our evidence contains no network inspection or security assessment.

What happened when we ran it

Our October 1, 2026 run at commit 53f090c completed dependency installation in 159 seconds, recording 1,769 dependencies and 2,364 MB on disk. The source build exited 1 after 188 seconds, and the test command exited 1 after 7 seconds. Those are repository setup results, with no recorded desktop task or authenticated capability execution.

The test log reached the app's Bun-based command and printed sh: 1: bun: not found, followed by a spawn error and the failed lifecycle status. That establishes a missing executable at that stage. It provides no passing assertion count and no basis for saying the product's application tests exposed incorrect behavior.

The supplied build tail contains a child-process failure, JavaScript stack frames and the lifecycle exit. It does not identify the command's underlying error. Assigning the build failure to Bun as well would go beyond this evidence. Getting dependencies onto disk was successful; completing the source build was not.

The configured sandbox had 3 CPUs and 8 GB RAM under image label lab-node:22. The actual build tail says Node.js v24.19.0. The image name therefore cannot establish the runtime version. The checkout scan recorded 42 CI workflow files and monorepo workspaces. Its failure to detect a tests directory does not establish an absence of coverage: the current README locates executable coverage under evals/specs.

Den changes the licensing decision

The README places code outside ee/ under MIT and OpenWork Den under the OpenWork EE License. Den's code is source-available, with production subscription requirements and exceptions. The stated exceptions include organizations with up to five users, evaluation for 30 days at any size, and development use. Enterprise releases convert to MIT after two years.

If your procurement rule requires an MIT team control plane, that distinction can end the evaluation early. If your organization qualifies for an exception, read the applicable terms before assuming the exception covers the deployment you intend. The free local desktop does not settle Den's licensing for a larger organization.

Current releases do not validate our older checkout

GitHub records a November 3, 2026 push, and the recent activity feed includes pull requests updated that day. The October 26 v0.18.63 release describes Claude-history imports and connected-file transfers requiring approval. Together these show ongoing development, rather than support for an abandonment claim. They do not establish response times or released-product reliability.

That release came after our October 1 source run. Its transfer and import features remain upstream descriptions here. If those features are why you want OpenWork, evaluate the intended release with representative files and permissions instead of using our source timings as a proxy for their behavior.

OpenCode and Ollama answer narrower requirements

OpenCode describes an open-source coding agent and offers terminal and desktop interfaces. Start there if coding is your main requirement and OpenWork's organization assignments add little to your workflow. OpenWork itself uses OpenCode, so this is a choice about the surrounding workspace and sharing features.

Ollama documents a REST API for running and managing models. Choose it when the missing component is model access for an application you already have. It is also a documented local-model option for OpenWork. We have no comparative speed or reliability measurements for either alternative.

Documentation earns 3/5 on a limited editorial scale: 1 means a route cannot be followed from the material read, 3 means useful instructions with an unresolved requirement, and 5 requires instructions verified across the reviewed routes. OpenWork explains its routes well, but our observed Bun requirement remains unresolved by the contributor prerequisite list. Other dimensions remain unassessed. Before rollout, make the proposed file task or shared capability succeed with the permissions your colleagues will actually have.

Alternatives

ProjectWhat it isPick it when
OpenCode gh↗An open-source AI coding agent with terminal and desktop interfaces.Pick OpenCode directly when coding is the main job and you do not need OpenWork's shared-capability layer.
Ollama gh↗A model runtime with a REST API for running and managing models.Pick Ollama when model access through an API is the requirement. It can also supply local models to OpenWork, so these tools can be used together.

Sources

  1. OpenWork README
  2. OpenWork repository facts
  3. OpenWork v0.18.63
  4. OpenCode README
  5. Ollama README
  6. OpenWork recent issue and PR activity

More ai tools reviews