Yes. skybridge runs. Argusic installed and launched it on a clean machine in 39 minutes, hitting 3 errors on the way, and recorded the session.

How did Argusic test skybridge?

On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8bc3175dcfd6. One attempt is recorded, and the full method is on the methodology page.

What did it cost to test skybridge?

The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.

How long does skybridge take to install?

39 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.

Does skybridge need a GPU?

Not to start. Argusic reached a running state on a machine with no GPU.

What goes wrong when installing skybridge?

3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.

Where is the evidence for skybridge?

The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

skybridge

Skybridge is a full-stack TypeScript framework for MCP Apps and ChatGPT Apps. Type-safe. React-powered. Platform-agnostic.

Runssource: GitHub homepageTypeScriptMITcommit 8bc3175dcfd6

TypeScript, MIT licensed. The project labels itself: agent, ai, apps sdk, chatgpt, claude, claude code, devtools and ext apps.

skybridge runs. An Argusic agent installed it in 39 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Skybridge monorepo installs, builds, and all 476 unit tests pass across all packages (core, vite-plugin, devtools, create-skybridge, test). The CLI reports skybridge/1.0.0 and responds to --version and --help commands.
What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict: Runs
Argusic Score: 100 / 100
cost of the verifying run: $0.09 (measured)
recorded runs: 1
last tested: 2026-10-04
stars: 2,133
forks: 139
open issues: 55
watchers: 8
size: 48 MB
created: 2025-10-07
last push: 2026-10-02

Subject data from GitHub, linked at the top of this page, refreshed 2026-10-04. Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing skybridge, drawn from the recorded run — Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

Node.js v18.19.1 below required v24.18.08 minutes
pnpm not found in PATH1 minute
Vite-plugin 2 tests timed out at 5000ms when run concurrently from root via pnpm -r, due to @babel/core cold-start latency

Install time: 39 minutes
Cold machine to finish: 44 minutes
Errors hit and fixed: 3 hit, 3 fixed with no human help
How the result was proved: pnpm -r test:unit: packages/core 405/405 passed, packages/create-skybridge 8/8 passed, packages/vite-plugin 15/15 passed, packages/devtools 23/23 passed, packages/test 25/25 passed = 476 passed, 0 failed; pnpm build all packages succeeded; node ./bin/run.js --version returned skybridge/1.0.0
Model tokens used: 66,132
Exact commit tested: 8bc3175dcfd6
Container image: sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory: this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run: each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**Summary of what was done:**
- Installed Node.js v24.18.0 (was v18.19.1, below the required v24.18.0)
- Installed pnpm v10.34.5 (was not installed)
- Ran `pnpm install` (includes prepare script which builds all packages)
- Ran unit tests across all packages: **476 tests passed, 0 failed**
  - `packages/core`: 405 passed
  - `packages/create-skybridge`: 8 passed
  - `packages/vite-plugin`: 15 passed
  - `packages/devtools`: 23 passed
  - `packages/test`: 25 passed
- `pnpm build` from root completed successfully
- CLI binary reports `skybridge/1.0.0 linux-x64 node-v24.18.0`

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

Reached a running state on a clean machine, with the session recorded.
Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
Ran without a GPU, so it does not need one to start.
Licensed MIT, as reported by its host.

What did not, or is not known

Took 39 minutes to install, slower than the median of the 68 comparable projects Argusic has measured.
Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 69 agent projects Argusic has installed and timed, skybridge was the 66th fastest to reach a running state, and 47 of 69 reached one at all.

What it is a reasonable choice for

Trying it on a laptop or a small server: it reached a running state without a GPU.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested by	attempt	outcome	score	cost USD	when
Argusic Runner	1/3	Runs	100.00	0.09	2026-10-04 14:00 UTC

Topics (from GitHub)

agent ai apps-sdk chatgpt claude claude-code devtools ext-apps llms mcp mcp-apps mcp-server mcp-ui modelcontextprotocol openai react skills tooling typescript

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/skybridge.svg)](https://argusic.com/subject/skybridge)

Questions

Does skybridge run?: Yes. skybridge runs. Argusic installed and launched it on a clean machine in 39 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test skybridge?: On a fresh, disposable machine, with every command recorded and the repository pinned at commit 8bc3175dcfd6. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test skybridge?: The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does skybridge take to install?: 39 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does skybridge need a GPU?: Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing skybridge?: 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does skybridge compare with the alternatives?: Of the 69 agent projects Argusic has installed and timed, skybridge was the 66th fastest to reach a running state, and 47 of 69 reached one at all.
Where is the evidence for skybridge?: The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.