nitrostack
The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps.
Runssource: GitHubhomepageTypeScriptApache-2.0commit 4c1a1c472d8e
TypeScript, Apache-2.0 licensed. The project labels itself: agentic ai, ai, chatgpt, chatgpt apps, claude, claude apps, mcp and mcp client.
nitrostack runs. An Argusic agent installed it in 1 minute and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All three NitroStack packages (core, cli, widgets) build and all 892 tests pass on Node.js 18.19.1. The CLI binary responds to --help. The core server starts over stdio, initializes, lists tools, and executes tools successfully.
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 60 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Widget bridge tests fail in full suite due to jsdom having window.parent === window as a read-only computed property (Object.defineProperty cannot override it)20 minutes
- @modelcontextprotocol/server v2 SDK uses bare `crypto.randomUUID()` which is not available as a global in Node.js 18 module context (only -e eval)15 minutes
- Install time
- 1 minutes
- Cold machine to finish
- 75 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm test on all 3 packages: core 60 suites / 707 tests passed, cli 11 suites / 76 tests passed, widgets 10 suites / 109 tests passed; stdio smoke test passed end-to-end
- Model tokens used
- 563,736
- Exact commit tested
- 4c1a1c472d8e
- 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.
- `widget-polyfill.test.ts`: Same change for its `frameWidget`/`unframeWidget` helpers 2026-10-03T18:53:08.425405Z ERROR codex_core::session: failed to record rollout items: thread 01a10… tokens used 563,736 All tests pass. Let me compile the final results: **Fixes applied:** 1. **Core package** (`@nitrostack/core`): Added `jest.setup.cjs` with a `crypto` shim for Node.js 1… 2. **Widgets package** (`@nitrostack/widgets`): Fixed test isolation issues and jsdom compatibility: - `widget-polyfill.ts`: Changed the framing check in `rpcCall` from strict `window.parent === wi… - `WidgetLayout.tsx`: Same fix for its `callParentRpc` and ResizeObserver postMessage calls - `WidgetLayout.bridge.test.tsx`: Changed mocking strategy to mock `window.postMessage` directly… - `widget-polyfill.test.ts`: Same change for its `frameWidget`/`unframeWidget` helpers
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.
- Installed in 1 minute, faster than the median of the 12 comparable projects Argusic has measured.
- Recovered from all 2 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 Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 13 agentic-ai projects Argusic has installed and timed, nitrostack was the 1st fastest to reach a running state, and 9 of 13 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.
- A quick evaluation: it was running 1 minutes after the clone.
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 | 2/3 | Runs | 100.00 | 0.82 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.07 |
Topics (from GitHub)
agentic-aiaichatgptchatgpt-appsclaudeclaude-appsmcpmcp-clientmcp-servermcp-serversmcp-toolsmcpagentsmcpappsmodel-context-protocolmodelcontextprotocol
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/nitrostack)Questions
- Does nitrostack run?
- Yes. nitrostack runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test nitrostack?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4c1a1c472d8e. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test nitrostack?
- The run that produced this verdict cost $0.82: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does nitrostack take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does nitrostack need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing nitrostack?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does nitrostack compare with the alternatives?
- Of the 13 agentic-ai projects Argusic has installed and timed, nitrostack was the 1st fastest to reach a running state, and 9 of 13 reached one at all.
- Where is the evidence for nitrostack?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.