nimbalyst
Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents in parallel, edit their work visually in markdown, mockups, and diagrams, and track tasks. Free, MIT-licensed desktop app for macOS, Windows, Linux, with mobile companion for iOS and Android.
Runssource: GitHubhomepageTypeScriptMITcommit 34b14f33e48f
TypeScript, MIT licensed. The project labels itself: agentic ai, agentic ide, ai agents, ai coding assistant, claude code, codex, coding agent and developer tools.
nimbalyst runs. An Argusic agent installed it in 41 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Nimbalyst monorepo installs, builds (runtime, extension-sdk, collab-bundle), and passes its full vitest unit test suite with 1546 passing test files and 12983 passing tests.
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
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.
- zip command not found (marketplace tests)3 minutes
- extension-sdk dist missing; collab-bundle build failed3 minutes
- OOM during runtime build with default heap2 minutes
- unzip command not found (marketplace tests)2 minutes
- collab-bundle dist missing; docsUiStoreBinding test failed2 minutes
- Node 18 installed but project requires Node 24+1 minute
- Install time
- 41 minutes
- Cold machine to finish
- 41 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- npm run test:unit -- --run exited 0; 1546 files passed, 12983 tests passed, 0 failed
- Model tokens used
- 262,726
- Exact commit tested
- 34b14f33e48f
- 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.
Total elapsed: ~41 minutes === ERRORS FIXED === 1. Node 18 -> Node 24 (required v24) 2. OOM on runtime build (needed --max-old-space-size=8192) 3. zip command not found (created Python shim) 4. unzip command not found (created Python shim) 5. extension-sdk needed building before collab-bundle 6. collab-bundle needed building for docsUiStoreBinding test Now generating the final ARGUSIC_RESULT report. tokens used 262,726 Now generating the final ARGUSIC_RESULT report.
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 6 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.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 41 minutes to install, slower than the median of the 7 comparable projects Argusic has measured.
Of the 8 agentic-ai projects Argusic has installed and timed, nimbalyst was the 8th fastest to reach a running state, and 5 of 8 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
Topics (from GitHub)
agentic-aiagentic-ideai-agentsai-coding-assistantclaude-codecodexcoding-agentdeveloper-toolselectronidekanbanmarkdown-editormcpmulti-agent-systemsopencodeworktree-managerwysiwyg-editor
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/nimbalyst)Questions
- Does nimbalyst run?
- Yes. nimbalyst runs. Argusic installed and launched it on a clean machine in 41 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test nimbalyst?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 34b14f33e48f. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test nimbalyst?
- The run that produced this verdict cost $0.16: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does nimbalyst take to install?
- 41 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 nimbalyst need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing nimbalyst?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does nimbalyst compare with the alternatives?
- Of the 8 agentic-ai projects Argusic has installed and timed, nimbalyst was the 8th fastest to reach a running state, and 5 of 8 reached one at all.
- Where is the evidence for nimbalyst?
- 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.