openmeld
The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex, Claude Code, Grok, Grok Bot, OpenCode, Antigravity, and Cursor.
Runssource: GitHubhomepageTypeScriptMITcommit 82643a14b038
TypeScript, MIT licensed. The project labels itself: agent client protocol, agent orchestration, agent skills, ai agents, claude code, codex, cursor and grok.
openmeld runs. An Argusic agent installed it in 1 minute and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The OpenMeld monorepo builds cleanly (31/31 tasks). The openmeld CLI binary (v0.3.262) runs and prints version and help information. The public documentation dev server serves HTTP 200 on /docs. The desktop Electron application launches and its main process remains alive on the virtual display. The CLI test suite passes 3510 of 3535 tests and the schemas package passes 1761 of 1765 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.
- pnpm build hangs—local-resources memory admission denies heavy build in container with 8GiB constrained memory and 1.6GiB available15 minutes
- Node.js 18 in the environment but repo requires Node 242 minutes
- openmeld-web build fails: cannot resolve origin/main (shallow clone)1 minute
- pnpm/corepack not available with system Node
- 25 of 3535 CLI test failures and 4 of 1765 schemas test failures are pre-existing repo-internal test/source drift
- Install time
- 1 minutes
- Cold machine to finish
- 49 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- pnpm build exited 0 (31/31 tasks); node dist/openmeld.js --version returned 0.3.262; node dist/openmeld.js --help returned usage text; pnpm exec vitest run CLI: 3510 passed, 25 failed (pre-existing); pnpm exec vitest run schemas: 1761 passed, 4 failed (pre-existing); curl -s -o /dev/null -w %{http_code} 127.0.0.1:3691/docs returned 200; electron . stayed alive >30s on DISPLAY=:99
- Model tokens used
- 1,753,010
- Exact commit tested
- 82643a14b038
- 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.
exec /bin/sh -lc 'kill $(pgrep -f "electron/dist/electron '"\\.\" | head -10) 2>/dev/null; kill 38392 2>… succeeded in 0ms: exec /bin/sh -lc 'ps aux | grep -iE "electron|vite" | grep -v grep | grep -v codex | head -3; echo "---"… succeeded in 0ms: --- time used --- 11:32 Good — 11:32, 49 minutes elapsed. Here is my final assessment. tokens used 1,753,010 Good — 11:32, 49 minutes elapsed. Here is my final assessment.
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.
- Recovered from all 5 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
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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
Topics (from GitHub)
agent-client-protocolagent-orchestrationagent-skillsai-agentsclaude-codecodexcursorgrokgrok-bothuman-ai-collaborationknowledge-basemcpmulti-agentopencodeopenmeldtask-managementteam-collaborationworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openmeld)Questions
- Does openmeld run?
- Yes. openmeld runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test openmeld?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 82643a14b038. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test openmeld?
- The run that produced this verdict cost $0.40: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does openmeld 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 openmeld need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing openmeld?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for openmeld?
- 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.