ag-ui
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
Runssource: GitHubTypeScriptMITcommit b8ebd02c84a3
TypeScript, MIT licensed. The project labels itself: ag ui protocol, agent frontend, agent ui, agentic workflow and ai agents.
ag-ui runs. An Argusic agent installed it in 2 minutes and hit 1 error on a clean machine with no GPU, and the whole session was recorded.
The AG-UI monorepo installs, builds (35/35 projects), and tests (5576 passed, 1 dotnet-only failure due to dotnet not being available in the container) under Node.js v22.23.3. The dojo demo viewer serves HTTP 200. The core SDK (@ag-ui/core, @ag-ui/client, @ag-ui/encoder, etc.) exports a working protocol implementation.
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 80 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
- dotnet CLI not found — cross-language .NET test suite fails to build its TestServer
- Install time
- 2 minutes
- Cold machine to finish
- 16 minutes
- Errors hit and fixed
- 1 hit, 0 fixed with no human help
- How the result was proved
- pnpm install exited 0 in 21.2s. nx run-many -t build succeeded for all 35 projects. nx run-many -t test: 5576 passed (+2 todo) across 236 test files in 28 project groups; 1 failure (cross-language dotnet) because dotnet is not installed. dojo web app launched on port 3456 and served HTTP 200 with valid HTML. @ag-ui/core library loads in Node and exports 31 EventType entries, PROTOCOL_VERSION=1.0.
- Model tokens used
- 403,794
- Exact commit tested
- b8ebd02c84a3
- 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.
Now using node v22.23.3 (npm v10.9.9) Tests passed: 5576 (+ 2 todo) Test files: 236 Project groups: 28 exec /bin/sh -lc 'kill %1 2>/dev/null; true' in /work/repo succeeded in 0ms: Now I have everything I need. Let me compile the final result. 2026-09-26T10:31:25.963975Z ERROR codex_core::session: failed to record rollout items: thread 01a0d… tokens used 403,794 Now I have everything I need. Let me compile the final result.
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 2 minutes.
- 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
- Hit 1 error during setup, 1 of which were not solved.
- 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 2 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)
ag-ui-protocolagent-frontendagent-uiagentic-workflowai-agents
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ag-ui)Questions
- Does ag-ui run?
- Yes. ag-ui runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test ag-ui?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b8ebd02c84a3. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ag-ui?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ag-ui take to install?
- 2 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 ag-ui need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ag-ui?
- 1 thing broke in the recorded run. Each one, and the time it cost, is listed on this page.
- Where is the evidence for ag-ui?
- 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.