agent-beacon
The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBu
Runssource: GitHubhomepageGoMITcommit 7e47847cf18f
Go, MIT licensed. The project labels itself: agent ai cli, agent harnesses, agent security, browser extension, ci, claude code, cloud and codex.
agent-beacon runs. An Argusic agent installed it in 28 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The Beacon CLI builds, runs, and responds to commands; all Go tests pass (131/131), all TypeScript/Javascript tests pass (307/307), and the built binary correctly reports its version 7e47847.
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 96 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.
- Install time
- 28 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- go test ./... in cli/beacon passed (68/68), go test -race ./internal/endpoint/... passed (37/37), go test ./... in cli/beacon-hooks passed (8/8), go test ./... in pkg/asymptoteobserve passed (6/6), go test ./... in collector-builder/exporter/beaconjsonexporter passed (3/3), go test ./... in beacon-sandbox passed (9/9), npm test in packages/asymptote-sdk-js passed (22/22), npm run test:unit in browser-extension passed (177/177), npm test in browser-extension passed (10/10), bun test in all 7 plugin directories passed (108/108 total). ./beacon version returned 'beacon version 7e47847'.
- Model tokens used
- 210,745
- Exact commit tested
- 7e47847cf18f
- 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
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Everything works as expected — it correctly reports that no endpoint is set up yet (which is fine f… Let me also quickly check the beacon-sandbox test suite already ran. Let me compute approximate ins… exec /bin/sh -lc 'ls -la /tmp/go/bin/go /tmp/node-v22.14.0-linux-x64/bin/node /tmp/bun-extract/bun-linux… succeeded in 0ms: -rwxr-xr-x 1 runner runner 107308936 Nov 9 16:24 /tmp/bun-extract/bun-linux-x64/bun -rwxr-xr-x 1 runner runner 14314681 Feb 10 2025 /tmp/go/bin/go -rwxr-xr-x 1 runner runner 120177224 Feb 11 2025 /tmp/node-v22.14.0-linux-x64/bin/node Good. Here's my comprehensive summary: tokens used 210,745 Good. Here's my comprehensive summary:
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 28 minutes.
- Nothing broke on the way: zero errors between clone and running.
- 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 it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- Following its own README: the documented path worked with nothing to fix.
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 | 0.07 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.09 |
Topics (from GitHub)
agent-ai-cliagent-harnessesagent-securitybrowser-extensionciclaude-codecloudcodexcursordetection-engineeringjevknowledge-basememorymobile-device-managementobservabilitysecuritysecurity-information-and-event-managementsecurity-toolstelemetrytraces
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-beacon)Questions
- Does agent-beacon run?
- Yes. agent-beacon runs. Argusic installed and launched it on a clean machine in 28 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test agent-beacon?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7e47847cf18f. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test agent-beacon?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-beacon take to install?
- 28 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 agent-beacon need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-beacon?
- Nothing did, in the recorded run: zero errors between clone and running.
- Where is the evidence for agent-beacon?
- 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.