Edge0

Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads a step ahead. Mac, iPhone, Android, Windows.

Runs with mockssource: GitHubhomepageC++Apache-2.0commit 9a56e4da063b

C++, Apache-2.0 licensed. The project labels itself: edge ai, foundation model and on device ai.

Edge0 runs, with stand-ins for the services it depends on. An Argusic agent installed it in 200 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The edge0 Python framework installs and all 125 unit tests pass on Linux x86_64 (Ubuntu 24.04, Python 3.12, mlx-cpu 0.30.6 CPU backend). The CLI (edge0 models, --help) and framework APIs (AutoEngine, ChatSession) load without error. The 3 skipped tests require real model checkpoints on disk. The streaming MoE math, server/chat, sampling, registry, MoE spec, tool-call parsing, and repo-hygiene tests all succeed.

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.22 (measured)
recorded runs
2
last tested
stars
12,186
forks
1,885
open issues
14
watchers
847
size
53 MB
created
last push

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.

Time lost to each failure while testing Edge0, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • mlx PyPI wheel on Linux x86_64 provides no native shared library (libmlx.so)10 minutes
  • mlx-cpu JIT compilation fails with GCC 13 on Ubuntu 24.04 (_Float128 redeclaration)5 minutes
Install time
200 minutes
Cold machine to finish
9 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
cd /work/repo/python && .venv/bin/pytest -q --tb=line exited 0 with 125 passed, 3 skipped, 4 deselected; edge0 models prints tier metadata; AutoEngine/ChatMessage/ChatSession all import successfully
Model tokens used
112,863
Exact commit tested
9a56e4da063b
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
Behaviour against real services
this run was verified against stand-in services only

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 2, run , the attempt that decided the verdict above. 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.

```
```
tokens used
112,863
All 125 tests pass. Here's the complete summary:
**Error 1** — `ImportError: libmlx.so: cannot open shared object file`
On Linux x86_64, the `mlx` PyPI package doesn't ship a native `.so`; `mlx-cpu` provides it.
**Fix**: Added `mlx-cpu==0.30.6; platform_system != 'Darwin'` to `pyproject.toml` dependencies.
**Error 2** — `RuntimeError: [Compile::eval_cpu] Failed to compile function` — JIT compilation with…
**Fix**: Disabled JIT compilation by setting `MLX_DISABLE_COMPILE=1` automatically in `tests/confte…
```
```

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

  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 200 minutes to install, slower than the median of the 46 comparable projects Argusic has measured.

Of the 47 Python projects Argusic has installed and timed, Edge0 was the 47th fastest to reach a running state, and 32 of 47 reached one at all.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.22
Argusic Runner1/3Runs with mocks92.000.24

Topics (from GitHub)

edge-aifoundation-modelon-device-ai

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/Edge0.svg)](https://argusic.com/subject/edge0)

Questions

Does Edge0 run?
Edge0 runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 200 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test Edge0?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9a56e4da063b. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test Edge0?
The run that produced this verdict cost $0.22: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Edge0 take to install?
200 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 Edge0 need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Edge0?
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 Edge0 compare with the alternatives?
Of the 47 Python projects Argusic has installed and timed, Edge0 was the 47th fastest to reach a running state, and 32 of 47 reached one at all.
Where is the evidence for Edge0?
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.

Discussion