Edge0
Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Runs with mockssource: GitHubPythonApache-2.0commit 9a56e4da063b
Python, Apache-2.0 licensed.
Edge0 runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The edge0 Python framework installs on Linux x86_64 with EDGE0_BACKEND=mock. 100 unit tests pass (registry, CLI flags, MoE spec resolution, prefill hooks, repo hygiene, server chat/HTTP, tool call parsing). The CLI enumerates both model tiers (edge0-35b, edge0-8b) with full config profiles. AutoConfig/AutoModel/AutoEngine resolve both tiers correctly.
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
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.
- MLX (Apple Silicon) wheel installs on x86_64 Linux but libmlx.so is missing — all MLX code fails at import20 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 26 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- EDGE0_BACKEND=mock .venv/bin/pytest tests/, 100 passed, 7 skipped in 2.91s (excluding 2 test files that import mlx.core directly and require MLX runtime)
- Model tokens used
- 377,414
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
python/src/edge0/streaming/layer.py | 15 ++++++++++++++-
5 files changed, 58 insertions(+), 16 deletions(-)
Now I have all the data. Let me produce the final report.
exec
/bin/sh -lc "cd /work/repo && date +%s && cat /proc/uptime 2>/dev/null | awk '{printf \"uptime: %.0…
succeeded in 0ms:
1791456096
uptime: 1186326 seconds
Here is the final report:
tokens used
377,414
Here is the final 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
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
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 5 minutes to install, slower than the median of the 36 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 37 Python projects Argusic has installed and timed, Edge0 was the 21st fastest to reach a running state, and 20 of 37 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.24 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](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 5 minutes, hitting 1 error 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. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Edge0?
- The run that produced this verdict cost $0.24: 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?
- 5 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?
- 1 thing broke in the recorded run, and 1 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 37 Python projects Argusic has installed and timed, Edge0 was the 21st fastest to reach a running state, and 20 of 37 reached one at all.
- Where is the evidence for Edge0?
- 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.