10x

⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted.

Runssource: GitHubhomepageTypeScriptMITcommit 6ea128c31173

TypeScript, MIT licensed. The project labels itself: ai agents, anthropic, claude, claude code, codex, coding agent, continue and gemini cli.

10x runs. An Argusic agent installed it in 1.5 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.

CLI help/version output works, web app returns HTTP 200 on /, 232 of 234 tests pass, and all 4 packages build cleanly; the 2 failing router tests need a real OpenRouter API key which the BYOK design requires.

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

At a glance

verdict
Runs
Argusic Score
91 / 100
cost of the verifying run
$0.01 (measured)
recorded runs
2
last tested
stars
1,367
forks
111
open issues
26
watchers
19
size
16 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 10x, 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.

  • bun runtime not pre-installed; install required0.5 minutes
  • 2 Router stream() tests fail: hit real OpenRouter API with no credentials0.2 minutes
Install time
2 minutes
Cold machine to finish
4 minutes
Errors hit and fixed
2 hit, 1 fixed with no human help
How the result was proved
curl -s -o /dev/null -w '%{http_code}' localhost:3457 returned 200; 'bun run apps/cli/dist/index.js --help' returned help text; 'bun run apps/cli/dist/index.js --version' returned 0.1.0; 232/234 tests passed across @10x/core and @10x/shared
Model tokens used
93,243
Exact commit tested
6ea128c31173
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.

- **Web app** — starts and returns HTTP 200 on `/`
2026-11-15T19:19:55.690040Z ERROR codex_core::session: failed to record rollout items: thread 01a1e…
tokens used
93,243
That's the full picture. Let me compile the report.
**Observations:**
- **bun** wasn't pre-installed; installed via `npm install -g bun` into `~/.npm-global` (no root)
- **`bun install`** completed successfully (423 packages)
- **Build** — all 4 packages (shared, core, cli, web) built fine via `turbo build`
- **Tests** — `@10x/shared`: 50/50 pass; `@10x/core`: 182/184 pass (2 Router stream tests fail hitt…
- **CLI** — `bun run apps/cli/dist/index.js --help` prints usage, `--version` prints `0.1.0`
- **Web app** — starts and returns HTTP 200 on `/`

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 1.5 minutes, faster than the median of the 123 comparable projects Argusic has measured.
  • 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 did not, or is not known

  • Hit 2 errors during setup, 1 of which were not solved.

Of the 124 ai-agents projects Argusic has installed and timed, 10x was the 31st fastest to reach a running state, and 96 of 124 reached one at all.

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 1.5 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

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs90.000.01
Argusic Runner1/3Runs with mocks92.000.07

Topics (from GitHub)

ai-agentsanthropicclaudeclaude-codecodexcoding-agentcontinuegemini-cliopen-code

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/10x.svg)](https://argusic.com/subject/10x)

Questions

Does 10x run?
Yes. 10x runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test 10x?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6ea128c31173. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test 10x?
The run that produced this verdict cost $0.01: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does 10x take to install?
1.5 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 10x need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing 10x?
2 things 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 10x compare with the alternatives?
Of the 124 ai-agents projects Argusic has installed and timed, 10x was the 31st fastest to reach a running state, and 96 of 124 reached one at all.
Where is the evidence for 10x?
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