devXOS

commit → merged → stabilized → survived

Measure what survives, not what ships.

Your team ships more than ever. devXOS reads the Git history behind it and separates the code that lasted from the code that just landed — and shows whether AI is helping it last.

stabilization_ratio

Shipping got cheap. Proof got expensive.

AI tools multiplied your commits and halved your cycle time. Every dashboard is green — and none of them can tell you whether the code holds. The metrics that mattered before AI measure motion. The ones that matter now measure what remains.

velocitythroughputcycle_time
stabilizationdurabilitysignal_vs_noise

stabilization_by_origin

79% vs 64%

AI-assisted code stabilized more often than human code in our validation set — the point is that now you can see it.

attribution_gap

45%

of commits labeled "human" moved at AI velocity. Attribution is a measurement problem, and devXOS treats it like one.

3,497 commits · 1,211 PRs

58 repos

Every metric validated on a real organization before it shipped: 58 repositories, 3,497 commits, 1,211 merged PRs.

harness_profile

The agent works inside a harness. devXOS watches the harness.

Agentic engineering wraps AI in tests, reviews, and boundaries so speed doesn't outrun control. devXOS doesn't run inside that loop — it reads what the harness actually let through, across the three dimensions that decide whether a codebase is holding.

Maintainability

Is the code staying changeable?

Churn chains, duplication, moved code, and how much brand-new code gets rewritten within weeks.

  • churn_chains
  • duplicate_ratio
  • moved_code_pct
  • new_code_churn

Architecture

Is the structure holding its shape?

A structural harnessability score: type coverage, module boundaries, and the sensors the repo carries.

  • harnessability
  • type_coverage
  • module_boundaries

Behaviour

Is correctness holding up?

Reverts, fix latency, correction cascades, and change-failure rate — conditioned on who wrote the code.

  • revert_rate
  • fix_latency
  • correction_cascades
  • dora_cfr

Every number on this page is a field in the report — no metric ships without a name, a unit, and a documented computation.

Intelligence that audits itself.

usage_rollup × durability

What the tokens buy

Daily AI token spend, correlated with the survival of the code it produced. Cost per feature that lasted — not cost per line generated.

cross_correlations

Checked against DORA

Engine series are correlated with change-failure rate and time-to-restore, with significance tested against t-table critical values. A correlation we can't defend doesn't ship.

Runs where the history lives.

install
$ curl -fsSL https://devxos.ai/install.sh | sh

One script. Python 3.11+ and Git are the only requirements.

attribute
$ devxos hook install

A prepare-commit-msg hook records which AI tool touched each commit — Copilot, Claude, Cursor, Windsurf, and others.

analyze
$ devxos /path/to/repo --trend

The engine reads Git metadata and diffs locally and writes a Markdown report plus JSON metrics. Your code never leaves the machine.

aggregate
$ devxos login && devxos push

Optional: push metrics to the platform for org-wide dashboards, trends over time, and cross-repo comparison.

What devXOS refuses to be.

Not a surveillance tool

It analyzes systems, never individuals. No per-author scores, no leaderboards — by design, permanently.

Not a live dashboard

Point-in-time reports. Durability is measured in weeks, not in minutes of screen time.

Not an IDE plugin

It works from Git history alone. Nothing to install in anyone's editor.

Not a productivity tracker

It measures whether the work lasted, not how fast it was typed.

Run it on a repo you care about.

One command. The engine runs locally — the platform is optional.

$ curl -fsSL https://devxos.ai/install.sh | sh

Python 3.11+ · Git · zero dependencies · code never uploaded