Skip to content
CAI
Software that uses CAICheck a score

biheto/DevAgent-Studio

38.4

Weak · 17 November 2026

19.1k

lines of production code

Python

with TypeScript

1

measurement over time

CAI band scale
CAI lens gauges

What this system is

Behavioural changes

10 commits (0 fixes) modifying app/api

A change to existing behaviour in app/api — 10 commits, 2 files: “feat: add governed RAG memory and evaluation”; “feat: complete plugin marketplace integration”; “feat: add durable workflows, trusted identities and reliable RAG”; and 7 more.

app/api · medium confidence · unverified

11 commits (0 fixes) modifying app/persistence

A change to existing behaviour in app/persistence — 11 commits, 4 files: “feat: add pgvector RAG persistence”; “feat: add governed RAG memory and evaluation”; “feat: add typed RAG chunking and pgvector coverage”; and 8 more.

app/persistence · medium confidence · unverified

17 commits (1 fix) modifying web

A change to existing behaviour in web — 17 commits (1 fix), 10 files: “feat: refresh workbench visual design and previews”; “style: improve MCP logs and benchmark detail layout”; “feat: add governed RAG memory and evaluation”; and 14 more.

web · medium confidence · unverified

2 commits (0 fixes) modifying app/agents

A change to existing behaviour in app/agents — 2 commits, 6 files: “feat: add typed RAG chunking and pgvector coverage”; “feat: add core project analysis and review agents”.

app/agents · medium confidence · unverified

2 commits (0 fixes) modifying app/harness

A change to existing behaviour in app/harness — 2 commits, 5 files: “feat: add durable workflows, trusted identities and reliable RAG”; “feat: add harness runtime and persistent task state”.

app/harness · medium confidence · unverified

2 commits (0 fixes) modifying scripts

A change to existing behaviour in scripts — 2 commits, 4 files: “feat: add durable workflows, trusted identities and reliable RAG”; “feat: add real MCP client and management console”.

scripts · medium confidence · unverified

4 commits (0 fixes) modifying app/marketplace

A change to existing behaviour in app/marketplace — 4 commits, 3 files: “feat: complete plugin marketplace integration”; “feat: refine skill marketplace approval workflow”; “feat: add plugin marketplace install console”; and 1 more.

app/marketplace · medium confidence · unverified

4 commits (0 fixes) modifying app/skills

A change to existing behaviour in app/skills — 4 commits, 5 files: “feat: add plugin marketplace install console”; “feat: add harness runtime and persistent task state”; “feat: add skill runtime management console”; and 1 more.

app/skills · medium confidence · unverified

5 commits (0 fixes) modifying app/providers

A change to existing behaviour in app/providers — 5 commits, 3 files: “feat: add LLM trace and prompt governance”; “feat: add durable workflows, trusted identities and reliable RAG”; “feat: add extended benchmark suites”; and 2 more.

app/providers · medium confidence · unverified

6 commits (0 fixes) modifying app

A change to existing behaviour in app — 6 commits, 6 files: “feat: add governed RAG memory and evaluation”; “feat: add durable workflows, trusted identities and reliable RAG”; “feat: add extended benchmark suites”; and 3 more.

app · medium confidence · unverified

6 commits (0 fixes) modifying app/graphs

A change to existing behaviour in app/graphs — 6 commits, 3 files: “feat: add durable workflows, trusted identities and reliable RAG”; “feat: add business scenarios and github integration”; “feat: add skill runtime management console”; and 3 more.

app/graphs · medium confidence · unverified

7 commits (0 fixes) modifying dev-agent-studio

A change to existing behaviour in dev-agent-studio — 7 commits, 6 files: “feat: add governed RAG memory and evaluation”; “feat: add durable workflows, trusted identities and reliable RAG”; “feat: add harness runtime and persistent task state”; and 4 more.

dev-agent-studio · medium confidence · unverified

Test coverage

5 commits adding/updating tests in tests

Test coverage in tests — 5 commits, 12 files: “feat: add governed RAG memory and evaluation”; “feat: add typed RAG chunking and pgvector coverage”; “feat: add durable workflows, trusted identities and reliable RAG”; and 2 more.

tests · high confidence · unverified

Dependencies

4 commits updating dependencies (3 manifests)

A dependency / build maintenance change in (dependencies) — 4 commits, 3 files: “feat: add typed RAG chunking and pgvector coverage”; “feat: add durable workflows, trusted identities and reliable RAG”; “feat: add React workbench and task timeline”; and 1 more.

(dependencies) · medium confidence · unverified

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

How this codebase got here

Baseline

  • First survey — no prior run to compare against. CAI 38.4.

Lenses

  • Code Health 47.5
  • Architecture 76.1
  • Maturity 78.7
  • Readiness 22.8
  • Security 94.9
  • Accessibility 35.4
  • Performance 100.0

Changes since last survey

  • 43 commits — 42 feature/other, 1 fixes

By area

  • web/src — 12 commits
  • docs/assets — 8 commits
  • (repo) — 7 commits
  • (root) — 7 commits
  • app/providers — 2 commits
  • app/agents — 1 commit
  • app/benchmark_runner.py — 1 commit
  • app/graphs — 1 commit
  • app/harness — 1 commit
  • app/skills — 1 commit
  • docs/IMPLEMENTATION_TIMELINE.md — 1 commit
  • docs/PHASE_8_WORKFLOW_PRODUCTION.md — 1 commit

Notable commits

  • fix: fix: prevent benchmark panels from overlapping
  • change: docs: add MIT license and attribution
  • change: docs: add skill marketplace documentation and screenshots
  • change: docs: clean project documentation
  • change: docs: document implementation timeline and priorities
  • change: docs: improve GitHub SVG compatibility
  • change: docs: replace architecture diagram with PNG
  • change: docs: rewrite README for governed skill platform
  • change: docs: rewrite bilingual README for open source
  • change: docs: update README preview screenshots
  • change: feat: add LLM trace and prompt governance
  • change: feat: add React workbench and task timeline
  • change: feat: add benchmark runner and evaluation dashboard
  • change: feat: add business scenarios and github integration
  • change: feat: add core project analysis and review agents
  • change: feat: add durable workflows, trusted identities and reliable RAG
  • change: feat: add extended benchmark suites
  • change: feat: add governed RAG memory and evaluation
  • change: feat: add governed long-term memory
  • change: feat: add harness runtime and persistent task state
  • …and 23 more

Architecture

  • 0 containers · 1 bounded contexts · 0 dependency edges (baseline)

Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.

Survey your own repository

biheto/DevAgent-Studio was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.

About this page

  • The score is its most recent published measurement, taken on 17 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
  • Measured at commit 6065d1ed4558da820acd1062dc0e226a562e34cc — the exact code this score is about.
  • Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
  • Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.85+preprod-eba6548ac50f.