Report · marked 25 Aug 2026
ggml-org/whisper.cpp
An agent can work here, but it will waste turns finding its footing.
C++ · 53,177 stars · 1,923 files · branch master
61
/100
B-
Instructions
21/27Whether the repo tells an agent how to behave before it starts guessing. Losing marks on instruction quality.Setup
6/14Whether an agent can install the project and get it running without a human. Losing marks on deterministic install and pinned runtime version.Verification loop
10/25Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy. Losing marks on tests exist and test command is discoverable.Context economy
14/20Whether the repo fits in a context window, or fights it. Losing marks on file sizes fit in context.Navigability
8/10How quickly anything new can orient itself. Losing marks on written documentation.
Higher is better. Accent marks what is costing you most.
Fix these first
01
Test command is discoverable
Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.
02
Deterministic install
Commit the lockfile your package manager generates. Without it, an agent's install and your install are different builds, and 'works on my machine' becomes unfalsifiable.
03
File sizes fit in context
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
The full marking
Every deduction below names the file or setting it came from.
Instructions 21/27 A-
Whether the repo tells an agent how to behave before it starts guessing.
✓Agent instruction file
12/12
AGENTS.md is present, which is the format the most tools read.
✗Instruction quality
6/12
Real instructions, with gaps.
Worth fixing: it never states a build, test, or run command; has no code blocks.
6,191 characters, a workable length
uses headings, so an agent can skim it
✓README as an entry point
3/3
README has a clear getting-started section.
Setup 6/14 C
Whether an agent can install the project and get it running without a human.
✗Deterministic install
0/6
No lockfile. An agent installing dependencies may not get what CI got.
Commit the lockfile your package manager generates. Without it, an agent's install and your install are different builds, and 'works on my machine' becomes unfalsifiable.
✓Discoverable commands
6/6
Commands are declared where an agent will look for them.
Makefile
scripts/ directory
–Environment config
n/a
Not applicable — this reads as a library, with no environment to configure.
✗Pinned runtime version
0/2
No pinned runtime version.
Add a .nvmrc, .python-version, or equivalent so the agent's toolchain matches yours.
–Reproducible environment
n/a
Not applicable — a library doesn't need a container to be worked on.
Verification loop 10/25 C
Whether an agent can check its own work. This is the category that most decides whether agent output is trustworthy.
✗Tests exist
6/8
88 test files against 869 source files.
e.g. bindings/go/pkg/whisper/context_test.go, bindings/go/pkg/whisper/model_test.go, bindings/go/pkg/whisper/util_test.go
✗Test command is discoverable
0/7
There's no obvious way to run the tests. Even if tests exist, an agent won't reliably find the entry point.
Add a `test` script or a `test` target that runs the whole suite with no arguments. The convention is the interface — an agent tries `npm test` and `make test` before it tries reading your CI config.
✓Continuous integration
4/4
22 GitHub Actions workflows define what "passing" means.
✗Lint and format rules
0/3
No linter or formatter config. Style is tribal knowledge, so agent output will drift from yours.
A formatter config is the cheapest way to stop reviewing whitespace in agent diffs. It moves style from opinion to a command.
✗Static type checking
0/3
No static type checking.
A type checker gives an agent an error message instead of a runtime surprise. It's the second-fastest feedback loop after the compiler.
Context economy 14/20 B+
Whether the repo fits in a context window, or fights it.
✓No committed build output
6/6
No generated directories committed.
✓.gitignore hygiene
3/3
.gitignore covers 58 patterns.
✗File sizes fit in context
0/6
38 source files are over 100KB.
A single file that fills the context window forces an agent to work from fragments, and it will confidently edit code it never saw. Splitting the worst offenders pays for itself immediately.
examples/miniaudio.h — 4011KB
ggml/src/ggml-opencl/ggml-opencl.cpp — 1181KB
ggml/src/ggml-vulkan/ggml-vulkan.cpp — 997KB
✓Repository weight
5/5
About 43.9MB checked out, which is comfortable.
Here is your AGENTS.md
Drafted from what is actually in this repository: the install
command from your lockfile, the commands you already declare, your real directory layout. Anything
marked TODO needs a person. Save it at the root as AGENTS.md.
# AGENTS.md Port of OpenAI's Whisper model in C/C++ ## Setup ``` # TODO: the install command. No lockfile was found, so this could not be inferred. ``` ## Commands ``` make build # produce a build make samples ``` ## Layout - `ggml/` 574 source files - `bindings/` 109 source files - `examples/` 105 source files - `scripts/` 22 source files - `tests/` 22 source files - `src/` 18 source files ## Conventions - Tests live alongside the code they cover, following `bindings/go/pkg/whisper/context_test.go`. - CI defines what passing means. See `.github/workflows/bindings-go.yml`, and keep it green. - TODO: add the two or three conventions a newcomer always gets wrong here. ## Gotchas - `examples/miniaudio.h` is 4011KB. It will not fit comfortably in context, so read it in parts. - No lockfile is committed, so an install here may not match what CI produced. --- Drafted by agentreadme.com from what is in this repository. Everything marked TODO needs a human. Check it in as AGENTS.md at the root.
Open the raw markdown
or
curl -o AGENTS.md agentreadme.com/draft/ggml-org/whisper.cpp.md
Show the mark
The badge re-checks daily, so it keeps up as the repository changes. Use mark again to force it now.
[](https://agentreadme.com/ggml-org/whisper.cpp)Other C++ repositories, marked
Think this mark is wrong?
Every deduction above names the file it came from, so this can be settled by looking. If a check missed something, that is a rule worth fixing.