generic-ml-cache-cli

gmlcache

Detached ML Execution Cache — the terminal client

gmlcache runs, records, and replays detached ML workloads — record a real client (or API) call once, replay it forever by its content key, offline and byte-for-byte.

Single-user, local — not a gateway. gmlcache runs on your machine, as you, across the subscriptions and APIs you already hold. It is not a multi-user router and not a way to share one subscription — see Positioning.

gmlcache: a miss records the real client call; the same command again is served instantly from cache, byte-identical

_{Detached + live streaming — run --detach returns an id; execution watch follows the client's live progress to the result}

gmlcache run --detach, then execution watch streaming the client's live thinking and tool calls to the result

Install

pip install generic-ml-cache-cli

This installs the gmlcache command and pulls in the engine, generic-ml-cache-core.

Use

gmlcache run    --client claude --model sonnet --prompt "…"            # record on a miss, replay on a hit
gmlcache check  --client claude --model sonnet --prompt "…"            # forecast: is this exact call cached?
gmlcache run    --client claude --model sonnet --prompt "…" --detach   # run detached → prints an execution id
gmlcache alias  claude -- -p "…" --model sonnet                        # thin wrapper: cache a raw native call
gmlcache execution watch <id>                                         # follow a detached run's live progress
gmlcache session report <id>                                          # token usage by provider/model for a workflow
gmlcache encrypt                                                      # encrypt the whole store at rest
gmlcache export --tag eval -o data.jsonl                              # export the (input, output) dataset corpus
gmlcache list | tags | stats | inspect <key>                          # browse stored executions
gmlcache doctor | models | status | init                             # environment & configuration helpers

What it does

Records a real agentic CLI client (claude, codex, cursor-agent) or an API call — stdout, stderr, exit code, generated files, and token usage.
Replays an identical request instantly and offline, byte-for-byte — gmlcache adds nothing to the client's output, so it is a transparent drop-in.
Reports — list, group, inspect, and measure stored executions and their savings.
And more — group a workflow's runs into sessions with per-provider/model usage reports, encrypt the whole store at rest, run detached (--detach) with a live progress stream, and export an (input, output) dataset.

Built on a reusable engine

gmlcache is the terminal client — one inbound driver over the engine. The whole cache logic and every adapter live in generic-ml-cache-core, a stateless library. To embed the cache in your own application instead of driving it from a terminal, depend on the core and inject your own data source — you never reimplement the adapters.

License

Apache-2.0 — see LICENSE and NOTICE.

Release files for generic-ml-cache-cli 0.13.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for generic-ml-cache-cli 0.13.0
File	Size	Uploaded
generic_ml_cache_cli-0.13.0.tar.gz	60.9 kB	Jun 25, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for generic-ml-cache-cli 0.13.0
File	Interpreter	ABI	Platform	Reset
generic_ml_cache_cli-0.13.0-py3-none-any.whl 41.5 kB Jun 25, 2026	Python 3	none	any	Details

Total release size: 102.4 kB

Release files / generic_ml_cache_cli-0.13.0.tar.gz

Download URL	generic_ml_cache_cli-0.13.0.tar.gz
Size	60.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`78e2977b96c5bded6be8ab85e03bdab8654050cb03ccdf3deb0823042cf4dc3a`
BLAKE2b-256 checksum How to use checksums	`6cb39479942ac263b30cd33907ccbbc6794bb01dbfbc7f85833a3df5b6cbdb9b`
Upload date	Jun 25, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/danielslobozian/generic-ml-cache
Publishing commit: github.com/danielslobozian/generic-ml-cache/tree/ce74f607bc35f1d5b46b233fd505e6c5fa984a2f

Workflow

Publishing configuration: github.com/danielslobozian/generic-ml-cache/blob/ce74f607bc35f1d5b46b233fd505e6c5fa984a2f/.github/workflows/release.yml
Publishing logs: github.com/danielslobozian/generic-ml-cache/actions/runs/28198643182/attempts/1

Artifact

Subject: generic_ml_cache_cli-0.13.0.tar.gz
SHA-256 checksum: 78e2977b96c5bded6be8ab85e03bdab8654050cb03ccdf3deb0823042cf4dc3a Verifying attestations

Release files / generic_ml_cache_cli-0.13.0-py3-none-any.whl

Download URL	generic_ml_cache_cli-0.13.0-py3-none-any.whl
Size	41.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`f24881111a120d1357cbeb98e9c1b2c660b758f767aab8c3f877db190186594c`
BLAKE2b-256 checksum How to use checksums	`07929246d871e781decf7d96f3dd8d4ea461aee4428d9e2e08d1b48c7af9b542`
Upload date	Jun 25, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.12`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/danielslobozian/generic-ml-cache
Publishing commit: github.com/danielslobozian/generic-ml-cache/tree/ce74f607bc35f1d5b46b233fd505e6c5fa984a2f

Workflow

Publishing configuration: github.com/danielslobozian/generic-ml-cache/blob/ce74f607bc35f1d5b46b233fd505e6c5fa984a2f/.github/workflows/release.yml
Publishing logs: github.com/danielslobozian/generic-ml-cache/actions/runs/28198643182/attempts/1

Artifact

Subject: generic_ml_cache_cli-0.13.0-py3-none-any.whl
SHA-256 checksum: f24881111a120d1357cbeb98e9c1b2c660b758f767aab8c3f877db190186594c Verifying attestations