opencomplai-ai
The optional AI intent classification plugin for Opencomplai.
It adds the --ai-intent flag to opencomplai scan, classifying how each AI callsite in
your code is actually used — its decision autonomy, the subjects it acts on, and which EU
AI Act risk tier and Annex III area it maps to.
All inference runs locally — models execute on your machine via ONNX Runtime or llama.cpp. No code or prompts leave your environment.
Prerequisites
opencomplai-ai is a plugin. Install the core engine first:
pip install opencomplai-core # or the opencomplai / opencomplai-cli suite
Install
# Base install — CodeBERT (ONNX) classification, no extra build deps
pip install opencomplai-ai
# Deep install — adds llama.cpp for generative GGUF models
pip install "opencomplai-ai[deep]"
Usage
Once installed alongside the CLI, the --ai-intent flag becomes available on the scan
command:
opencomplai scan --ai-intent
By default only callsites in files with lexical findings are annotated (fast). To analyze every callsite in the repository:
opencomplai scan --ai-intent --ai-deep
Useful flags:
| Flag | Effect |
|---|---|
--ai-intent |
Enable AI intent classification |
--ai-model <id> |
Choose a model (see catalog below) |
--ai-deep |
Annotate every callsite, not just those near lexical findings |
--ai-verbose |
Show all callsite annotations (default: top 10 by risk tier) |
Supported models
The default model (codebert-onnx) runs on the base install. The generative GGUF models
require the [deep] extra. Models are downloaded from the Hugging Face Hub on first use
and cached locally under ~/.opencomplai/.
| Model ID | Runtime | Size | Needs [deep] |
|---|---|---|---|
codebert-onnx (default) |
ONNX Runtime | ~440 MB | no |
qwen2.5-coder-0.5b |
llama.cpp | ~400 MB | yes |
qwen2.5-coder-1.5b (recommended) |
llama.cpp | ~1.0 GB | yes |
smollm2-1.7b |
llama.cpp | ~1.1 GB | yes |
phi-3.5-mini |
llama.cpp | ~2.2 GB | yes |
mistral-7b |
llama.cpp | ~4.1 GB | yes |
opencomplai scan --ai-intent --ai-model qwen2.5-coder-1.5b
Model download flow
On first use of a model, the plugin prompts before downloading and shows a progress bar. The CodeBERT model has no prebuilt ONNX artifact on the Hub, so it is exported from the official PyTorch checkpoint on first run and then cached. Subsequent scans reuse the cached model with no network access.
Documentation
Full AI-intent guide and the model reference at docs.opencomplai.com.
License
AGPL-3.0-only. See LICENSE.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file opencomplai_ai-0.3.0.tar.gz.
File metadata
- Download URL: opencomplai_ai-0.3.0.tar.gz
- Upload date:
- Size: 34.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a8aee5b83623115a2ae7da86fb4f0c0e5a27043437c1ec2f9ce484f8735678f6
|
|
| MD5 |
9e16c2621948dc25e61be511ea14d699
|
|
| BLAKE2b-256 |
c6a3b28543aa2884f60914ea315ec6ca75c4e22433df397417b1c9bf4cbed16f
|
Provenance
The following attestation bundles were made for opencomplai_ai-0.3.0.tar.gz:
Publisher:
publish-pypi.yml on Opencomplai/opencomplai-enterprise
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
opencomplai_ai-0.3.0.tar.gz -
Subject digest:
a8aee5b83623115a2ae7da86fb4f0c0e5a27043437c1ec2f9ce484f8735678f6 - Sigstore transparency entry: 2451550952
- Sigstore integration time:
-
Permalink:
Opencomplai/opencomplai-enterprise@69effa8429019a5b36405181014ba165ad153ba6 -
Branch / Tag:
refs/tags/v0.3.0 - Owner: https://github.com/Opencomplai
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-pypi.yml@69effa8429019a5b36405181014ba165ad153ba6 -
Trigger Event:
push
-
Statement type:
File details
Details for the file opencomplai_ai-0.3.0-py3-none-any.whl.
File metadata
- Download URL: opencomplai_ai-0.3.0-py3-none-any.whl
- Upload date:
- Size: 34.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e0f34508a06f3dd634f39df86559d41a0e9976121e853f4b6b059aca29a90f36
|
|
| MD5 |
8000a3efe17fceafe60cf493d415242f
|
|
| BLAKE2b-256 |
5490f7984b346e543b2e0f741d88d36f62096690719ef424bcb1fe058130ea0f
|
Provenance
The following attestation bundles were made for opencomplai_ai-0.3.0-py3-none-any.whl:
Publisher:
publish-pypi.yml on Opencomplai/opencomplai-enterprise
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
opencomplai_ai-0.3.0-py3-none-any.whl -
Subject digest:
e0f34508a06f3dd634f39df86559d41a0e9976121e853f4b6b059aca29a90f36 - Sigstore transparency entry: 2451551475
- Sigstore integration time:
-
Permalink:
Opencomplai/opencomplai-enterprise@69effa8429019a5b36405181014ba165ad153ba6 -
Branch / Tag:
refs/tags/v0.3.0 - Owner: https://github.com/Opencomplai
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-pypi.yml@69effa8429019a5b36405181014ba165ad153ba6 -
Trigger Event:
push
-
Statement type:
