lfx-loopgrid
LoopGrid extension for Langflow 1.12 / LFX. It adds a LoopGrid bundle with six components for recording and verifying signed, tamper-evident evidence around consequential AI-agent decisions.
Design-partner release. LoopGrid records evidence; it does not execute the external business action.
Components
Inside the Loopgrid bundle in the Langflow palette:
- Record Decision
- Record Action
- Record Outcome
- Submit Review
- Get Decision
- Verify Decision
The shorter palette labels are intentional so the operations remain distinguishable in Langflow's narrow component sidebar. Internal component class names remain stable (LoopGridRecordDecision, LoopGridRecordAction, and so on).
Visual chaining
Components that operate on an existing decision expose two alternatives:
- Decision Data — connect a
Dataoutput from another LoopGrid component. The decision ID is extracted automatically. - Decision ID — enter an existing LoopGrid decision ID manually when the component is not connected upstream.
A typical connected flow is:
Record Decision
-> Record Action
-> Record Outcome
-> Get Decision
-> Verify Decision
For human review, connect a pending-review decision (for example from Get Decision) to Submit Review, or enter the pending decision ID manually.
Requirements
- Python 3.10-3.14
- Langflow 1.12.x / LFX Bundle API v1
- A reachable LoopGrid deployment
- LoopGrid workspace ID and API key
Local development (Windows PowerShell)
uv venv --python 3.12 .venv
.\.venv\Scripts\Activate.ps1
uv pip install "langflow~=1.12.3" build twine pytest
lfx extension validate .
python -m unittest discover -s tests -v
python -m compileall -q src tests
python -m build
python -m twine check dist/*
lfx extension validate . --execute-imports is an optional deeper import probe. Langflow/LFX 1.12.3 can report a subprocess circular-import false positive even when normal imports and runtime loading succeed, so release validation should include the actual Langflow UI smoke test.
To register the extension for local development:
lfx extension dev .
If the project path contains spaces on Windows and the dev command's automatic launcher mis-parses the path, registration still succeeds; launch Langflow separately:
langflow run
The Loopgrid bundle should appear in the component palette with all six components.
Install after PyPI release
uv pip install lfx-loopgrid==0.1.0
langflow run
Extension discovery occurs when Langflow starts, so restart Langflow after installation or upgrade.
Credentials
Each component accepts:
- LoopGrid Base URL — for example
http://127.0.0.1:8000locally or an HTTPS deployment - LoopGrid API Key — secret field, sent only in
X-LoopGrid-Key - Workspace ID — defaults to
default
For a lifecycle using all six components, the key needs the corresponding LoopGrid ingest, read, and review permissions. Prefer narrower keys for narrower flows.
Privacy
Record Decision defaults to redacted. Only map data intentionally selected for evidence capture. The extension does not automatically read complete chats, files, environment variables, or unrelated flow state.
Verification
Verify Decision performs verification through the connected LoopGrid service. Independent/offline evidence-bundle verification remains available through loopgrid-verify.
Source and support
- Source: https://github.com/loopgridio/loopgrid-langflow
- Website: https://loopgrid.io
- Contact: hello@loopgrid.io
License
Apache-2.0.
Release files for lfx-loopgrid 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| lfx_loopgrid-0.1.0.tar.gz | 11.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| lfx_loopgrid-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 28.0 kB
Release files / lfx_loopgrid-0.1.0.tar.gz
| Download URL | lfx_loopgrid-0.1.0.tar.gz |
|---|---|
| Size | 11.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
17933b10e7200c69441cb079b47a49a3a36a6176162e7a25b1c760f585cdf47c
|
|
BLAKE2b-256 checksum How to use checksums |
abfe981e491f8b4d7eccd150e0a909ecb4b5c0c9d7a837893048d5987285d25d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 24, 2026.
Transparency logRelease files / lfx_loopgrid-0.1.0-py3-none-any.whl
| Download URL | lfx_loopgrid-0.1.0-py3-none-any.whl |
|---|---|
| Size | 16.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6eedc374b186e4b8fa258b9ad1353b6266a0b45ffdbd6594901f8a8b046ac6dc
|
|
BLAKE2b-256 checksum How to use checksums |
f7f015dddf95de90ea1143cde821693c01e27b4ac57db79bb31dcc01a6b81b21
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 24, 2026.
Transparency log