Fences is an LLM augmented OpenAPI interpreter with a visual interface to easily make requests
An LLM augmented OpenAPI specification interpreter that provides a human-readable interactive representation of APIs, automatically generate requests and stores both requests and responses on your browser to improve AI-generated requests in future queries.
Fences operates similarly to SwaggerUI, but with a more human-friendly interface. It uses AI to create a visual diagram and categorize endpoints. After the initial parse Fences uses the OpenAPI specification to automatically generate request bodys for you, filling with it with sample data. It stores every single request and response data in your browser to better generate future requests. Data is only stored locally, the only third-party server it uses is Anthropic's API to access LLMs.
Fences is still under construction and may break for some edge cases. Please submit an issue with a reproducible example if you encounter any problems.
pip install fences-api # Installation command
fences # You will be prompted for an anthropic api key and for the link to the openapi spec
You will be prompted to enter your anthropic key so that fences can make requests to an LLM model to parse the OpenAPI specification.
PR's are welcome!
Please create an issue before opening a PR so that we can discuss the changes you want to make.
pip install -r requirements.txt
cd ui && npm install && npm run build && cd..
python fences/cli.py
pip install -e . # To test package locally
FAQs
Fences is an LLM augmented OpenAPI interpreter with a visual interface to easily make requests
We found that fences-api demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Application Security
/Security News
Socket CEO Feross Aboukhadijeh and a16z partner Joel de la Garza discuss vibe coding, AI-driven software development, and how the rise of LLMs, despite their risks, still points toward a more secure and innovative future.
Research
/Security News
Threat actors hijacked Toptal’s GitHub org, publishing npm packages with malicious payloads that steal tokens and attempt to wipe victim systems.
Research
/Security News
Socket researchers investigate 4 malicious npm and PyPI packages with 56,000+ downloads that install surveillance malware.