gateway
Self-hosted firewall for securing AI applications with guardrails and content moderation.
GraphCanon updated today · GitHub synced today
Decision brief
Self-hosted firewall for securing AI applications with guardrails and content moderation.
Good fit when
- When you need to self-host a secure gateway for LLM-based AI applications that requires local deployment via Docker
- If your application requires PII redaction or prompt injection prevention measures built into the gateway framework
Avoid when
- Avoid if you are looking for cloud-managed services, as this tool is designed solely for local or self-hosted environments
- Not suitable if you require extensive customization beyond the provided policies.yaml file and predefined guardrails for content moderation and security
- Pricing:
- freemium - Open-source with no explicit monetary cost, but requires users to handle infrastructure costs associated with local Docker deployment
- Requirements:
- Min 4 GB RAM; Requires Docker; Docker and Docker Compose are required for deployment; Initial launch takes several minutes due to downloading machine learning models (~1.5GB+) for the first time
Observed Jul 15, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (385d since push)
- As of today
- Provenance
- Not a fork · Organization account
- As of today
- Security (OSV)
- No lockfile
- As of today
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install gatewaySimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
trylonai/gateway provides an open-source gateway to secure LLM-based AI applications by implementing powerful guardrails and measures such as PII redaction, prompt injection prevention, and more. Users can deploy the service locally via Docker. The framework allows for custom policies to control access and content flow through API requests.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Jul 15, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Jul 15, 2026
- Languages
- python
Source: github.language+pyproject.toml · Jul 15, 2026
Categories
Tags
README
Quick Start
The fastest way to deploy your own AI Gateway.
Prerequisites: Docker and Docker Compose.
-
Clone the repository:
git clone https://github.com/trylonai/gateway.git cd gateway -
Prepare your environment:
# Copy the example environment file. No edits are needed to run the quick start. cp .env.example .env # An example policies.yaml and docker-compose.yml are already present. -
Launch the Gateway:
docker-compose up -dNote: The first launch will take several minutes. The gateway needs to download the machine learning models (~1.5GB+). Subsequent launches will be much faster because the models are stored in a persistent Docker volume (trylon_hf_cache).
You can monitor the download progress and see when the application is ready by watching the logs:
docker-compose logs -f -
Test a Guardrail in Action
The default
policies.yamlcomes with a PII guardrail enabled to block any request containing an email address. Let's test it.curl -s -X POST "http://localhost:8000/v1/chat/completions" \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "My email address is test@example.com"}] }' | jqYou'll see a response with
finish_reason: "content_filter", confirming the block. Congratulations! You've just seen a guardrail in action without writing any code.
For agents
This page has a .md twin and JSON over the API.