LocalMod
github.com
- Free plan
- Linux
- API
- Self-hosted
What LocalMod is
LocalMod is a free, self-hosted API for moderating text and images within your own infrastructure. The project says it runs offline and keeps user data there. Text classifiers check for personally identifiable information (PII), toxicity, prompt injection, spam, and NSFW content. The PII classifier detects emails, phone numbers, Social Security numbers, and credit card numbers; the image classifier detects explicit or adult images. API endpoints support single and batch text analysis, PII redaction, and image analysis from a URL or uploaded file. The README documents Python use, an API server, and Docker deployment. A Discord bot example shows real-time text and image moderation with automatic deletion, timeouts, and logging. Offline setup requires downloading the models once and then setting LOCALMOD_OFFLINE=1. The documented model download is about 3.5 GB and includes the image model. The project recommends a GPU for production workloads and lists latency estimates for CPU and GPU by classifier. LocalMod is MIT licensed and is listed for Linux, API, and self-hosted use.
Who it suits
It suits teams that want content moderation to run on their own infrastructure, including offline. It is aimed at users who can deploy and operate a self-hosted API.
Good to know, and what to watch
- Moderates text and images
- Supports batch text analysis and PII redaction
- Runs offline after model download
- MIT licensed
- Model download is about 3.5 GB
- Project recommends a GPU for production workloads
Plans
Every plan and priceFree, self-hosted
Free plan
The verdict
LocalMod offers text and image moderation through an API that can run within your infrastructure. Its offline setup requires an initial model download, and the project recommends a GPU for production workloads.
What the maker publishes
- API endpoints
- The API includes endpoints for single and batch text analysis, PII redaction, and image analysis by URL or uploaded file. source
- Audience
- The project describes itself as a self-hosted content moderation API for users who want moderation within their own infrastructure. source
- Compute
- The README recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier. source
- Discord
- A Discord bot example supports real-time text and image moderation, auto-delete, timeout, and logging. source
- Image checks
- Its image moderation classifier detects explicit or adult images. source
- License
- The repository identifies LocalMod as MIT licensed. source
- Model download
- The documented model download is about 3.5 GB and includes the image model. source
- Offline setup
- The README says to download the models once, then configure LOCALMOD_OFFLINE=1 to run offline. source
- PII detection
- The PII classifier detects emails, phone numbers, Social Security numbers, and credit card numbers. source
- Privacy
- The project says it runs offline and that user data never leaves their infrastructure. source
- Purpose
- LocalMod is a fully offline, self-hosted content moderation API for text and images. source
- Text checks
- Its text classifiers cover PII, toxicity, prompt injection, spam, and NSFW text. source
- Ways to run
- The README documents Python usage, an API server, and Docker deployment. source
Checked against the maker's pages on 8 Oct 2026.