- Home
- AI Content Moderation Software
- LocalMod
LocalMod
What it is
LocalMod is a free, self-hosted API for moderating text and images within a user's own infrastructure. The project says it can run offline, keeping user data there. Text classifiers check for personally identifiable information, toxicity, prompt injection, spam, and NSFW text. Its PII detection covers email addresses, phone numbers, Social Security numbers, and credit card numbers; image moderation detects explicit or adult images. API endpoints support single and batch text analysis, PII redaction, and image checks using a URL or uploaded file. The README documents use through Python, an API server, or Docker, and includes an example Discord bot for real-time text and image moderation with auto-delete, timeouts, and logging. Offline operation requires downloading the models once and setting LOCALMOD_OFFLINE=1; the documented download is about 3.5 GB and includes the image model. The project recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier. LocalMod is MIT licensed and listed for Linux and self-hosted use.
For and against
For
- Checks text for five listed categories
- Detects explicit or adult images
- Supports batch analysis and PII redaction
- MIT licensed
Against
- Offline setup requires a model download of about 3.5 GB
- Project recommends a GPU for production workloads
- Listed platform support is Linux and self-hosted
The verdict
LocalMod covers text and image moderation through a free API that can operate offline. Plan for the initial model download, and consider the project's GPU recommendation for production workloads.
Who it suits
It suits developers and teams who want text and image moderation to run inside their own infrastructure. The documented options include Python, an API server, and Docker deployment.
Plans and prices
Free, self-hosted
No price stated · self-hosted content moderation API
Read 8 Oct 2026 · github.com
On the record
- API endpoints
- The API includes endpoints for single and batch text analysis, PII redaction, and image analysis by URL or uploaded file.github.com · read 8 Oct 2026
- Audience
- The project describes itself as a self-hosted content moderation API for users who want moderation within their own infrastructure.github.com · read 8 Oct 2026
- Compute
- The README recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier.github.com · read 8 Oct 2026
- Discord
- A Discord bot example supports real-time text and image moderation, auto-delete, timeout, and logging.github.com · read 8 Oct 2026
- Image checks
- Its image moderation classifier detects explicit or adult images.github.com · read 8 Oct 2026
- License
- The repository identifies LocalMod as MIT licensed.github.com · read 8 Oct 2026
- Model download
- The documented model download is about 3.5 GB and includes the image model.github.com · read 8 Oct 2026
- Offline setup
- The README says to download the models once, then configure LOCALMOD_OFFLINE=1 to run offline.github.com · read 8 Oct 2026
- PII detection
- The PII classifier detects emails, phone numbers, Social Security numbers, and credit card numbers.github.com · read 8 Oct 2026
- Privacy
- The project says it runs offline and that user data never leaves their infrastructure.github.com · read 8 Oct 2026
- Purpose
- LocalMod is a fully offline, self-hosted content moderation API for text and images.github.com · read 8 Oct 2026
- Text checks
- Its text classifiers cover PII, toxicity, prompt injection, spam, and NSFW text.github.com · read 8 Oct 2026
- Ways to run
- The README documents Python usage, an API server, and Docker deployment.github.com · read 8 Oct 2026
