LocalMod
github.com
What it is
LocalMod is a free content moderation API for text and images that runs on Linux within a self-hosted setup. The project says it can run offline, keeping user data within the user's infrastructure. Text classifiers check for PII, toxicity, prompt injection, spam, and NSFW text; the PII classifier covers emails, 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 analysis from a URL or uploaded file. The README documents Python use, running an API server, and Docker deployment, 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 README recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier. LocalMod is MIT licensed.
Spec sheet
- Purpose
- LocalMod is a fully offline, self-hosted content moderation API for text and images.Read 8 Oct 2026 · github.com
- Audience
- The project describes itself as a self-hosted content moderation API for users who want moderation within their own infrastructure.Read 8 Oct 2026 · github.com
- Privacy
- The project says it runs offline and that user data never leaves their infrastructure.Read 8 Oct 2026 · github.com
- License
- The repository identifies LocalMod as MIT licensed.Read 8 Oct 2026 · github.com
- API endpoints
- The API includes endpoints for single and batch text analysis, PII redaction, and image analysis by URL or uploaded file.Read 8 Oct 2026 · github.com
- Compute
- The README recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier.Read 8 Oct 2026 · github.com
- Discord
- A Discord bot example supports real-time text and image moderation, auto-delete, timeout, and logging.Read 8 Oct 2026 · github.com
- Image checks
- Its image moderation classifier detects explicit or adult images.Read 8 Oct 2026 · github.com
- Model download
- The documented model download is about 3.5 GB and includes the image model.Read 8 Oct 2026 · github.com
- Offline setup
- The README says to download the models once, then configure LOCALMOD_OFFLINE=1 to run offline.Read 8 Oct 2026 · github.com
- PII detection
- The PII classifier detects emails, phone numbers, Social Security numbers, and credit card numbers.Read 8 Oct 2026 · github.com
- Text checks
- Its text classifiers cover PII, toxicity, prompt injection, spam, and NSFW text.Read 8 Oct 2026 · github.com
- Ways to run
- The README documents Python usage, an API server, and Docker deployment.Read 8 Oct 2026 · github.com
Plans and prices
Strong points and limits
Strong points
- Runs offline after a one-time model download.
- Checks text for PII, toxicity, and spam.
- Supports image moderation and PII redaction.
- Offers Python, API server, and Docker usage.
- MIT licensed.
Limits
- Documented model download is about 3.5 GB.
- A GPU is recommended for production workloads.
- Self-hosted deployment is required.
Who it suits
LocalMod suits teams that want text and image moderation to run within their own infrastructure. It is aimed at users who need an API and can manage a self-hosted deployment.
Verdict
LocalMod combines text checks, image moderation, and PII redaction in a self-hosted API. Plan for the model download and deployment setup, especially for offline use.
Where Specifiction places it
- AI Content Moderation Software#19 of 277.5