Freedom251 › AI Content Moderation Software
LocalMod
What LocalMod is
LocalMod is a free content moderation API for text and images that runs within your own infrastructure. The project says it operates offline, so user data does not leave that infrastructure. Text classifiers cover PII, toxicity, prompt injection, spam, and NSFW text; the PII classifier detects emails, phone numbers, Social Security numbers, and credit card numbers. Image checks detect explicit or adult images. The API provides 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, as well as a Discord bot example for real-time text and image moderation, auto-delete, timeout, and logging. To work offline, download the models once and set 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, API, and self-hosted use.
Who it suits
It suits people or teams who want text and image moderation inside their own infrastructure, including offline use. Developers can use the documented Python interface, API server, or Docker deployment.
What it does well
- Runs offline after the documented model download.
- Checks text for PII, toxicity, prompt injection, spam, and NSFW content.
- Supports image analysis by URL or uploaded file.
- Includes a Discord bot example.
- MIT licensed.
What to know first
- The model download is about 3.5 GB.
- The project recommends a GPU for production workloads.
- Offline use requires downloading models once first.
Limits
The free self-hosted plan has a documented model download of about 3.5 GB, including the image model. The project recommends a GPU for production workloads.
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Free, self-hosted | No price stated · self-hosted content moderation API | Free |
As github.com lists them, read 8 Oct 2026. The maker's own page has the final word.
Getting started
- Use a Linux environment for the self-hosted API.
- Choose Python usage, an API server, or Docker deployment as documented in the README.
- Download the models once; the documented download is about 3.5 GB and includes the image model.
- Set LOCALMOD_OFFLINE=1 to run offline.
- Use the API endpoints for text analysis, PII redaction, or image analysis.
Verdict
LocalMod offers a broad set of moderation checks in a self-hosted API, with offline operation and several deployment approaches. Account for the initial model download and the project's GPU recommendation for production workloads.
Questions
How much does LocalMod cost?
The self-hosted plan is free.
Can LocalMod run offline?
The project says it can. The documented setup downloads the models once and then sets LOCALMOD_OFFLINE=1.
What does LocalMod moderate?
It checks text for PII, toxicity, prompt injection, spam, and NSFW text, and detects explicit or adult images.
How can LocalMod be deployed?
The README documents Python usage, an API server, and Docker deployment.
Is LocalMod open source?
The repository identifies LocalMod as MIT licensed.
What hardware does the project recommend?
The project recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier.
Facts from LocalMod's own pages
- API endpoints
- The API includes endpoints for single and batch text analysis, PII redaction, and image analysis by URL or uploaded file. · github.com, 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, 8 Oct 2026
- Compute
- The README recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier. · github.com, 8 Oct 2026
- Discord
- A Discord bot example supports real-time text and image moderation, auto-delete, timeout, and logging. · github.com, 8 Oct 2026
- Image checks
- Its image moderation classifier detects explicit or adult images. · github.com, 8 Oct 2026
- License
- The repository identifies LocalMod as MIT licensed. · github.com, 8 Oct 2026
- Model download
- The documented model download is about 3.5 GB and includes the image model. · github.com, 8 Oct 2026
- Offline setup
- The README says to download the models once, then configure LOCALMOD_OFFLINE=1 to run offline. · github.com, 8 Oct 2026
- PII detection
- The PII classifier detects emails, phone numbers, Social Security numbers, and credit card numbers. · github.com, 8 Oct 2026
- Privacy
- The project says it runs offline and that user data never leaves their infrastructure. · github.com, 8 Oct 2026
- Purpose
- LocalMod is a fully offline, self-hosted content moderation API for text and images. · github.com, 8 Oct 2026
- Text checks
- Its text classifiers cover PII, toxicity, prompt injection, spam, and NSFW text. · github.com, 8 Oct 2026
- Ways to run
- The README documents Python usage, an API server, and Docker deployment. · github.com, 8 Oct 2026
Where LocalMod stands on Freedom251
- AI Content Moderation Software#5 of 27