sherwinvishesh/SurrogateShield
Library
Can I trust it?
Worth a closer look before you use it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active Check
Last change 31 days ago.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A privacy-first proxy and Python library that detects personal data in text, replaces it with consistent realistic surrogates before it reaches an LLM, and restores the real values in the reply. Detection combines regex patterns, a DeBERTa PII tagger and spaCy, and surrogate…
Who it's for
Python developers building LLM chatbots or RAG pipelines who need to keep personal data out of third-party model providers
How to use it
Install
pip install ./python-libraryFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up sherwinvishesh/SurrogateShield in my project. Follow its README: https://github.com/sherwinvishesh/SurrogateShield. Explain each step and check it is safe before running anything.
Star curve
On the radar
Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.
Records
- Best place on RepoAlerts: #99, on 9 Nov 2026
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/sherwinvishesh/SurrogateShield?ref=badge)Similar repos
- huggingface/safeagents
A local proxy placed between a coding agent and its model server. It checks every tool call the model returns, blocks undeclared tools and suspicious calls via atif-scan detectors and an optional judg
- jannybloug/openai-gemini
A serverless proxy that exposes an OpenAI-compatible API backed by Google's Gemini API. It supports chat completions, embeddings and models endpoints, and can be deployed to Vercel, Netlify, Cloudflar
- xiaoyulei317-droid/PromptGuard---AI-Privacy-Sanitizer
A single-file, client-side web tool that redacts emails, phone numbers, IP addresses, API keys and user-defined keywords from text, replacing them with placeholder tags before the text is pasted into
- 8hjkkwikl8/ai-portfolio
A portfolio of three runnable AI engineering projects: InsightRAG (traceable Chinese RAG with hybrid retrieval and citation checks), PromptLens (versioned prompt evaluation with reproducible runs) and
- l-wn/ClusterChat
A browser-based chatbot that splits one large language model across the browsers of its users over WebRTC, using WebGPU. Each user gets a separate chat, several replies run concurrently, and participa
- BehiSecc/HuntProxy
A web security workbench that lets AI agents drive security testing of web targets. It provides projects, an HTTP/HTTPS capture proxy with searchable history, persistent Chromium browser profiles, sit