SurrogateShield

A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks.

sherwinvishesh/SurrogateShield

View on GitHub ↗

A privacy-first guardrail for LLMs and RAG pipelines. SurrogateShield detects, redacts, and reconstructs sensitive PII data on the fly while defending against adversarial attacks.

SurrogateShield ranks 149th of 872 in Evaluation & Guardrails, last commit 37 days ago.

Star trajectory

16 days tracked
2026-11-061k stars today2026-11-22
Momentum

- in 30d, below the Evaluation & Guardrails median of +1.4%.

Maintenance

Last commit 37 days ago, staler than the median of 15d.

How it compares in Evaluation & Guardrails

SurrogateShield
1k
stars
- 30d
commit 37 days ago
Evaluation & Guardrails median
235
stars
+1.4% 30d
commit ~15d ago
Leader · impeccable
114.7k
stars
+0.0% 30d
commit today

Ranked 149th of 872 by stars.

Ranked by shared tags, then keywords, then stars

Where SurrogateShield sits

Hover or focus a node for details. Click to open it.

  • This repo
  • Related repo
  • Tag or category
  1. Keep secrets and PII out of logs, Sentry, LLM prompts and commits. Reads values, not field names. Zero…

    Committed yesterday · TypeScript · MIT

    Shares Evaluation & Guardrails, Tools & Integrations

  2. Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket…

    +55 (+5.7%) in 30d · Committed today · Go · Apache-2.0

    Shares Evaluation & Guardrails, Tools & Integrations

  3. Agentic SDLC infrastructure. Define guardrails. Collect signals. Enforce continuously. Signed records of what…

    +11 (+1.8%) in 30d · Committed today · Go · Apache-2.0

    Shares Evaluation & Guardrails, Tools & Integrations

  4. SecureClaw - Security Plugin and Skill for OpenClaw OWASP-Aligned

    +3 (+0.9%) in 30d · Committed 223d ago · TypeScript

    Shares Tools & Integrations, Evaluation & Guardrails

  5. Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane…

    +9 (+4.5%) in 30d · Committed 67d ago · Python · MIT

    Shares Tools & Integrations, Evaluation & Guardrails

  6. Wireshark-like forensic analysis for Model Context Protocol communications Capture, inspect, and investigate…

    +0 (+0.0%) in 30d · Committed 209d ago · JavaScript · Other license

    Shares Evaluation & Guardrails, Tools & Integrations

  7. OpenKeylet — Local password and credential manager for AI agents via MCP. Use passwords, API keys, SSH, and…

    +7 (+5.4%) in 30d · Committed 27d ago · Rust · MIT

    Shares Tools & Integrations, Evaluation & Guardrails

  8. An Execution Isolation Architecture for LLM-Based Agentic Systems

    +4 (+3.2%) in 30d · Committed 659d ago · Python · Other license

    Shares Evaluation & Guardrails, Tools & Integrations

  9. Text-to-SQL access control: schema selection that gives the LLM only the tables the caller is allowed to read…

    +22 (+21%) in 30d · Committed 3d ago · Python · Apache-2.0

    Shares Tools & Integrations, Evaluation & Guardrails

  10. Independent security verification for code written by humans and AI agents. Scan, repair, then prove it —…

    +3 (+2.5%) in 30d · Committed yesterday · TypeScript · MIT

    Shares Tools & Integrations, Evaluation & Guardrails

Language
Python
License
Apache License 2.0
Contributors
1
Forks
137
Watchers
1
Open issues
0
Releases
2
Created
2026-05-13
Stars this week
+30

You've seen where SurrogateShield stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain SurrogateShield?

Claim this page to add your own call-to-action.

Claim this page