Skip to content
#

prompt-guard

Star

Here are 18 public repositories matching this topic...

Language: All
Filter by language
All 18 Python 10 Jupyter Notebook 2 Go 1 JavaScript 1 Rust 1 Shell 1 TypeScript 1
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated
semantic_router

redhat-et / semantic_router

Star 22

LLM Semantic Router: Intelligent Mixture-of-Models (MoM) System with Privacy Preservation and Prompt Guard. The semantic router intelligently directs OpenAI compliant API requests to the most suitable backend models based on semantic understanding of request content.

python rust golang envoy-proxy pii-detection bert-fine-tuning mixture-of-models openai-api bert-classification llm-inference semantic-router prompt-guard
  • Updated Aug 30, 2025
  • Python

yfedoseev / jailguard

Star 13

Pure-Rust prompt-injection detector with 1.5MB embedded MLP classifier. 98.40% accuracy, p50 14ms CPU inference, bindings for Python/JS/Go. Apache-2.0/MIT alternative to Rebuff (archived) and Lakera Guard.

nodejs rust golang machine-learning neural-network python-bindings ai-safety security-tools jailbreak-detection onnx ai-security guardrails embedded-ml prompt-injection llm-security llm-firewall prompt-guard prompt-injection-detection rebuff-alternative lakera-alternative
  • Updated Aug 13, 2026
  • Rust

thehuanlwd / deepseek-v4-prompt-plus

Star 12

Local DeepSeek V4 proxy: reduces hallucinations strengthens system prompt following stops reasoning loops repairs empty tool-call replies — with built-in session analysis and GUI. / 本地 DeepSeek V4 代理：降低幻觉、增强 system prompt 遵循、防思维循环、修复空回复 自带会话分析与 GUI。

api-proxy hallucination instruction-following sillytavern llm-proxy deepseek anthropic-api deepseek-api prompt-guard openai-compatible anti-hallucination session-analysis deepseek-v4 anti-loop deepseek-proxy deepseek-v4-hallucination deepseek-v4-proxy
  • Updated Oct 17, 2026
  • Go

MoleCare / privacy-gate-llm

Star 2

Keep sensitive prompts local: a 1,024-weight head on bge-m3 that catches health data, credentials and PII written as plain English, which regex and entity tools miss. A second gate for LLM routers and guardrails. Not a medical device.

python privacy text-classification embeddings healthcare gdpr data-loss-prevention guardrails presidio pii-detection sentence-transformers local-llm ollama llm-safety molecare llm-router bge-m3 prompt-guard phi-detection not-a-medical-device
  • Updated Nov 4, 2026
  • Python

jafeeri / wardbreaker

Star 2

A local, zero-dependency fuzzer for open-weight LLM guardrails (Llama Guard, Prompt Guard). Measures per-family bypass rate and over-blocking - and verifies each bypass still works on the model behind the guard.

python jailbreak fuzzer ai-safety security-research red-teaming defensive-security guardrails huggingface adversarial-robustness llm prompt-injection llm-security ollama llama-guard llm-guardrails prompt-guard ai-red-teaming
  • Updated Sep 25, 2026
  • Python

ZZZEPOCHE / epochguard

Star 0

ARCHIVED - A practical hybrid safety middleware for Large Language Models. It runs both a FastAPI production endpoint and the original interactive CLI with heartbeat. For AI labs, red/blue teaming, prompt engineering

observability ai-safety prometheus-metrics ai-alignment fastapi responsible-ai prompt-injection conversation-memory llm-security llm-safety prompt-guard llm-guardrail hybrid-cli zzzepoche zzzepoche-epochguard
  • Updated Jul 22, 2026

Add this topic to your repo

To associate your repository with the prompt-guard topic, visit your repo's landing page and select "manage topics."

Learn more