Skip to content
#

ai-firewall

Star

Here are 36 public repositories matching this topic...

Language: All
Filter by language
All 36 Python 17 TypeScript 7 Rust 3 Go 2 Elixir 1 Java 1
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated
pipelock

luckyPipewrench / pipelock

Sponsor
Star 723

Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.

golang security mcp dlp ssrf security-tools ai-agents integrity-monitoring ai-security security-scanning github-action prompt-injection llm-security fetch-proxy agent-security mcp-security ai-firewall ai-agent-security egress-proxy ssrf-protection
  • Updated Jun 18, 2026
  • Go

DmitrL-dev / AISecurity

Star 107

AI Security Platform: Defense (61 Rust engines + Micro-Model Swarm) + Offense (39K+ payloads)

python cybersecurity penetration-testing offensive-security ai-safety jailbreak-detection adversarial-attacks ai-security ai-red-team prompt-injection llm-security mcp-security ai-firewall langchain-alternative agentic-ai-security llm-attacks rlm-toolkit ai-security-academy owasp-asi-top10 llm-security-training
  • Updated Jun 19, 2026
  • Python

CollieAi / llm-firewall

Star 43

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

cybersecurity openai ai-safety adversarial-attacks machine-learning-security ai-security content-moderation guardrails responsible-ai pii-detection llm prompt-engineering generative-ai chatgpt prompt-injection llm-security ai-gateway hallucination-detection llm-observability ai-firewall
  • Updated Jun 14, 2026

Sushegaad / Semantic-Privacy-Guard

Star 12

Semantic Privacy Guard: A Java middleware that intercepts text, identifies PII using a three-layer hybrid pipeline (Regex + Naive Bayes ML + Apache OpenNLP NER), and redacts it before it reaches an LLM or leaves the corporate network — with stream-based processing for memory-efficient handling of large files and log streams.

java nlp middleware machine-learning maven regex naive-bayes compliance zero-dependency java-library data-privacy gdpr ai-safety pii-detection pii-redaction prompt-engineering llm-security llm-privacy eu-ai-act ai-firewall
  • Updated Jun 14, 2026
  • Java

issdandavis / SCBE-AETHERMOORE

Sponsor
Star 6

Geometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.

machine-learning cryptography post-quantum-cryptography hyperbolic-geometry multi-agent-systems autonomous-agents ai-safety security-framework ai-alignment adversarial-ml ai-governance poincare-ball ai-red-team prompt-injection llm-security patent-pending ai-firewall runtime-governance sacred-tongues geometric-security
  • Updated Jun 19, 2026
  • Python

WardLink / TrustLayer--Security-Control-Plane-For-LLM-AI

Star 5

TrustLayer is an API-first security control plane for LLM apps and AI agents. It protects production systems from prompt injection, tool hijacking, and behavioral drift, and provides incident lockdown when attacks are detected. Built for fast integration, low latency, and real production use.

saas artificial-intelligence cybersecurity ai-safety ai-agents llm langchain prompt-injection gpt-security llm-security ai-firewall
  • Updated Jan 31, 2026

vartulzeroshieldai / AIMeshFirewall

Star 2

ZeroShield AI Mesh Firewall is a centralized AI security gateway for governing LLM and RAG traffic with inline prompt injection defense, vector database isolation, multi model routing control, and compliance grade observability.

docker redis ai-security open-policy-agent fastapi ai-observability llm-security enterprise-ai litellm ai-gateway genai-security ai-infrastructure llm-governance ai-guardrails prompt-injection-defense ai-firewall multi-model-routing rag-security vector-database-security model-isolation
  • Updated Apr 23, 2026

tsm7979 / tsm79

Star 1

Inline AI control plane — polyglot dataplane (Rust + Python ML + Go + Java + .NET + C++) with sovereign overlay (.tsm) namespace. Prevention-first AI firewall — every prompt evaluated before it leaves the perimeter. MIT.

rust ed25519 ebpf xdp libp2p dataplane mtls ai-security pii-detection wasmtime secret-scanning ai-governance prompt-injection llm-security local-ai ai-gateway ai-firewall polyglot-architecture sovereign-overlay
  • Updated Jun 13, 2026
  • Rust

Improve this page

Add a description, image, and links to the ai-firewall topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

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

Learn more