The agentic pentesting environment that lives on your machine. AI agent teams, visual workflows and your own tools, 100% local.
- ai-agents
- bug-bounty
- electron
- offensive-security
Repository Index
47,133 repositories indexed
49–68 of 68 · Most stars
Open-source agentic security operations platform:
- agentic-security
- cyber-security
- cyber-threat-intelligence
- cybersecurity
A blade runner for your network. Detects shadow AI agents before they go rogue.
TranslatedFush Vue MCP — Vue frontend reverse engineering + web security testing tool (Chrome extension + MCP server, 91 tools)
TranslatedAn AI multi-agent security testing platform for authorized security testing and local research.
eBPF Information Flow Enforcement for AI Agent safety, security and effectiveness
- ebpf
- harness
- ifc
- policy-engine
Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.
eBPF Security Monitoring and Sandboxing Agent Based on Aya
AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.
- ai-agents
- document-processing
- dspy
- entity-extraction
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
Agentic LLM CTF to test prompt injection attacks and preventions
A SSH Server in Go that logs username/password combos
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
- golang
- observability
- opentelemetry
- policy-engine
Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.
opa-middleware gather all the middlewares you need to use Open Policy Agent with your API
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
- agentic-ai
- ai-safety
- fastapi
- langchain
Keep your secrets out of your AI coding agents. A local HTTPS proxy that swaps real credentials with placeholders and injects them at the network boundary.
💬 Lightweight AlgoChat client for corvid-agent — GitHub Pages hosted
- algochat
- algorand
- blockchain
- encrypted-messaging
Package to set up autonomous agents to trade on TBD
- agents
- agents-md
- ai-agents
- autonomous-agents