data-privacy-stack/presidio
Presidio is an open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data, leveraging NLP and customizable pipelines.
Awesome Infra for AI › AI Safety & Guardrails
ZaxbyHub/opencode-swarm
OpenCode Swarm is a plugin for OpenCode that transforms a single AI coding session into a collaborative, architect-led team of specialized AI agents. It addresses the trust gap in AI-generated code by implementing a robust, gated execution pipeline where different agents handle planning, implementation, review, testing, and documentation. The project emphasizes security and quality assurance by requiring multiple approvals from dedicated agents, such as reviewers and test engineers, before any code ships. Key features include a wide array of specialized agents (architect, coder, reviewer, test_engineer, critic, etc.), a gated pipeline that ensures reviewer and test engineer approval, and a 'DEEP_DIVE Protocol' for on-demand codebase audits. Swarm also incorporates an 'External Skill Curation Pipeline' for validated skill discovery, robust security mechanisms like SAST, secrets scanning, dependency audits, and comprehensive shell write detection with scope enforcement to prevent unauthorized operations. It supports 20 programming languages and offers full configurability for agents and guardrails, ensuring that code generated by AI not only works but is also secure and adheres to project standards. The tool is designed to work with OpenCode Zen's free model roster and saves all state for resumable sessions, making it a practical solution for developers looking to integrate reliable AI-powered code generation into their workflows.
https://github.com/ZaxbyHub/opencode-swarm
Also in AI Safety & Guardrails
NVIDIA-NeMo/Guardrails
NVIDIA NeMo Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational applications, focusing on safety, security, and controlled dialog.
superagent-ai/superagent
Superagent is an open-source SDK providing safety features for AI applications, including prompt injection detection, PII redaction, repository scanning for threats, and red teaming capabilities fo...
Tencent/AI-Infra-Guard
AI-Infra-Guard is a full-stack AI red teaming platform providing comprehensive security analysis, vulnerability scanning, and jailbreak evaluation for AI ecosystems and LLMs.
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit (AGT) provides policy enforcement, identity management, execution sandboxing, and reliability engineering to secure autonomous AI agents in production.
FailproofAI/failproofai
Observability and policy enforcement for AI agent harnesses, hooking twelve coding and chat harnesses to record every run and block dangerous tool calls before they execute.
protectai/llm-guard
LLM Guard is a comprehensive open-source security toolkit designed to fortify Large Language Model (LLM) interactions by providing robust sanitization, malicious content detection, data leakage pre...
lennney/stop-that-shit
Multi-platform hook and skill guard for AI coding agents that blocks unrequested work such as generated hashes, checksums and task-scope expansion at the harness hook boundary.