Adding guardrails to large language models.
Repository Index
142,273 visible repositories in the index
1–19 of 19 · Most stars
NeMo Guardrails is an open-source library for applying programmable safety and security controls to LLM and agentic applications.
- agents
- guardrails
- python
- safety
Set of tools to assess and improve LLM security.
DeepTeam is a framework to red team LLMs and AI agents.
- llm-guardrails
- llm-red-teaming
- llm-safety
- python
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
- ai-gateway
- observability
- simulation
- ai-agents
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
- agentic-ai
- agentic-workflow
- agents
- function-calling
A security scanner for your LLM agentic workflows
- agentic-ai
- agentic-framework
- agentic-workflow
- ai
OpenClaw Security Vault — Atomic "claw" control: every AI reach, within your sight.
The repository host gives no description.
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.
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
- agent-security
- ai-agents
- audit-log
- claude-code
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
- cybersecurity
- security
- agent-security
- agents
AI Agent Identity and Access Management and Inference Firewall
- agent-identity
- ai-audit
- ai-firewall
- ai-gateway
Safely run your agents using any coding harness
- harness
- harness-ai
- security
Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
The repository host gives no description.
[ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
- action-proposals
- agentic-ai
- agents
- ai
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