Security & AI safety

AI guardrails & agent security

3,625 agents · most starred first

AI guardrails & agent security, page 37 of 37

semantic-kernel-surface

Surface for Semantic Kernel: the link-safety layer between an AI agent and the open web. One tool, surface_preflight, that tells your agent whether a link is worth fetching.

smolagents-surface

Surface for smolagents: the link-safety layer between an AI agent and the open web. One tool, surface_preflight, that tells your agent whether a link is worth fetching.

surface-haystack

Surface for Haystack: the link-safety layer between an AI agent and the open web. One tool, surface_preflight, that tells your agent whether a link is worth fetching.

vluthra-agent-ledger

Tamper-evident audit trails for AI agent tool calls: SHA-256 hash chains and Merkle trees. Python port of the npm package @vluthra/agent-ledger, with identical hashes and roots across languages.

ProofChain

Compliance rail for AI agents - on-chain audit trails, AgentID soulbound identity verification, and EU AI Act Article 50 reports.

HOL Guard

Open-source Apache-2.0 local runtime security for AI coding agents. Intercepts tool use (shell, secrets, MCP, installs) on your machine instead of trusting the model. Optional paid Guard Cloud.

trustdex

A local-first trust, provenance, and review gate for AI agent tools, MCP servers, skills, and plugins.

@hivecommons/rationguard

Detect and rebut rationalization patterns in AI agent output

@7one/vite-agent-poisoner

Vite plugin for LLM agent evasion: adversarial vocabulary, uglification, and comment injection.

@sandboxaq/switch-trust-sdk-ts

Lightweight SDK for routing AI agent LLM traffic through a guardrails proxy

@oked/openai-agents

OKed for the OpenAI Agents SDK. Gates risky tool calls behind a human approval in Telegram or on the web dashboard.

auto-permission-system

Security for the Pi coding agent: zero-trust permission system, OS sandbox, tool guard, secret scanning and a Claude-style tool view. Pi permissions, Claude auto mode.

pi-agentic-core

Pure, I/O-free kernel for agentic-pi: manifests, grants, policy PDP, audit hash chain + anchor, budget math, gate pipeline. Zero runtime dependencies.

pi-agentic

Pi extension that turns a session into a governed agentic-org unit: default-deny, audited tool policy; bubblewrap-sandboxed bash; secret redaction; budget metering with escalation; org delegate/complete/escalate tools; manifest-listed project trust.

agentic-identity

People, agents, and the access they share: delegation, invites, links, and an audit trail.

affixio-agent-action-assurance

Signed agent mandates, constrained delegation and durable execution evidence.

agenticreq

Checks whether an agentic AI system's declared requirements are enforced in its code, with measured confidence and without any LLM.

agentsec-pack

Measure what an AI agent's sandbox lets it reach: network, secrets, host filesystem, privileges and processes, from inside the sandbox.

curbi-langchain

Fail-closed remote Curbi configured-rule checking for LangChain text runnables

curbi-llamaindex

Fail-closed remote Curbi configured-rule checking for completed LlamaIndex responses

langchain-sealkeeper

LangChain tools and gates that check a SealKeeper SEAL before an agent calls an agent or an MCP server.

langchain-x402-cleanweb

LangChain official tool integration for x402 CleanWeb Agent (87% token reduction, multimodal alt-text, anti-prompt injection, and autonomous micropayments)

tba-provider-jose-swarmauri

Deprecated compatibility facade; use tba-provider-identity-jose instead.

handup

AI agents send handup the real command, diff, file or email draft before they act. You approve, or deny with a note, from the terminal, desktop app or Android. Works with Claude Code, Codex, Cursor, omp and any MCP client. 14-day trial, then $30 once.

Agent Security Index

Agent Security Index is a free, independent directory of 102 AI agent security tools. It covers guardrails, red teaming, MCP security, observability and governance. Each listing has a plain summary, and the site sends a weekly briefing on agent security news.

More in Security & AI safety