#agent-security

🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.

Open evidence profile for MCP tool actions. Enforce configured tool-call policies and record decisions and observations in offline-verifiable bundles. Optional Linux kernel controls. No hosted backend required.

OWASP Foundation web repository

The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.

Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.

The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.

The IAM layer for AI agents: cryptographic identity, capability authorization, and audit trails for non-human identities. Open source.

Framework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.

Accountable Autonomy: open-source evidence layer that gates every AI agent tool call against your policy and writes a hash-chained record an auditor verifies offline, without trusting you. Root-agnostic; binds to TPM 2.0 / SEV-SNP when present. Your environment, no SaaS, no telemetry. AGPL-3.0.

Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable rules across 10 categories; merged into Microsoft AGT, Cisco AI Defense, MISP, OWASP, FINOS & SigmaHQ. MIT-licensed.

Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, in the browser, or in the cloud.

Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. 109 rules, SARIF output, OWASP LLM Top 10 mapping.

A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

Give an agent a job, not your keys. Open-source control plane for AI agent work: each agent gets its own identity, a bounded job, and a signed record of what it did.

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.)

One scan for AI risk. `opena2a review` checks an AI project across credentials, shadow agents, MCP servers, and dependencies, returns a score, and routes each finding to the tool that fixes it. Open source.

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

Executable security regression testing for agentic applications and MCP-integrated systems.

Active security scanner for A2A and MCP servers

Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)

Composable security scanning harness for agent skills

Scan AI components (MCP servers, agent skills, npm/PyPI packages) for malware & risky capabilities. Local, deterministic, evidence-anchored. Free & OSS.

The leaked Anthropic reasoning protocol. Running locally. Zero-drift coding with Strict Write Discipline and adaptive Claude Opus 5 thinking. Mythos