NVIDIA/SkillSpectorSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
Python★ 17.8K2026年9月19日
arcjet/arcjet-jsRuntime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.
TypeScript★ 682↓ 2.2M/月2026年9月11日
nolabs-ai/nonosecure multiplexed execution paths for agents - zero trust, zero setup, zero latency.
Rust★ 4,037↓ 118.6K/月2026年9月11日
Mindburn-Labs/helm-ai-kernelFail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Go★ 552026年9月10日
PyPI · crates.io · npm93卓越健康指数
hashgraph-online/hol-guardOpen-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Python · TypeScript★ 557↓ 95.5K/月2026年9月5日
Garudex-Labs/caracal🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.
TypeScript · Go★ 2062026年9月8日
Rul1an/assayOpen 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.
Rust · Python · Shell★ 13↓ 4,222/月2026年10月13日
Python★ 155↓ 2,902/月2026年8月25日
DataFog/datafog-pythonOffline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.
Python★ 72↓ 34K/月2026年9月9日
node9-ai/node9-proxyThe Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
TypeScript★ 211↓ 7,422/月2026年9月13日
Go · TypeScript · Python★ 67↓ 3,281/月2026年10月9日
responsibleai/agent-hooksFramework-neutral control contract for AI agents: eight interception points, three verdicts, and a conformance kit.
Rust · Python · Go★ 19↓ 31.1K/月2026年10月6日
vaaraio/vaaraAccountable 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.
Python★ 15↓ 7,475/月2026年10月20日
Agent-Threat-Rule/agent-threat-rulesOpen 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.
TypeScript★ 388↓ 72.8K/月2026年9月9日
Asymptote-Labs/agent-beaconAgent 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.
Go★ 3322026年9月8日
cfgaudit/cfgauditStatic 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.
Go★ 82026年10月20日
sattyamjjain/agent-airlockA 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.
Python★ 15↓ 3,569/月2026年9月18日
emiliaprotocol/emilia-protocolAuthority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
TypeScript · HTML★ 649↓ 1,109/月2026年9月5日
getlarge/themoltnetGive 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.
TypeScript · Go★ 16↓ 4,548/月2026年9月14日
PrismorSec/prismor 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.)
Python★ 343↓ 2,863/月2026年9月11日
opena2a-org/opena2aOne 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.
TypeScript★ 21↓ 16.4K/月2026年9月28日
peg/rampartOpen-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.
Go★ 832026年9月6日
perplexityai/numbatVisibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
Go★ 1,0682026年9月20日
Python★ 50↓ 46/月2026年9月20日
Go★ 12026年9月14日
lua-ai-global/governanceZero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
TypeScript★ 26↓ 18.7K/月2026年9月13日
Go · Python★ 162026年9月13日
pezhik/skilltotalScan AI components (MCP servers, agent skills, npm/PyPI packages) for malware & risky capabilities. Local, deterministic, evidence-anchored. Free & OSS.
Python★ 6↓ 2,906/月2026年10月9日
thewaltero/mythos-routerThe leaked Anthropic reasoning protocol. Running locally. Zero-drift coding with Strict Write Discipline and adaptive Claude Opus 5 thinking. Mythos
TypeScript★ 299↓ 321/月2026年9月9日
sinewaveai/agent-security-scanner-mcpSecurity scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.
JavaScript · Python · TypeScript★ 122↓ 2,960/月2026年10月9日