PyPI · crates.io · npm
hashgraph-online/hol-guard
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
Apache-2.02026年9月5日 · 指标 2.10.0
全部标签
目录标签
#agent-security
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
37 条记录
Go
mindburn-labs/helm-ai-kernel
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Apache-2.02026年7月17日 · 指标 2.10.0
PyPI · RubyGems
OWASP/www-project-agent-memory-guard
OWASP Foundation web repository
Apache-2.02026年8月25日 · 指标 2.10.0
Go
mindburn-labs/helm-oss
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Apache-2.02026年7月18日 · 指标 2.10.0
crates.io
nolabs-ai/nono
Sandbox any AI agent in seconds - zero setup, zero latency.
Apache-2.02026年7月16日 · 指标 2.10.0
crates.io
always-further/nono
Sandbox any AI agent in seconds - zero setup, zero latency.
Apache-2.02026年7月17日 · 指标 2.10.0
crates.io
lukehinds/nono
Sandbox any AI agent in seconds - zero setup, zero latency.
Apache-2.02026年7月19日 · 指标 2.10.0
PyPI
datafog/datafog-python
Offline PII firewall for AI agents and LLM apps: fast local detection and redaction, Claude Code hook, LiteLLM guardrail. Zero network calls, one dependency.
MIT2026年7月16日 · 指标 2.10.0
npm
garudex-labs/caracal
🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.
Apache-2.02026年7月15日 · 指标 2.10.0
npm
emiliaprotocol/emilia-protocol
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.
Apache-2.02026年9月5日 · 指标 2.10.0
PyPI
vaaraio/vaara
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.
AGPL-3.02026年8月22日 · 指标 2.10.0
Go
peg/rampart
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.
Apache-2.02026年9月6日 · 指标 2.10.0
npm · PyPI
Agent-Threat-Rule/agent-threat-rules
Open detection standard -- like Sigma, but for AI agents. 425 rules, shipped in Microsoft AGT, Cisco AI Defense, MISP, OWASP A-S-R-H. 97.1% recall on NVIDIA garak. NIST OSCAL Path 1.
MIT2026年7月16日 · 指标 2.10.0
Go
cfgaudit/cfgaudit
AI agent configuration security auditor - find misconfigurations in Claude Code, Cursor, and other AI tools
Apache-2.02026年8月23日 · 指标 2.10.0
npm
lua-ai-global/governance
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)
MIT2026年7月26日 · 指标 2.10.0
npm
node9-ai/node9-proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
自定义许可证2026年7月22日 · 指标 2.10.0
—
Asymptote-Labs/agent-beacon
Agent Beacon is the world's first open-source telemetry layer for AI agents wherever they run: locally, in CI, or in the cloud.
MIT2026年7月15日 · 指标 2.10.0
npm
Synapsor/Synapsor-Runner
Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
Apache-2.02026年8月22日 · 指标 2.10.0
crates.io · npm
backbay-labs/clawdstrike
AI EDR for developer workstations and autonomous agent fleets. Build Swarm Detection & Response platforms with Clawdstrike.
Apache-2.02026年8月4日 · 指标 2.10.0
Go
calbebop/batesian
Active security scanner for A2A and MCP servers
Apache-2.02026年7月27日 · 指标 2.10.0
npm
thewaltero/mythos-router
The leaked Anthropic reasoning protocol. Running locally. Zero-drift coding with Strict Write Discipline and adaptive Claude Opus 4.8 thinking. Mythos
MIT2026年7月17日 · 指标 2.10.0
npm
comisai/comis
Open-source security-first runtime for AI agents that learn and act across sessions.
Apache-2.02026年7月20日 · 指标 2.10.0
PyPI · npm
gautamvarmadatla/mcpsafetywarden
MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.
自定义许可证2026年8月1日 · 指标 2.10.0
PyPI
msaleme/red-team-blue-team-agent-fabric
540 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, MCP tool-poisoning reproduction. v4.9.1
Apache-2.02026年7月20日 · 指标 2.10.0
Go
openclaw/clawscan
Composable security scanning harness for agent skills
MIT2026年7月23日 · 指标 2.10.0
PyPI
philpaz/recusal
Deterministic governance for Claude and MCP tool calls. Pin approved capabilities, detect drift, and refuse unsafe or unapproved actions before execution. No model in the decision path.
Apache-2.02026年7月27日 · 指标 2.10.0
PyPI · npm
PrismorSec/prismor
Runtime Firewall for AI agents which catches the rogue tool call before it runs. Dangerous commands, secret leaks, prompt injection. For Claude Code, Codex and framework SDKs
Apache-2.02026年7月19日 · 指标 2.10.0
Go
tiagosilva07/zyrax-guard
Audit your AI agent configs before you run them — prompt injection, rogue MCP servers, credential-exfil. Plus dependency vetting.
MIT2026年8月28日 · 指标 2.10.0
Go
lelu-ai/lelu
Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail
MIT2026年7月16日 · 指标 2.10.0
npm
sgateway/s-gw
Local credential control for AI coding agents.
Apache-2.02026年7月29日 · 指标 2.10.0