All tags
Catalogue tag

#agent-security

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

23 records
Tagged “agent-security”Ranked by health index
Go
77Goodhealth index
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.
Go · Java★ 53Jul 17, 2026
Apache-2.0Jul 17, 2026 · metrics 1.13.0
crates.io
75Goodhealth index
always-further/nono
Sandbox any AI agent in seconds - zero setup, zero latency.
Rust★ 3,036Jul 17, 2026
Apache-2.0Jul 17, 2026 · metrics 1.13.0
crates.io
75Goodhealth index
lukehinds/nono
Sandbox any AI agent in seconds - zero setup, zero latency.
Rust★ 3,047Jul 19, 2026
Apache-2.0Jul 19, 2026 · metrics 1.13.0
Go
75Goodhealth index
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.
Go · Java★ 53Jul 18, 2026
Apache-2.0Jul 18, 2026 · metrics 1.13.0
crates.io
74Goodhealth index
nolabs-ai/nono
Sandbox any AI agent in seconds - zero setup, zero latency.
Rust★ 3,016Jul 16, 2026
Apache-2.0Jul 16, 2026 · metrics 1.13.0
PyPI
73Goodhealth index
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.
Python★ 67↓ 34K/moJul 16, 2026
MITJul 16, 2026 · metrics 1.13.0
npm
73Goodhealth index
garudex-labs/caracal
🐾 Authority, not credentials, for AI agents: policy-approved actions, delegation that can only narrow, instant revocation, tamper-evident audit.
TypeScript · Go★ 155Jul 15, 2026
Apache-2.0Jul 15, 2026 · metrics 1.13.0
PyPI · npm
70Goodhealth index
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.
Python · TypeScript · JavaScript★ 396Jul 15, 2026
Custom licenseJul 15, 2026 · metrics 1.13.0
npm · PyPI
68Moderatehealth index
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.
TypeScript★ 314↓ 9,370/moJul 16, 2026
MITJul 16, 2026 · metrics 1.13.0
npm
66Moderatehealth index
node9-ai/node9-proxy
The Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
TypeScript★ 209↓ 9,089/moJul 22, 2026
Custom licenseJul 22, 2026 · metrics 1.13.0
npm
66Moderatehealth index
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
TypeScript★ 279↓ 579/moJul 17, 2026
MITJul 17, 2026 · metrics 1.13.0
—
65Moderatehealth index
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.
Go★ 293Jul 15, 2026
MITJul 15, 2026 · metrics 1.13.0
Go
65Moderatehealth index
calbebop/batesian
Active security scanner for A2A and MCP servers
Go★ 1Jul 22, 2026
Apache-2.0Jul 22, 2026 · metrics 1.13.0
npm
65Moderatehealth index
emiliaprotocol/emilia-protocol
Receipt Required for AI agents — no receipt, no irreversible action. An open, offline-verifiable authorization-receipt protocol: a named human signs the exact high-risk action (payment, deploy, delete, permissions) before it runs, and anyone can verify it later, trusting no one. Apache-2.0 · formally verified · IETF Internet-Drafts.
JavaScript★ 3↓ 934/moJul 15, 2026
Apache-2.0Jul 15, 2026 · metrics 1.13.0
PyPI
65Moderatehealth index
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
Python★ 20↓ 667/moJul 20, 2026
Apache-2.0Jul 20, 2026 · metrics 1.13.0
PyPI
65Moderatehealth index
vaaraio/vaara
Open-source evidence layer for AI governance. Gates every AI agent tool call against your policy and writes a hash-chained execution record an auditor verifies offline, without trusting the operator. Root-agnostic, and binds to a TPM 2.0 or SEV-SNP hardware root when present. Your environment, no SaaS, no telemetry. AGPL-3.0.
Python★ 10↓ 7,840/moJul 14, 2026
AGPL-3.0Jul 14, 2026 · metrics 1.13.0
npm
64Moderatehealth index
comisai/comis
Open-source security-first runtime for AI agents that learn and act across sessions.
TypeScript★ 5Jul 20, 2026
Apache-2.0Jul 20, 2026 · metrics 1.13.0
Go
63Moderatehealth index
openclaw/clawscan
Composable security scanning harness for agent skills
Go · Python★ 12Jul 23, 2026
MITJul 23, 2026 · metrics 1.13.0
PyPI · npm
62Moderatehealth index
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
Python · HTML★ 240↓ 6,171/moJul 19, 2026
Apache-2.0Jul 19, 2026 · metrics 1.13.0
Go
59Moderatehealth index
lelu-ai/lelu
Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail
TypeScript · Go★ 43Jul 16, 2026
MITJul 16, 2026 · metrics 1.13.0
Go
57Moderatehealth index
trustabl/trustabl
Static analyzer for agent reliability.
Go★ 22Jul 21, 2026
Apache-2.0Jul 21, 2026 · metrics 1.13.0
PyPI
52Moderatehealth index
vishnu-77/secchecker
No repository description published.
Python★ 1Jul 22, 2026
MITJul 22, 2026 · metrics 1.13.0
PyPI
42At riskhealth index
vdalal/agentx-security-sdk
Runtime action firewall for AI agents: the keyless Shield. Blocks catastrophic tool calls (DROP TABLE, SSRF, secret exfil) in-process, no key. MIT.
Python★ 0↓ 5,745/moJul 19, 2026
MITJul 19, 2026 · metrics 1.13.0