Search
tailnet-guard
Aryan Falahatpisheh <[email protected]>
Pure, dependency-free trust barrier for Tailscale-fronted services: tailnet/loopback membership, constant-time token auth, and bind-safety.
...moremcp-action-firewall
Bakir Talibov
A transparent MCP proxy that intercepts dangerous tool calls and requires OTP-based user approval.
diplomat-agent-ts
Scan TypeScript AI agent code for unguarded tool calls — pip wrapper for diplomat-agent-ts
agent-circuit-breaker
Sagar Chhatrala
Local-first safety runtime for AI coding agents
hemlock-scan
Supply-chain scanner for npm and PyPI. Flags packages that behave like an attack, not just ones with a CVE.
agentauthlayer
Vaibhav Ahluwalia
Library-first authentication and authorization SDK for AI agents
aileron
Kamal Lohchab <[email protected]>
Flight recorder for AI agents: tamper-evident audit logging, policy enforcement, and incident reports
e2e-encryption
mychewcents
Send and receive messages in an End-to-End Encrypted Environment.
gpt-oss-20b-redteam
Guy Nachshon <[email protected]>
GPT-OSS-20B Red-Teaming Harness: Masks, Sandbags, and Sabotage
antiscamai
AntiScam AI
AntiScam AI – AI-powered request inspection middleware for Python
injection-detector
Server-side prompt injection detection for AI applications. Drop-in protection for any Python app using OpenAI, Anthropic, or any LLM.
...moreairom
AIROM Authors
Python SDK for AIROM — the open-source AI Bill of Materials (AIBOM) scanner
amanai
Aji Purnomo <[email protected]>
Action Policy Engine for AI agents: policy-as-code for tool-calls — evaluate, enforce (block/warn/approve), and trace agent actions, with the same policy asserted in CI. Plus local guardrails and an offline judge. Pure-Python, zero dependencies.
...moreagentkey
AgentKey
Authorization and evidence SDK for AI agents: check permissions before every action, record what agents actually did.
is-safe-filename
sindresorhus
Check if a filename is safe to use in a path join operation
@xzar90/secure-storage
xzar90
Secure localStorage data with high level of encryption
agentscan-py
JohnDoeAnon
Read-only scanner for exposed AI/agent services: detects unauthenticated endpoints on standard ports and enumerates their API surface.
...morellm-taint
Lightweight taint tracking for LLM pipelines — label secrets at entry, block them at unsafe sinks
upash
simonepri
Unified API for password hashing algorithms
ecrypto-cli
rudra_826
Military-grade folder & file encryption tool with XChaCha20-Poly1305 and Argon2id. Interactive file browser, cross-platform CLI.
...more