Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.
Repository Index
47,133 repositories indexed
121–144 of 150 · Most stars
Modern, profile-based hosts file manager for macOS. Block ads, trackers, and distractions with ease.
- ad-blocker
- dns
- hosts-file
- macos
Sandboxed devcontainer for running Claude Code, Codex, and OpenCode in bypass / auto-approve mode.
- ai
- claude-code
- codex
- devcontainer
High-performance network library for D programming language, event-driven asynchonous implemention(IOCP / kqueue / epoll).
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies
- autoresearch
- claude-code
- cli
- developer-tools
AfterGlow Cloud is a security visualization tool which lets users upload data and visualize the data as graphs on-the-fly (part of Google Summer of Code 2012).
Give the agent a cage, not your keys. One-command Docker sandbox for AI coding agents: full autonomous permissions, per-project isolation, your host stays untouched.
One isolated Lima VM per GitHub project — sandboxed Claude Code/Codex, Docker, Node, signed git
It falls out of your notch. Hotkey, repo, Return: your terminal opens with Claude Code, Codex or any agent already running. Free, MIT, local-only macOS.
Static analysis from configs → Kubernetes NetworkPolicies in seconds
🛡️ Static security scanner (SAST) for Ansible playbooks, roles, and collections. 1,000+ rules across 30+ categories detecting malicious code, RCE, hardcoded credentials, and supply-chain risk. Outputs SARIF, CycloneDX SBOM, and GitLab SAST. SLSA Build Level 3, Sigstore-signed.
- ansible
- ansible-playbook
- devsecops
- infrastructure-as-code
Agile Threat Modeling as Code
- cdk
- modeling
- threagile
- threat
A Commitment Scheme library for Coin Flipping/Tossing algorithms and sort. :four_leaf_clover: :camel: :lock: :key:
- ocaml
- commitment-schemes
- secure-multi-party-computation
- cryptography
Keep your secrets out of your AI coding agents. A local HTTPS proxy that swaps real credentials with placeholders and injects them at the network boundary.
A utility package for Google Apis in Blazor.
- auth
- blazor
- blazor-client
- blazor-server
AI writes. SPARDA proves. A deterministic, offline gate that catches when an AI edit removes a guard, exposes a route, or breaks an invariant — no API key, right in the agent edit loop.
- ai-agents
- ai-code-review
- authorization
- bola
Tamper-evident audit log for Go: an append-only, hash-chained, optionally Ed25519-signed log/slog handler, with offline logx verify. Built on the standard library, zero third-party dependencies. Also a full slog toolkit (colored output, JSON, rotation, fan-out, CLI).
- cli
- go
- golang
- slog
HTTP honeypot on autopilot
- canarytokens
- deception
- deception-technology
- honeypot
Pin AI Skill behavior. Block unapproved drift in CI. See exactly what changed in every PR.
- ai
- ai-skills
- apache-2
- claude-code
AWS_MSK_IAM Authentication Plugin for Broadway Kafka
A standalone fast word generator in the spirit of hashcat's mask generator with unicode support
- hashcat
- hashcat-masks
- password-cracking
- word-generator
Code for ASE'21 Paper "CorbFuzz: Checking Browser Security Policies with Fuzzing"
- fuzzing
- concolic-execution
- browser-security
Universal indie sales tracker for LemonSqueezy, Gumroad, and Stripe. iOS + macOS. 100% on-device privacy.
- gumroad
- indie-hacker
- ios
- lemonsqueezy
Crystal implementation of the Cipher-based Message Authentication Code (CMAC)