Sandbox
25 repos for sec · Harnesses · CodexClear
huytieu/
COG-second-brain

Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.

1.2k

🌊 Lagune is your security copilot as you build, your Blue Team when you audit, whether you're a developer or not (no API key needed).

148
aisa-group/
skill-inject

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

96
affaan-m/
ECC
affaan-m/ECCHarnesses

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

258k

Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.

173
TheAstrelo/
Claude-Pipeline

Tool-agnostic 13-phase AI development pipeline — turns a task description into reviewed, committed code through automated design, adversarial review, security, test, and code-review gates. One bash engine, balanced Opus/Sonnet routing, self-healing commit review.

45
mturac/
everything-openai-codex

EOC: open-source operating system for OpenAI Codex workflows with agents, skills, hooks, rules, memory, safety gates, and cross-harness adapters.

90
CodelyTV/
agent-harness

Our agent harness: Skills, plugins, hooks, and utilities to improve the quality of your agent.

261
blogminhquy/
javis-os

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

194
AnastasiyaW/
codex-claude-code-config

Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development

150
FrancyJGLisboa/
agent-skills-platform

Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery, updates, rollback, quarantine, and 17-platform distribution.

2.4k

Local-first runtime for project-scoped AI coding-agent sessions, with durable state, authority boundaries, and multi-harness interoperability.

47
ZhixiangLuo/
10xProductivity

Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.

474
aliengiraffe/
vigilante

Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.

40
AR6420/
Hail_Hydra

🐉 Hail Hydra — Multi-headed speculative execution framework for Claude Code. 10 AI agents, 3x faster, ~70% cheaper. Inspired by speculative decoding.

47
FailproofAI/
failproofai

Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement. 40 built-in policies, a local dashboard, no account required with a generous free cloud plan

2.7k
ruvnet/rufloHarnesses

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

72k
ruvnet/
metaharness

🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works with Claude Code, Codex, pi.dev, Hermes, OpenClaw, and RVM (hardware-isolated sandbox).

645
SamurAIGPT/
llm-wiki-agent

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

3.5k
wasintoh/
toh-framework

Type one sentence, approve once, walk away — Toh Framework installs an AI build department (14 commands, 8 agents, 23 skills) into your project and keeps building, testing and fixing until it is verified done. Works in Claude Code, Cursor, Antigravity, Codex and ZCode.

96

Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.

85