#ai-agents

Repo Seatbelt

A safety layer for AI coding agents. CLAUDE.md/AGENTS.md generator, MCP runtime guardrail, pre-commit hook, GitHub Action.

Screenbox

Real virtual desktops for AI agents. MCP-native, self-hosted, fully isolated.

RunawayContext

Persistent context for any AI agent with rules that hold themselves.

Shellguard

MCP server that gives LLM agents read-only shell access over SSH. Powers Fawdy (fawdy.com)

Skill Manager

Automatically detect and disable irrelevant Claude Code skills per project to save tokens and streamline your tech workflow.

Deloc

Open-source CLI and MCP for Deloc — deploy static apps from your terminal or AI coding agent

Prism

First adversarial AI validator on ERC-8004

Genetic AI Starter

From 50% to 100% agent success on complex repos: portable map-first kit - genetic tags, subsystem indexes, controlled-change genes, validate...

Codex Plus Hermes Team

Local MCP bridge that gives Codex a specialist Hermes Agent team

Agentsonar

Coordination intelligence for any agent system

Vexp Swe Bench

Open benchmark for AI coding agents on SWE-bench Verified. Compare resolution rates, cost, and unique wins.

Teamfuse

Fuse Claude Code agents into a working team. AgentDM-powered template with a cabinet-style control panel, five starter roles