Sandbox
39 repos for ats · TestingClear
pbshgthm/
arc-skill

An agent skill that plays ARC-AGI-3. One rule: say what an action will do before you spend it. Claude Code on Opus 5 finished all 25 public games at 100.00 RHAE in 7,645 actions.

89
coleam00/
dark-factory-experiment

A repository that ships its own code. AI workflows triage issues, implement them, review, and auto-merge with no human reading the diff. Runs on Archon. The app it maintains is a cited RAG chat over YouTube transcripts, live at chat.dynamous.ai.

151
NVIDIA/
NeMo-Relay
NVIDIA/NeMo-RelayFrameworks & SDKs

Multi-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.

169
proxysoul/
Empryo

Empryo issue tracker + SoulForge (v2). Empryo is the graph-powered AI coding agent that edits symbols, not strings: AST surgery, full LSP, a live code genome. Get it at https://empryo.com

1.2k
KryptosAI/
mcp-observatory

CI-native security testing for MCP servers. Attack simulation, schema drift detection, and health scoring before agents depend on them.

146

Find and repair substance defects in AI-assisted prose, code, docs, and agent output. Reports defects, never authorship. Structural tests over model judgement, because LLM judges agree with human slop labels at chance.

48

🤖 The one and only Claude Code Skill to Upgrade Rails by FastRuby.io -- Based on 60,000 dev/hours of experience upgrading Rails from 2.3 all the way to 8.1. Dual boot your Rails application and gradually upgrade one minor version at a time. 🚀

382
arpitnath/
claude-capsule-kit

A toolkit that makes Claude Code better at engineering — session memory, dependency analysis, large file navigation, 18 specialist agents, and crew teams for parallel multi-branch work.

90
mixpeek/
amux

Open-source control plane for AI coding agents. Run an AI engineering team: parallel Claude Code, Codex, and Gemini workers with a shared board, atomic tasks, schedules, loops, origin-stamped messaging, model switching, and self-healing recovery. One dashboard, or your phone. MIT, single Rust binary.

437
jpicklyk/
task-orchestrator

Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce — the server blocks the call if they don't. Works with any MCP-compatible client.

205
redhat-et/
ripwire

The ripgrep of AI context: a zero-dependency C++23 CLI + MCP server for coding agents. Find what you want without reading the repo, then check you built what you meant — blast radius, tests-to-run, quality deltas. Signatures at 74.7% fewer bytes than bodies; every guess labelled, every loss published. Paddle out with a map.

1.9k

AIPex: AI browser automation assistant, no migration and privacy first. Alternative to Manus Browser Operator、 Claude Chrome and Agent Browser

1.3k

MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland -- 30 tools for virtual and live sessions

48
doeixd/
opencode-ralph-rlm

OpenCode plugin: Ralph outer loop + RLM inner loop — iterative AI development with file-first discipline and sub-agent support

31
statsclaw/
statsclaw

A workflow framework for statistical package development

92