Sandbox
1,488 repos for ai · CodexClear
us/crwConnectors

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary. Self-host or use managed cloud.

970
NVIDIA/
SkillEvaluator

Multi-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.

424
DY-2026/
GameDesignOS

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

385

MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run geotechnical & geomechanics simulations through natural conversation

178
20000419/
fauxnix

Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (Claude Code, Codex, OpenCode...). GNU-style output, bash-style errors, UTF-8/GBK handled.

160
Da7-Tech/
mind

Persistent memory for AI coding agents: automatic capture, explainable recall, knowledge consolidation, privacy controls, and portable offline storage. One Python file, zero dependencies.

76

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

56
hauptsacheNet/
typo3-mcp-server

One MCP endpoint connects your TYPO3 site to Claude, Cursor, n8n, and any AI tool — safely through workspaces.

96

Local-first 3-in-1 AI memory layer & MCP server for Claude Code, Codex, Grok, Gemini, VS Code and Cursor. Fuses session history, codebase indexing & concept graphs in SQLite. Enables zero-cloud, privacy-first context & instant recall, supports multi-agent swarms.

350

Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI interface which allows parallel AI agents ask questions to you. Be the human in the human-in-the-loop!

145
slaveOftime/
open-relay

oly turns long-running and interactive CLI workflows into persistent, supervised sessions for humans and AI agents. Close the terminal, keep the process alive, get notified when input is needed, and jump back in from anywhere.

93
hanlulong/
openecon-data

Give your AI agent accurate economic data. 330K indicators from FRED, World Bank, IMF, Eurostat & more. MCP server + web UI.

71
tddworks/
SkillsManager

A macOS application for discovering, browsing, and installing skills for AI coding assistants. Manage skills for Claude Code and Codex from GitHub repositories or your local filesystem.

165
thClaws/
thClaws

Open-source AI agent harness in native Rust — GUI, CLI, headless, and webapp from one binary. Multi-provider, MCP, skills, plugins, agent teams.

1.2k

Open-source workspace manager for AI coding CLIs: Claude Code and ChatGPT Codex in one browser app. Discovers every session on disk, embedded terminals, phone-ready, cost tracking, kanban, docs. Windows, macOS, Linux.

381

Caller-owned Discord operations for AI agents - 208 typed tools, safety controls, resumable guild builds, and Activity Evidence.

71
ashuiGordon/
stata-cli

Agent-native Stata CLI for AI coding agents (Codex, Claude Code, Cursor). Run .do files, inspect data, and return econometric results as JSON via PyStata.

56

Every local AI coding session in one tab: Claude Code, Codex and OpenCode in a single list, with a queue you can schedule and isolated Claude Desktop instances kept apart. Local, private, MCP-native.

43
musoyangrigor/
scroll-video-website-skill

Scroll Video Website is a portable AI-agent skill that turns videos into smooth, scroll-controlled canvas experiences with optimized WebP frames, progressive loading, and responsive animation.

36
pacifio/
atlas

Source control for agents. Use multiple coding agents, track their changes and query them in one place

3.3k

oh-my-zsh for Claude Code — 16 agents, 35 commands, 32 skills, 21 safety hooks in one install. v4.0 adds an adversarial review loop: a second agent that never sees the first one's reasoning. MIT.

835