Sandbox
1,105 repos for cursor · CodexClear

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

466
ChenChenyaqi/
learn-anything

Learn Anything is an AI-powered recursive learning system — Socratic deep-dives and TDD-style exercises integrated directly into your coding assistant.

436
alirezarezvani/
ClaudeForge

A CLAUDE.md Generator and Maintenance tool for for Claude Code to create high-quality CLAUDE.md instruction files — aligned with Anthropic’s best practices for Claude Code.

424
FrkAk/
piyaz
FrkAk/piyazConnectors

The agentic workspace where people and agents work together in the loop.

190
seuros/
action_mcp
seuros/action_mcpFrameworks & SDKs

Rails Engine with MCP compliant Spec.

120
JingxuanC/
causal-memory

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

71
LeadMagic/
gtm-skills

GTM agent skills for Claude Code, Codex, and GitHub Copilot: sales, marketing, SEO, RevOps, and customer research playbooks with templates.

49
KyuRish/
mcp-dashboards

Turn your data into interactive dashboards inside any AI client - MCP Apps powered

45
etairl/
parallel-browser-mcp

An MCP server for parallel browser automation by AI agents with multiple cloud providers

42
JuliusBrussee/
caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

105k
1 add
openclaw/
Peekaboo

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

5.1k
evalstate/fast-agentFrameworks & SDKs

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

3.9k
MicrosoftDocs/
mcp

Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microsoft docs & code samples.

1.9k
evo-hq/evoPlugins

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

1.4k
yohey-w/
multi-agent-shogun

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

1.4k
Jane-xiaoer/
claude-skill-web-clone

Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code. Real source first.

996
zhuyansen/
agent-skills-hub

Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync

355

Agent skill that generates Apple-inspired bento grid presentation cards. For Claude Code, Codex, and any AI coding agent.

220
angristan/
fast-resume

Find that one coding agent session you want to get back to!

157
engasnm111/
lnwjud

lnwjud — local AI-agent runtime & MCP gateway

152
tikalk/
adlc-team-skills

🐙 ADLC Team Skills — Agentic SDLC for Engineering Teams

133
avivsinai/
agent-message-queue

File-based message queue for local agent-to-agent communication (Maildir-style)

85