#1
Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.
8.2K starsMar 18, 2026 pushagent-frameworksShellAI Agents
$ npx skills add automazeio/ccpmAlternatives
Agent Safehouse alternatives for AI agents.
Compare similar skills by workflow fit, trust score, quality, GitHub adoption, maintenance, and install readiness.
Current skill
Agent Safehouse
Sandbox your local AI agents so they can read/write only what they need
100
Quality
90
Trust
1.8K
Stars
#2
🔂 Ralph loop with PRs: Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging
1.3K starsJun 6, 2026 pushagent-frameworksShellAI Agents
$ npx skills add AnandChowdhary/continuous-claude#3
A complete starter kit for an Obsidian + Claude Code personal knowledge management system.
1.5K starsFeb 18, 2026 pushagent-frameworksShellAI Agents
$ npx skills add ballred/obsidian-claude-pkm#4
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
30K starsJun 12, 2026 pushagent-frameworksTypeScriptAI Agents
$ npx skills add nanocoai/nanoclaw#5
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
99K starsJun 13, 2026 pushagent-frameworksPythonAI Agents
$ npx skills add browser-use/browser-use#6
A symbiotic AI agent that remembers everything, challenges you, and extends your cognition.
728 starsApr 18, 2026 pushagent-frameworksShellAI Agents
$ npx skills add lout33/symbiotic-ai#7
Open-source AI coworker, with memory
15K starsJun 14, 2026 pushagent-frameworksTypeScriptAI Agents
$ npx skills add rowboatlabs/rowboat#8
Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications
944 starsJun 15, 2026 pushagent-frameworksPythonAI Agents
$ npx skills add tensorlakeai/tensorlake#9
The Company AI Command Center
20K starsJun 15, 2026 pushagent-frameworksTypeScriptAI Agents
$ npx skills add kortix-ai/suna#10
Let AI agents browse the web. An autonomous toolkit for browser-based AI agents.
9.5K starsApr 2, 2026 pushagent-frameworksTypeScriptAI Agents
$ npx skills add ntegrals/openbrowser#11
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
7.2K starsJun 9, 2026 pushagent-frameworksTypeScriptAI Agents
$ npx skills add steel-dev/steel-browser#12
Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.
977 starsApr 25, 2026 pushagent-frameworksTypeScriptAI Agents
$ npx skills add patoles/agent-flow#13
Semi-Structured Agentic Framework. Workflows build themselves as agents discover what needs to be done, not what you predicted upfront.
1.2K starsDec 1, 2025 pushagent-frameworksPythonAI Agents
$ npx skills add Ido-Levi/Hephaestus#14
35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.
3.5K starsJun 8, 2026 pushagent-frameworksJupyter NotebookAI Agents
$ npx skills add FareedKhan-dev/all-agentic-architectures#15
Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.
1.8K starsJun 8, 2026 pushagent-frameworksPythonAI Agents
$ npx skills add GammaLabTechnologies/harmonist#16
Autonomous AI development loop for Claude Code with intelligent exit detection
9.3K starsJun 15, 2026 pushagent-frameworksShellAI Agents
$ npx skills add frankbria/ralph-claude-codeHow to choose
When should you switch?
Use an alternative when it has a clearer install path, higher trust score, fresher maintenance, or better platform fit for your current agent stack. Keep Agent Safehouse if it already passes your workflow test and repository review.
Next step
Compare top candidates side by side
Open the compare page, test the install commands in a sandbox, and check each repository before using a skill in production.