12 open-source projects share topics or a category with superpowers-zh. Each comparison below is drawn from recorded GitHub metadata — language, license, activity and review status. None of them is a judgement about which is better for you.
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Choose headroom if…
you would rather work in Python than JavaScript
Apache License 2.0 suits your use better than MIT License
you want the more widely starred option (78.7k)
you specifically need agent or ai
Shares claude-code, cursor, mcp, prompt-engineering with superpowers-zh.
Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
Choose loop-engineering if…
you would rather work in TypeScript than JavaScript
you specifically need agentic-ai or ai-agents
Shares ai-coding, claude-code, mcp, prompt-engineering with superpowers-zh.
A practical Claude Code guide with clear mental models and copy-paste examples — setup, prompt engineering, slash commands, skills, hooks, subagents, agent teams, and MCP servers. Beginner path to power-user depth. Featured in Awesome Claude Code.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Choose graphify if…
you would rather work in Python than JavaScript
Apache License 2.0 suits your use better than MIT License
you want the more widely starred option (141.6k)
you specifically need ai-agents or antigravity
Shares claude-code, cursor, mcp, skills with superpowers-zh.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Choose code-review-graph if…
you would rather work in Python than JavaScript
you want the more widely starred option (32.6k)
you specifically need claude or graphrag
Shares ai-coding, claude-code, code-review, mcp with superpowers-zh.
Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Spec-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.
Choose gentle-ai if…
you would rather work in Go than JavaScript
you specifically need ai-agents or codex
Shares agent-skills, ai-coding, claude-code, code-review with superpowers-zh.
Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.
Choose cc-sdd if…
you would rather work in TypeScript than JavaScript
you prefer a smaller, narrower project to a large one
you specifically need codex or github-copilot
Shares agent-skills, claude-code, cursor, gemini-cli with superpowers-zh.
AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,115+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.
Choose agentic-awesome-skills if…
you would rather work in Python than JavaScript
you want the more widely starred option (49.1k)
you specifically need agentic-skills or ai-agent-skills
Shares agent-skills, ai-coding, claude-code, cursor with superpowers-zh.
