--- title: "pua vs agents" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/tanweai-pua-vs-wshobson-agents" tools: ["tanweai-pua", "wshobson-agents"] --- # pua vs agents *GraphCanon updated Aug 19, 2026* ## Verdict Pick pua if decision-critical facts for pua, a skill package for enhancing the functionality of AI agents within development environments; pick agents if the agents tool is a marketplace for plugins that enhances multiple AI agents, offering integration and management capabilities across several platforms, including Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot. [pua](https://openpua.ai/) reports 19k GitHub stars, 1.2k forks, and 10 open issues, last pushed Jul 16, 2026. [agents](https://sethhobson.com) has 39k stars, 4.1k forks, and 5 open issues, last pushed Aug 18, 2026. Figures are from public GitHub metadata via [pua's repository](https://github.com/tanweai/pua) and [agents's repository](https://github.com/wshobson/agents). | | [pua](/tools/tanweai-pua.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Tagline | A skill package for enhancing the functionality of AI agents within development environments | Multi-harness agentic plugin marketplace for various AI agents | | Stars | 19,454 | 38,928 | | Forks | 1,185 | 4,145 | | Open issues | 10 | 5 | | Language | TypeScript | Python | | Adopt for | Decision-critical facts for pua, a skill package for enhancing the functionality of AI agents within development environments. | The agents tool is a marketplace for plugins that enhances multiple AI agents, offering integration and management capabilities across several platforms, including Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot | | Persona | - | - | | Runtime | - | - | | License | - | MIT | | Categories | AI Agents, Developer Tools | AI Agents, Developer Tools | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [pua](/tools/tanweai-pua.md) | [agents](/tools/wshobson-agents.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 34d | 1d | | Open issues (now) | 10 | 5 | | Stars delta | +587 (30d) | +860 (30d) | | Open issues delta | +1 (30d) | +2 (30d) | | Full report | [trust report](/tools/tanweai-pua/trust.md) | [trust report](/tools/wshobson-agents/trust.md) | ## Shared compatibility - **Cursor**: [pua](/tools/tanweai-pua.md) - Works with Cursor; [agents](/tools/wshobson-agents.md) - Works with Cursor ## Decision facts: pua - **Requirements:** Manual registration in `~/.claude/plugins/installed_plugins.json` to complete user-level installation.; The package supports various install methods, and manually registering its presence can integrate it with the user or project environment effectively.; For using bare command alias features, an additional setup is required. - **Adopt for:** Decision-critical facts for pua, a skill package for enhancing the functionality of AI agents within development environments. ## Decision facts: agents - **Adopt for:** The agents tool is a marketplace for plugins that enhances multiple AI agents, offering integration and management capabilities across several platforms, including Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot ## Choose when ### Choose pua if… - pua is primarily TypeScript; agents is Python. - Requirements: Manual registration in `~/.claude/plugins/installed_plugins.json` to complete user-level installation.; The package supports various install methods, and manually registering its presence can integrate it with the user or project environment effectively.; For using bare command alias features, an additional setup is required.. - Tags unique to pua: agency, agent, claude, clawhub. - A high performative AI agent is needed to improve code productivity and quality in development tools like Claude Code where P8 engineers' expertise is valued. ### Choose agents if… - agents is primarily Python; pua is TypeScript. - Tags unique to agents: agent-skills, agentic-ai, automation, prompt-engineering. - You are working specifically within the ecosystems of Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, or Gemini CLI, as it provides tailored plugins for these environments ## When NOT to use pua - This package may not fit well if your project management style does not align with PUA's specific operational environment requirements for various code editor platforms and scope settings (user-level, - project-level). - PUI should be avoided for environments where custom installations through command line interface are discouraged or when the integration into development tools like Claude Code is not desired. ## When NOT to use agents - You are working solely within a niche environment that isn't one of the supported platforms (like Claude Code, Codex CLI, etc.) because it may not offer compatible plugins or extensive support - Your project requirements do not include interoperability between multiple AI agents and you only need to leverage functionalities from a single AI agent with a robust in-built plugin ecosystem ## Common questions ### What is the difference between pua and agents? pua: A skill package for enhancing the functionality of AI agents within development environments. agents: Multi-harness agentic plugin marketplace for various AI agents. See the comparison table for live GitHub stats and shared categories. ### When should I choose pua over agents? Choose pua over agents when pua is primarily TypeScript; agents is Python; Requirements: Manual registration in `~/.claude/plugins/installed_plugins.json` to complete user-level installation.; The package supports various install methods, and manually registering its presence can integrate it with the user or project environment effectively.; For using bare command alias features, an additional setup is required.; Tags unique to pua: agency, agent, claude, clawhub; A high performative AI agent is needed to improve code productivity and quality in development tools like Claude Code where P8 engineers' expertise is valued. ### When should I choose agents over pua? Choose agents over pua when agents is primarily Python; pua is TypeScript; Tags unique to agents: agent-skills, agentic-ai, automation, prompt-engineering; You are working specifically within the ecosystems of Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, or Gemini CLI, as it provides tailored plugins for these environments. ### When should I avoid pua? This package may not fit well if your project management style does not align with PUA's specific operational environment requirements for various code editor platforms and scope settings (user-level, project-level). PUI should be avoided for environments where custom installations through command line interface are discouraged or when the integration into development tools like Claude Code is not desired. ### When should I avoid agents? You are working solely within a niche environment that isn't one of the supported platforms (like Claude Code, Codex CLI, etc.) because it may not offer compatible plugins or extensive support Your project requirements do not include interoperability between multiple AI agents and you only need to leverage functionalities from a single AI agent with a robust in-built plugin ecosystem ### Is pua or agents more popular on GitHub? agents has more GitHub stars (38,928 vs 19,454). Stars measure visibility, not whether either tool fits your constraints. ### Are pua and agents open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to pua or agents? GraphCanon lists graph-backed alternatives at [pua alternatives](/tools/tanweai-pua/alternatives) and [agents alternatives](/tools/wshobson-agents/alternatives) ([pua markdown twin](/tools/tanweai-pua/alternatives.md), [agents markdown twin](/tools/wshobson-agents/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/tanweai-pua-vs-wshobson-agents.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, pua or agents? pua: Steady. agents: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for pua and agents? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [pua trust report](/tools/tanweai-pua/trust); [agents trust report](/tools/wshobson-agents/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=tanweai-pua`](/api/graphcanon/graph?tool=tanweai-pua) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_