--- title: "agent-toolkit vs pua" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/softaworks-agent-toolkit-vs-tanweai-pua" tools: ["softaworks-agent-toolkit", "tanweai-pua"] --- # agent-toolkit vs pua *GraphCanon updated Aug 19, 2026* ## Verdict Pick agent-toolkit if extends AI coding agent capabilities with Python skills for development and professional workflows; pick pua if decision-critical facts for pua, a skill package for enhancing the functionality of AI agents within development environments. [agent-toolkit](https://github.com/softaworks/agent-toolkit) reports 2.3k GitHub stars, 217 forks, and 17 open issues, last pushed Mar 5, 2026. [pua](https://openpua.ai/) has 19k stars, 1.2k forks, and 10 open issues, last pushed Jul 16, 2026. Figures are from public GitHub metadata via [agent-toolkit's repository](https://github.com/softaworks/agent-toolkit) and [pua's repository](https://github.com/tanweai/pua). | | [agent-toolkit](/tools/softaworks-agent-toolkit.md) | [pua](/tools/tanweai-pua.md) | | --- | --- | --- | | Tagline | A curated collection of skills for AI coding agents | A skill package for enhancing the functionality of AI agents within development environments | | Stars | 2,307 | 19,454 | | Forks | 217 | 1,185 | | Open issues | 17 | 10 | | Language | Python | TypeScript | | Adopt for | Extends AI coding agent capabilities with Python skills for development and professional workflows | Decision-critical facts for pua, a skill package for enhancing the functionality of AI agents within development environments. | | 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._ | | [agent-toolkit](/tools/softaworks-agent-toolkit.md) | [pua](/tools/tanweai-pua.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Steady (60%) | | Days since push | 159d | 34d | | Open issues (now) | 17 | 10 | | Stars delta | Unknown | +587 (30d) | | Open issues delta | Unknown | +1 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/softaworks-agent-toolkit/trust.md) | [trust report](/tools/tanweai-pua/trust.md) | ## Shared compatibility - **Cursor**: [agent-toolkit](/tools/softaworks-agent-toolkit.md) - Works with Cursor; [pua](/tools/tanweai-pua.md) - Works with Cursor ## Decision facts: agent-toolkit - **Adopt for:** Extends AI coding agent capabilities with Python skills for development and professional workflows ## 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. ## Choose when ### Choose agent-toolkit if… - agent-toolkit is primarily Python; pua is TypeScript. - Tags unique to agent-toolkit: agent-skills, ai, automation, claude-code. - For enhancing specific tasks like documentation, planning, and workflow management ### Choose pua if… - pua is primarily TypeScript; agent-toolkit 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, clawhub, codebuddy. - 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 NOT to use agent-toolkit - If you seek support for languages other than Python - When working with non-Python based coding agents that require specialized skills not covered by this toolkit - In cases where custom, from-scratch development is preferred over using pre-packaged scripts ## 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. ## Common questions ### What is the difference between agent-toolkit and pua? agent-toolkit: A curated collection of skills for AI coding agents. pua: A skill package for enhancing the functionality of AI agents within development environments. See the comparison table for live GitHub stats and shared categories. ### When should I choose agent-toolkit over pua? Choose agent-toolkit over pua when agent-toolkit is primarily Python; pua is TypeScript; Tags unique to agent-toolkit: agent-skills, ai, automation, claude-code; For enhancing specific tasks like documentation, planning, and workflow management. ### When should I choose pua over agent-toolkit? Choose pua over agent-toolkit when pua is primarily TypeScript; agent-toolkit 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, clawhub, codebuddy; 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 avoid agent-toolkit? If you seek support for languages other than Python When working with non-Python based coding agents that require specialized skills not covered by this toolkit In cases where custom, from-scratch development is preferred over using pre-packaged scripts ### 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. ### Is agent-toolkit or pua more popular on GitHub? pua has more GitHub stars (19,454 vs 2,307). Stars measure visibility, not whether either tool fits your constraints. ### Are agent-toolkit and pua open source? Yes - both are open-source projects on GitHub. ### Where can I find alternatives to agent-toolkit or pua? GraphCanon lists graph-backed alternatives at [agent-toolkit alternatives](/tools/softaworks-agent-toolkit/alternatives) and [pua alternatives](/tools/tanweai-pua/alternatives) ([agent-toolkit markdown twin](/tools/softaworks-agent-toolkit/alternatives.md), [pua markdown twin](/tools/tanweai-pua/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/softaworks-agent-toolkit-vs-tanweai-pua.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, agent-toolkit or pua? agent-toolkit: Slowing. pua: Steady. 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 agent-toolkit and pua? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [agent-toolkit trust report](/tools/softaworks-agent-toolkit/trust); [pua trust report](/tools/tanweai-pua/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=softaworks-agent-toolkit`](/api/graphcanon/graph?tool=softaworks-agent-toolkit) - 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/_