--- title: "PokeClaw vs Prompt-Engineering-Guide" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/agents-io-pokeclaw-vs-dair-ai-prompt-engineering-guide" tools: ["agents-io-pokeclaw", "dair-ai-prompt-engineering-guide"] --- # PokeClaw vs Prompt-Engineering-Guide *GraphCanon updated Jul 15, 2026* ## Verdict Pick PokeClaw when pokeClaw is primarily Kotlin; Prompt-Engineering-Guide is MDX; pick Prompt-Engineering-Guide when prompt-Engineering-Guide is primarily MDX; PokeClaw is Kotlin. [PokeClaw](https://github.com/agents-io/PokeClaw) reports 961 GitHub stars, 132 forks, and 25 open issues, last pushed Jun 2, 2026. [Prompt-Engineering-Guide](https://www.promptingguide.ai/) has 76k stars, 8.4k forks, and 274 open issues, last pushed Mar 11, 2026. Figures are from public GitHub metadata via [PokeClaw's repository](https://github.com/agents-io/PokeClaw) and [Prompt-Engineering-Guide's repository](https://github.com/dair-ai/Prompt-Engineering-Guide). | | [PokeClaw](/tools/agents-io-pokeclaw.md) | [Prompt-Engineering-Guide](/tools/dair-ai-prompt-engineering-guide.md) | | --- | --- | --- | | Tagline | PokeClaw (PocketClaw), first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket. | Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents | | Stars | 961 | 76,349 | | Forks | 132 | 8,361 | | Open issues | 25 | 274 | | Language | Kotlin | MDX | | Adopt for | - | Decision-critical facts for Prompt-Engineering-Guide | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | AI Agents, LLM Frameworks | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [PokeClaw](/tools/agents-io-pokeclaw.md) | [Prompt-Engineering-Guide](/tools/dair-ai-prompt-engineering-guide.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Slowing (36%) | | Days since push | 43d | 121d | | Open issues (now) | 25 | 274 | | Full report | [trust report](/tools/agents-io-pokeclaw/trust.md) | [trust report](/tools/dair-ai-prompt-engineering-guide/trust.md) | ## Decision facts: Prompt-Engineering-Guide - **Adopt for:** Decision-critical facts for Prompt-Engineering-Guide ## Choose when ### Choose PokeClaw if… - PokeClaw is primarily Kotlin; Prompt-Engineering-Guide is MDX. - License: PokeClaw is Apache-2.0, Prompt-Engineering-Guide is MIT. - Tags unique to PokeClaw: accessibility, ai-agent, android-automation, gemma4. ### Choose Prompt-Engineering-Guide if… - Prompt-Engineering-Guide is primarily MDX; PokeClaw is Kotlin. - License: Prompt-Engineering-Guide is MIT, PokeClaw is Apache-2.0. - Tags unique to Prompt-Engineering-Guide: agent, agents, ai-agents, chatgpt. - When you seek comprehensive documentation and educational materials specifically focused on the nuance of prompt engineering techniques. ## When NOT to use PokeClaw - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ## When NOT to use Prompt-Engineering-Guide - Avoid using if your focus is entirely on deep-learning frameworks without a need for detailed instructions or examples related to prompt crafting. - Not suitable when you require tools that go beyond guiding materials, such as custom prompts or direct software plugins provided by competitors focused more on practical implementation over learning. ## Common questions ### What is the difference between PokeClaw and Prompt-Engineering-Guide? PokeClaw: PokeClaw (PocketClaw), first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.. Prompt-Engineering-Guide: Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. See the comparison table for live GitHub stats and shared categories. ### When should I choose PokeClaw over Prompt-Engineering-Guide? Choose PokeClaw over Prompt-Engineering-Guide when PokeClaw is primarily Kotlin; Prompt-Engineering-Guide is MDX; License: PokeClaw is Apache-2.0, Prompt-Engineering-Guide is MIT; Tags unique to PokeClaw: accessibility, ai-agent, android-automation, gemma4. ### When should I choose Prompt-Engineering-Guide over PokeClaw? Choose Prompt-Engineering-Guide over PokeClaw when Prompt-Engineering-Guide is primarily MDX; PokeClaw is Kotlin; License: Prompt-Engineering-Guide is MIT, PokeClaw is Apache-2.0; Tags unique to Prompt-Engineering-Guide: agent, agents, ai-agents, chatgpt; When you seek comprehensive documentation and educational materials specifically focused on the nuance of prompt engineering techniques. ### When should I avoid PokeClaw? AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ### When should I avoid Prompt-Engineering-Guide? Avoid using if your focus is entirely on deep-learning frameworks without a need for detailed instructions or examples related to prompt crafting. Not suitable when you require tools that go beyond guiding materials, such as custom prompts or direct software plugins provided by competitors focused more on practical implementation over learning. ### Is PokeClaw or Prompt-Engineering-Guide more popular on GitHub? Prompt-Engineering-Guide has more GitHub stars (76,349 vs 961). Stars measure visibility, not whether either tool fits your constraints. ### Are PokeClaw and Prompt-Engineering-Guide open source? Yes - both are open-source projects on GitHub (PokeClaw: Apache-2.0, Prompt-Engineering-Guide: MIT). ### Where can I find alternatives to PokeClaw or Prompt-Engineering-Guide? GraphCanon lists graph-backed alternatives at [PokeClaw alternatives](/tools/agents-io-pokeclaw/alternatives) and [Prompt-Engineering-Guide alternatives](/tools/dair-ai-prompt-engineering-guide/alternatives) ([PokeClaw markdown twin](/tools/agents-io-pokeclaw/alternatives.md), [Prompt-Engineering-Guide markdown twin](/tools/dair-ai-prompt-engineering-guide/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/agents-io-pokeclaw-vs-dair-ai-prompt-engineering-guide.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, PokeClaw or Prompt-Engineering-Guide? PokeClaw: Steady. Prompt-Engineering-Guide: Slowing. 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 PokeClaw and Prompt-Engineering-Guide? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [PokeClaw trust report](/tools/agents-io-pokeclaw/trust); [Prompt-Engineering-Guide trust report](/tools/dair-ai-prompt-engineering-guide/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=agents-io-pokeclaw`](/api/graphcanon/graph?tool=agents-io-pokeclaw) - 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/_