--- title: "Prompt-Engineering-Guide vs refly" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/dair-ai-prompt-engineering-guide-vs-refly-ai-refly" tools: ["dair-ai-prompt-engineering-guide", "refly-ai-refly"] --- # Prompt-Engineering-Guide vs refly *GraphCanon updated Jul 15, 2026* ## Verdict Pick Prompt-Engineering-Guide when prompt-Engineering-Guide is primarily MDX; refly is TypeScript; pick refly when refly is primarily TypeScript; Prompt-Engineering-Guide is MDX. [Prompt-Engineering-Guide](https://www.promptingguide.ai/) reports 76k GitHub stars, 8.4k forks, and 274 open issues, last pushed Mar 11, 2026. [refly](https://refly.ai) has 7.4k stars, 720 forks, and 93 open issues, last pushed Mar 25, 2026. Figures are from public GitHub metadata via [Prompt-Engineering-Guide's repository](https://github.com/dair-ai/Prompt-Engineering-Guide) and [refly's repository](https://github.com/refly-ai/refly). | | [Prompt-Engineering-Guide](/tools/dair-ai-prompt-engineering-guide.md) | [refly](/tools/refly-ai-refly.md) | | --- | --- | --- | | Tagline | Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents | The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are in | | Stars | 76,349 | 7,435 | | Forks | 8,361 | 720 | | Open issues | 274 | 93 | | Language | MDX | TypeScript | | Adopt for | Decision-critical facts for Prompt-Engineering-Guide | - | | Persona | - | - | | Runtime | - | - | | License | MIT | Other | | Categories | AI Agents, LLM Frameworks | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [Prompt-Engineering-Guide](/tools/dair-ai-prompt-engineering-guide.md) | [refly](/tools/refly-ai-refly.md) | | --- | --- | --- | | Days since push | 121d | 111d | | Open issues (now) | 274 | 93 | | Full report | [trust report](/tools/dair-ai-prompt-engineering-guide/trust.md) | [trust report](/tools/refly-ai-refly/trust.md) | ## Decision facts: Prompt-Engineering-Guide - **Adopt for:** Decision-critical facts for Prompt-Engineering-Guide ## Choose when ### Choose Prompt-Engineering-Guide if… - Prompt-Engineering-Guide is primarily MDX; refly is TypeScript. - License: Prompt-Engineering-Guide is MIT, refly is Other. - Tags unique to Prompt-Engineering-Guide: agents, ai-agents, chatgpt, deep-learning. - When you seek comprehensive documentation and educational materials specifically focused on the nuance of prompt engineering techniques. ### Choose refly if… - refly is primarily TypeScript; Prompt-Engineering-Guide is MDX. - License: refly is Other, Prompt-Engineering-Guide is MIT. - Tags unique to refly: agent-skills, automation, claude, clawdbot. ## 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. ## When NOT to use refly - Last GitHub push was 112 days ago (slowing maintenance, Mar 25, 2026). Validate activity before betting a new project on refly. - 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. ## Common questions ### What is the difference between Prompt-Engineering-Guide and refly? Prompt-Engineering-Guide: Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. refly: The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are in. See the comparison table for live GitHub stats and shared categories. ### When should I choose Prompt-Engineering-Guide over refly? Choose Prompt-Engineering-Guide over refly when Prompt-Engineering-Guide is primarily MDX; refly is TypeScript; License: Prompt-Engineering-Guide is MIT, refly is Other; Tags unique to Prompt-Engineering-Guide: agents, ai-agents, chatgpt, deep-learning; When you seek comprehensive documentation and educational materials specifically focused on the nuance of prompt engineering techniques. ### When should I choose refly over Prompt-Engineering-Guide? Choose refly over Prompt-Engineering-Guide when refly is primarily TypeScript; Prompt-Engineering-Guide is MDX; License: refly is Other, Prompt-Engineering-Guide is MIT; Tags unique to refly: agent-skills, automation, claude, clawdbot. ### 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. ### When should I avoid refly? Last GitHub push was 112 days ago (slowing maintenance, Mar 25, 2026). Validate activity before betting a new project on refly. 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. ### Is Prompt-Engineering-Guide or refly more popular on GitHub? Prompt-Engineering-Guide has more GitHub stars (76,349 vs 7,435). Stars measure visibility, not whether either tool fits your constraints. ### Are Prompt-Engineering-Guide and refly open source? Yes - both are open-source projects on GitHub (Prompt-Engineering-Guide: MIT, refly: Other). ### Where can I find alternatives to Prompt-Engineering-Guide or refly? GraphCanon lists graph-backed alternatives at [Prompt-Engineering-Guide alternatives](/tools/dair-ai-prompt-engineering-guide/alternatives) and [refly alternatives](/tools/refly-ai-refly/alternatives) ([Prompt-Engineering-Guide markdown twin](/tools/dair-ai-prompt-engineering-guide/alternatives.md), [refly markdown twin](/tools/refly-ai-refly/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/dair-ai-prompt-engineering-guide-vs-refly-ai-refly.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, Prompt-Engineering-Guide or refly? Prompt-Engineering-Guide: Slowing. refly: 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 Prompt-Engineering-Guide and refly? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [Prompt-Engineering-Guide trust report](/tools/dair-ai-prompt-engineering-guide/trust); [refly trust report](/tools/refly-ai-refly/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=dair-ai-prompt-engineering-guide`](/api/graphcanon/graph?tool=dair-ai-prompt-engineering-guide) - 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/_