--- title: "hello-agents vs workflow" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/datawhalechina-hello-agents-vs-durable-workflow-workflow" tools: ["datawhalechina-hello-agents", "durable-workflow-workflow"] --- # hello-agents vs workflow *GraphCanon updated Jul 15, 2026* ## Verdict Pick hello-agents when hello-agents is primarily Python; workflow is PHP; pick workflow when workflow is primarily PHP; hello-agents is Python. [hello-agents](https://hello-agents.datawhale.cc) reports 65k GitHub stars, 8.1k forks, and 144 open issues, last pushed Jul 10, 2026. [workflow](https://durable-workflow.com) has 1.2k stars, 70 forks, and 0 open issues, last pushed Jul 15, 2026. Figures are from public GitHub metadata via [hello-agents's repository](https://github.com/datawhalechina/hello-agents) and [workflow's repository](https://github.com/durable-workflow/workflow). | | [hello-agents](/tools/datawhalechina-hello-agents.md) | [workflow](/tools/durable-workflow-workflow.md) | | --- | --- | --- | | Tagline | Course on building intelligent agents from scratch | Core package for defining and running durable workflows and activities. Supports long-running persistent workflows, retries, queues, parallel execution, workflow monitoring, dedicated storage connecti | | Stars | 65,432 | 1,217 | | Forks | 8,109 | 70 | | Open issues | 144 | 0 | | Language | Python | PHP | | Adopt for | hello-agents is a comprehensive guide and hands-on tutorial for developing AI agents using LLMs (Large Language Models) and RAG methods. | - | | Persona | - | - | | Runtime | - | - | | License | hello-agents is covered under an unconventional license which may require further review before usage. | MIT | | Categories | AI Agents, LLM Frameworks | AI Agents, Data & Retrieval, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [hello-agents](/tools/datawhalechina-hello-agents.md) | [workflow](/tools/durable-workflow-workflow.md) | | --- | --- | --- | | Open issues (now) | 144 | 0 | | Full report | [trust report](/tools/datawhalechina-hello-agents/trust.md) | [trust report](/tools/durable-workflow-workflow/trust.md) | ## Decision facts: hello-agents - **Requirements:** Min 4 GB RAM; Python knowledge assumed - **Adopt for:** hello-agents is a comprehensive guide and hands-on tutorial for developing AI agents using LLMs (Large Language Models) and RAG methods. - **License detail:** hello-agents is covered under an unconventional license which may require further review before usage. ## Choose when ### Choose hello-agents if… - hello-agents is primarily Python; workflow is PHP. - License: hello-agents is Other, workflow is MIT. - Requirements: Min 4 GB RAM; Python knowledge assumed. - Tags unique to hello-agents: agent, llm, rag, tutorial. - You should use hello-agents if you are interested in practical, step-by-step instructions on building intelligent agents from the ground up. ### Choose workflow if… - workflow is primarily PHP; hello-agents is Python. - License: workflow is MIT, hello-agents is Other. - Tags unique to workflow: background-jobs, bpm, bpmn, durable-functions. - Also covers Data & Retrieval. ## When NOT to use hello-agents - Avoid using hello-agents if you are looking for a quick, superficial introduction to AI agents; this tool focuses heavily on in-depth learning and practical application. - Do not opt for hello-agents if you want a more general AI development resource; unlike some competitors, it has a narrower focus specifically on agent creation with advanced methods like LLMs and RAG. ## When NOT to use workflow - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. - 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 hello-agents and workflow? hello-agents: Course on building intelligent agents from scratch. workflow: Core package for defining and running durable workflows and activities. Supports long-running persistent workflows, retries, queues, parallel execution, workflow monitoring, dedicated storage connecti. See the comparison table for live GitHub stats and shared categories. ### When should I choose hello-agents over workflow? Choose hello-agents over workflow when hello-agents is primarily Python; workflow is PHP; License: hello-agents is Other, workflow is MIT; Requirements: Min 4 GB RAM; Python knowledge assumed; Tags unique to hello-agents: agent, llm, rag, tutorial; You should use hello-agents if you are interested in practical, step-by-step instructions on building intelligent agents from the ground up. ### When should I choose workflow over hello-agents? Choose workflow over hello-agents when workflow is primarily PHP; hello-agents is Python; License: workflow is MIT, hello-agents is Other; Tags unique to workflow: background-jobs, bpm, bpmn, durable-functions; Also covers Data & Retrieval. ### When should I avoid hello-agents? Avoid using hello-agents if you are looking for a quick, superficial introduction to AI agents; this tool focuses heavily on in-depth learning and practical application. Do not opt for hello-agents if you want a more general AI development resource; unlike some competitors, it has a narrower focus specifically on agent creation with advanced methods like LLMs and RAG. ### When should I avoid workflow? AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Data & Retrieval: Skip a heavy ingestion framework when your corpus is small and static; a script plus the embedding API is enough. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ### Is hello-agents or workflow more popular on GitHub? hello-agents has more GitHub stars (65,432 vs 1,217). Stars measure visibility, not whether either tool fits your constraints. ### Are hello-agents and workflow open source? Yes - both are open-source projects on GitHub (hello-agents: Other, workflow: MIT). ### Where can I find alternatives to hello-agents or workflow? GraphCanon lists graph-backed alternatives at [hello-agents alternatives](/tools/datawhalechina-hello-agents/alternatives) and [workflow alternatives](/tools/durable-workflow-workflow/alternatives) ([hello-agents markdown twin](/tools/datawhalechina-hello-agents/alternatives.md), [workflow markdown twin](/tools/durable-workflow-workflow/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/datawhalechina-hello-agents-vs-durable-workflow-workflow.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, hello-agents or workflow? hello-agents: Very active. workflow: 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 hello-agents and workflow? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [hello-agents trust report](/tools/datawhalechina-hello-agents/trust); [workflow trust report](/tools/durable-workflow-workflow/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=datawhalechina-hello-agents`](/api/graphcanon/graph?tool=datawhalechina-hello-agents) - 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/_