--- title: "llmflows vs PocketFlow" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/stoyan-stoyanov-llmflows-vs-the-pocket-pocketflow" tools: ["stoyan-stoyanov-llmflows", "the-pocket-pocketflow"] --- # llmflows vs PocketFlow Neutral, constraint-first comparison with live GitHub stats. | | [llmflows](/tools/stoyan-stoyanov-llmflows.md) | [PocketFlow](/tools/the-pocket-pocketflow.md) | | --- | --- | --- | | Tagline | LLMFlows - Simple, Explicit and Transparent LLM Apps | Pocket Flow: A minimalist LLM framework for agentic AI development. | | Stars | 706 | 10,946 | | Forks | 35 | 1,186 | | Open issues | 19 | 71 | | Language | Python | Python | | Adopt for | - | PocketFlow is a minimalist, lightweight Python library designed for building AI agents and workflows with large language models (LLMs) without any dependencies. | | Persona | - | - | | Runtime | - | - | | License | MIT | MIT | | Categories | Inference & Serving, Developer Tools | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [llmflows](/tools/stoyan-stoyanov-llmflows.md) | [PocketFlow](/tools/the-pocket-pocketflow.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Slowing (36%) | | Days since push | 502d | 103d | | Open issues (now) | 19 | 71 | | Owner type | User | Organization | | Security scan | 17 low (17 low) | No lockfile | | Full report | [trust report](/tools/stoyan-stoyanov-llmflows/trust.md) | [trust report](/tools/the-pocket-pocketflow/trust.md) | **Typed relationship:** llmflows _(alternative)_ PocketFlow PocketFlow is similar to LLMFlows as both aim at minimalist frameworks for building agentic AI applications. ## Shared compatibility - **Python**: [llmflows](/tools/stoyan-stoyanov-llmflows.md) - Python runtime; [PocketFlow](/tools/the-pocket-pocketflow.md) - Python runtime ## Decision facts: PocketFlow - **Adopt for:** PocketFlow is a minimalist, lightweight Python library designed for building AI agents and workflows with large language models (LLMs) without any dependencies. ## Choose when ### Choose llmflows if… - PocketFlow is similar to LLMFlows as both aim at minimalist frameworks for building agentic AI applications. - Tags unique to llmflows: llmops, vector-database, ai, python. - Also covers Inference & Serving, Developer Tools. ### Choose PocketFlow if… - PocketFlow is similar to LLMFlows as both aim at minimalist frameworks for building agentic AI applications. - Tags unique to PocketFlow: large-language-models, llm-agent, agentic-ai, retrieval-augmented-generation. - Also covers AI Agents, LLM Frameworks. - When you need to rapidly prototype or develop AI agents due to its extreme simplicity and small codebase. ## When NOT to use llmflows - Last GitHub push was 504 days ago (dormant maintenance, Feb 20, 2025). Validate activity before betting a new project on llmflows. - Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic. - Developer Tools: A gateway is overkill when you're pinned to a single provider and model. ## When NOT to use PocketFlow - If extensive customization and heavy dependency management are required for your project. - When a full-featured LLM framework with comprehensive abstractions is necessary to abstract away the complexity of building AI agents and workflows. ## Common questions ### What is the difference between llmflows and PocketFlow? llmflows: LLMFlows - Simple, Explicit and Transparent LLM Apps. PocketFlow: Pocket Flow: A minimalist LLM framework for agentic AI development.. See the comparison table for live GitHub stats and shared categories. ### When should I choose llmflows over PocketFlow? Choose llmflows over PocketFlow when PocketFlow is similar to LLMFlows as both aim at minimalist frameworks for building agentic AI applications; Tags unique to llmflows: llmops, vector-database, ai, python; Also covers Inference & Serving, Developer Tools. ### When should I choose PocketFlow over llmflows? Choose PocketFlow over llmflows when PocketFlow is similar to LLMFlows as both aim at minimalist frameworks for building agentic AI applications; Tags unique to PocketFlow: large-language-models, llm-agent, agentic-ai, retrieval-augmented-generation; Also covers AI Agents, LLM Frameworks; When you need to rapidly prototype or develop AI agents due to its extreme simplicity and small codebase. ### When should I avoid llmflows? Last GitHub push was 504 days ago (dormant maintenance, Feb 20, 2025). Validate activity before betting a new project on llmflows. Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic. Developer Tools: A gateway is overkill when you're pinned to a single provider and model. ### When should I avoid PocketFlow? If extensive customization and heavy dependency management are required for your project. When a full-featured LLM framework with comprehensive abstractions is necessary to abstract away the complexity of building AI agents and workflows. ### Is llmflows or PocketFlow more popular on GitHub? PocketFlow has more GitHub stars (10,946 vs 706). Stars measure visibility, not whether either tool fits your constraints. ### Are llmflows and PocketFlow open source? Yes - both are open-source projects on GitHub (llmflows: MIT, PocketFlow: MIT). ### Where can I find alternatives to llmflows or PocketFlow? GraphCanon lists graph-backed alternatives at /tools/stoyan-stoyanov-llmflows/alternatives and /tools/the-pocket-pocketflow/alternatives (/tools/stoyan-stoyanov-llmflows/alternatives.md, /tools/the-pocket-pocketflow/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 /compare/stoyan-stoyanov-llmflows-vs-the-pocket-pocketflow.md mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, llmflows or PocketFlow? llmflows: Dormant. PocketFlow: 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 llmflows and PocketFlow? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: llmflows: /tools/stoyan-stoyanov-llmflows/trust; PocketFlow: /tools/the-pocket-pocketflow/trust. --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=stoyan-stoyanov-llmflows`](/api/graphcanon/graph?tool=stoyan-stoyanov-llmflows) - 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/_