--- title: "keras vs PocketFlow" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/keras-team-keras-vs-tencent-pocketflow" tools: ["keras-team-keras", "tencent-pocketflow"] --- # keras vs PocketFlow *GraphCanon updated Jul 12, 2026* ## Verdict Pick keras when license: keras is Apache-2.0, PocketFlow is Other; pick PocketFlow when license: PocketFlow is Other, keras is Apache-2.0. [keras](http://keras.io/) reports 64k GitHub stars, 20k forks, and 228 open issues, last pushed Jul 7, 2026. [PocketFlow](https://pocketflow.github.io) has 2.9k stars, 490 forks, and 75 open issues, last pushed Mar 31, 2023. Figures are from public GitHub metadata via [keras's repository](https://github.com/keras-team/keras) and [PocketFlow's repository](https://github.com/Tencent/PocketFlow). | | [keras](/tools/keras-team-keras.md) | [PocketFlow](/tools/tencent-pocketflow.md) | | --- | --- | --- | | Tagline | Deep Learning for humans | An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications. | | Stars | 64,191 | 2,909 | | Forks | 19,752 | 490 | | Open issues | 228 | 75 | | Language | Python | Python | | Adopt for | - | - | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Other | | Categories | Model Training | Inference & Serving, Model Training, Vector Databases | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [keras](/tools/keras-team-keras.md) | [PocketFlow](/tools/tencent-pocketflow.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Dormant (18%) | | Days since push | 4d | 1198d | | Open issues (now) | 228 | 75 | | Security scan | No criticals | No lockfile | | Full report | [trust report](/tools/keras-team-keras/trust.md) | [trust report](/tools/tencent-pocketflow/trust.md) | ## Choose when ### Choose keras if… - License: keras is Apache-2.0, PocketFlow is Other. - Tags unique to keras: data-science, jax, machine-learning, neural-networks. - More GitHub stars (64k vs 2.9k) - visibility, not fit. ### Choose PocketFlow if… - License: PocketFlow is Other, keras is Apache-2.0. - Tags unique to PocketFlow: automl, computer-vision, mobile-app, model-compression. - Also covers Inference & Serving, Vector Databases. ## When NOT to use keras - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ## When NOT to use PocketFlow - Last GitHub push was 1198 days ago (dormant maintenance, Mar 31, 2023). Validate activity before betting a new project on PocketFlow. - Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic. - Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## Common questions ### What is the difference between keras and PocketFlow? keras: Deep Learning for humans. PocketFlow: An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.. See the comparison table for live GitHub stats and shared categories. ### When should I choose keras over PocketFlow? Choose keras over PocketFlow when License: keras is Apache-2.0, PocketFlow is Other; Tags unique to keras: data-science, jax, machine-learning, neural-networks; More GitHub stars (64k vs 2.9k) - visibility, not fit. ### When should I choose PocketFlow over keras? Choose PocketFlow over keras when License: PocketFlow is Other, keras is Apache-2.0; Tags unique to PocketFlow: automl, computer-vision, mobile-app, model-compression; Also covers Inference & Serving, Vector Databases. ### When should I avoid keras? Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. ### When should I avoid PocketFlow? Last GitHub push was 1198 days ago (dormant maintenance, Mar 31, 2023). Validate activity before betting a new project on PocketFlow. Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic. Model Training: Try prompting and RAG first; fine-tuning is the answer to style/format, not missing knowledge. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### Is keras or PocketFlow more popular on GitHub? keras has more GitHub stars (64,191 vs 2,909). Stars measure visibility, not whether either tool fits your constraints. ### Are keras and PocketFlow open source? Yes - both are open-source projects on GitHub (keras: Apache-2.0, PocketFlow: Other). ### Where can I find alternatives to keras or PocketFlow? GraphCanon lists graph-backed alternatives at [keras alternatives](/tools/keras-team-keras/alternatives) and [PocketFlow alternatives](/tools/tencent-pocketflow/alternatives) ([keras markdown twin](/tools/keras-team-keras/alternatives.md), [PocketFlow markdown twin](/tools/tencent-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 [this comparison](/compare/keras-team-keras-vs-tencent-pocketflow.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, keras or PocketFlow? keras: Very active. PocketFlow: Dormant. 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 keras and PocketFlow? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [keras trust report](/tools/keras-team-keras/trust); [PocketFlow trust report](/tools/tencent-pocketflow/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=keras-team-keras`](/api/graphcanon/graph?tool=keras-team-keras) - 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/_