--- title: "harbor vs llm-app" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/av-harbor-vs-pathwaycom-llm-app" tools: ["av-harbor", "pathwaycom-llm-app"] --- # harbor vs llm-app *GraphCanon updated Sep 20, 2026* ## Verdict Pick harbor if harbor is a rapid deployment tool for AI stacks using Docker and docker-compose; pick llm-app if llm-app offers cloud templates for RAG, AI pipelines, and enterprise search, supporting integration with various data sources like Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-time data APIs. [harbor](https://discord.gg/8nDRphrhSF) reports 3.2k GitHub stars, 227 forks, and 67 open issues, last pushed Sep 19, 2026. [llm-app](https://pathway.com/developers/templates/) has 59k stars, 1.5k forks, and 8 open issues, last pushed Jul 5, 2026. Figures are from public GitHub metadata via [harbor's repository](https://github.com/av/harbor) and [llm-app's repository](https://github.com/pathwaycom/llm-app). | | [harbor](/tools/av-harbor.md) | [llm-app](/tools/pathwaycom-llm-app.md) | | --- | --- | --- | | Tagline | Complete pre-wired LLM stack via one command | Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data | | Stars | 3,217 | 58,920 | | Forks | 227 | 1,498 | | Open issues | 67 | 8 | | Language | Python | Jupyter Notebook | | Adopt for | Harbor is a rapid deployment tool for AI stacks using Docker and docker-compose. | llm-app offers cloud templates for RAG, AI pipelines, and enterprise search, supporting integration with various data sources like Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-time data APIs. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT License | | Categories | Inference & Serving, LLM Frameworks, Model Training | Data & Retrieval, Evaluation & Observability, Inference & Serving, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [harbor](/tools/av-harbor.md) | [llm-app](/tools/pathwaycom-llm-app.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Steady (60%) | | Days since push | 0d | 74d | | Open issues (now) | 67 | 8 | | Stars delta | +55 (30d) | -117 (30d) | | Open issues delta | +3 (30d) | 0 (30d) | | Owner type | User | Organization | | Full report | [trust report](/tools/av-harbor/trust.md) | [trust report](/tools/pathwaycom-llm-app/trust.md) | ## Decision facts: harbor - **Adopt for:** Harbor is a rapid deployment tool for AI stacks using Docker and docker-compose. ## Decision facts: llm-app - **Pricing:** freemium - The repository is open-source under the MIT License, but additional services or support might incur costs. - **Requirements:** Min 4 GB RAM; Requires Docker; Requires Docker for running the cloud templates.; Supports integration with a variety of data sources including Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-time data APIs. - **Adopt for:** llm-app offers cloud templates for RAG, AI pipelines, and enterprise search, supporting integration with various data sources like Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-time data APIs. - **License detail:** MIT License ## Choose when ### Choose harbor if… - harbor is primarily Python; llm-app is Jupyter Notebook. - License: harbor is Apache-2.0, llm-app is MIT. - Tags unique to harbor: ai, automation, bash, cli. - Also covers LLM Frameworks. - - When you need to deploy an AI stack quickly with minimal configuration ### Choose llm-app if… - llm-app is primarily Jupyter Notebook; harbor is Python. - License: llm-app is MIT, harbor is Apache-2.0. - Pricing: The repository is open-source under the MIT License, but additional services or support might incur costs.. - Requirements: Min 4 GB RAM; Requires Docker; Requires Docker for running the cloud templates.; Supports integration with a variety of data sources including Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-time data APIs.. - Tags unique to llm-app: chatbot, hugging-face, llm, llm-local. - Also covers Data & Retrieval, Evaluation & Observability. - When you need ready-to-run cloud templates for RAG, AI pipelines, and enterprise search that integrate seamlessly with data sources such as Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-ti ## When NOT to use harbor - - If detailed customization at a service level is required beyond what the default setup offers - - In cases where the project does not align well with the pre-wired services and configurations harbor provides by default ## When NOT to use llm-app - Avoid using llm-app if your project does not require integration with specific data sources like Sharepoint or Google Drive, as the tool's strength lies in its broad data source support. - Do not use llm-app if you are looking for a tool that focuses solely on model training or inference without the need for cloud templates or enterprise search capabilities. ## Common questions ### What is the difference between harbor and llm-app? harbor: Complete pre-wired LLM stack via one command. llm-app: Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. See the comparison table for live GitHub stats and shared categories. ### When should I choose harbor over llm-app? Choose harbor over llm-app when harbor is primarily Python; llm-app is Jupyter Notebook; License: harbor is Apache-2.0, llm-app is MIT; Tags unique to harbor: ai, automation, bash, cli; Also covers LLM Frameworks; - When you need to deploy an AI stack quickly with minimal configuration. ### When should I choose llm-app over harbor? Choose llm-app over harbor when llm-app is primarily Jupyter Notebook; harbor is Python; License: llm-app is MIT, harbor is Apache-2.0; Pricing: The repository is open-source under the MIT License, but additional services or support might incur costs.; Requirements: Min 4 GB RAM; Requires Docker; Requires Docker for running the cloud templates.; Supports integration with a variety of data sources including Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-time data APIs.; Tags unique to llm-app: chatbot, hugging-face, llm, llm-local; Also covers Data & Retrieval, Evaluation & Observability; When you need ready-to-run cloud templates for RAG, AI pipelines, and enterprise search that integrate seamlessly with data sources such as Sharepoint, Google Drive, S3, Kafka, PostgreSQL, and real-ti. ### When should I avoid harbor? - If detailed customization at a service level is required beyond what the default setup offers - In cases where the project does not align well with the pre-wired services and configurations harbor provides by default ### When should I avoid llm-app? Avoid using llm-app if your project does not require integration with specific data sources like Sharepoint or Google Drive, as the tool's strength lies in its broad data source support. Do not use llm-app if you are looking for a tool that focuses solely on model training or inference without the need for cloud templates or enterprise search capabilities. ### Is harbor or llm-app more popular on GitHub? llm-app has more GitHub stars (58,920 vs 3,217). Stars measure visibility, not whether either tool fits your constraints. ### Are harbor and llm-app open source? Yes - both are open-source projects on GitHub (harbor: Apache-2.0, llm-app: MIT). ### Where can I find alternatives to harbor or llm-app? GraphCanon lists graph-backed alternatives at [harbor alternatives](/tools/av-harbor/alternatives) and [llm-app alternatives](/tools/pathwaycom-llm-app/alternatives) ([harbor markdown twin](/tools/av-harbor/alternatives.md), [llm-app markdown twin](/tools/pathwaycom-llm-app/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/av-harbor-vs-pathwaycom-llm-app.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, harbor or llm-app? harbor: Very active. llm-app: Steady. 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 harbor and llm-app? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [harbor trust report](/tools/av-harbor/trust); [llm-app trust report](/tools/pathwaycom-llm-app/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=av-harbor`](/api/graphcanon/graph?tool=av-harbor) - 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/_