--- title: "gateway vs llm" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/adaline-gateway-vs-simonw-llm" tools: ["adaline-gateway", "simonw-llm"] --- # gateway vs llm *GraphCanon updated Sep 30, 2026* ## Verdict Pick gateway if adaline Gateway is a production-grade, fully local Super SDK that supports over 300 LLMs with a unified interface, including features like batching, retries, caching, and OpenTelemetry integration; pick llm if decision-critical facts for 'llm'. [gateway](https://www.adaline.ai/docs) reports 607 GitHub stars, 26 forks, and 2 open issues, last pushed Jul 29, 2026. [llm](https://llm.datasette.io) has 12k stars, 978 forks, and 689 open issues, last pushed Sep 2, 2026. Figures are from public GitHub metadata via [gateway's repository](https://github.com/adaline/gateway) and [llm's repository](https://github.com/simonw/llm). | | [gateway](/tools/adaline-gateway.md) | [llm](/tools/simonw-llm.md) | | --- | --- | --- | | Tagline | Super SDK for calling over 300 LLMs with a unified interface | Access large language models from the command-line | | Stars | 607 | 12,473 | | Forks | 26 | 978 | | Open issues | 2 | 689 | | Language | TypeScript | Python | | Adopt for | Adaline Gateway is a production-grade, fully local Super SDK that supports over 300 LLMs with a unified interface, including features like batching, retries, caching, and OpenTelemetry integration. | Decision-critical facts for 'llm' | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | Inference & Serving, LLM Frameworks | Inference & Serving, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [gateway](/tools/adaline-gateway.md) | [llm](/tools/simonw-llm.md) | | --- | --- | --- | | Maintenance | Steady (60%) | Very active (96%) | | Days since push | 52d | 4d | | Open issues (now) | 2 | 689 | | Stars delta | +2 (30d) | +149 (30d) | | Open issues delta | 0 (30d) | +25 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/adaline-gateway/trust.md) | [trust report](/tools/simonw-llm/trust.md) | ## Shared compatibility - **OpenAI API**: [gateway](/tools/adaline-gateway.md) - OpenAI API; [llm](/tools/simonw-llm.md) - OpenAI API ## Decision facts: gateway - **Adopt for:** Adaline Gateway is a production-grade, fully local Super SDK that supports over 300 LLMs with a unified interface, including features like batching, retries, caching, and OpenTelemetry integration. ## Decision facts: llm - **Requirements:** - Installation supports multiple methods including `pip`, Homebrew (with caveats noted), `pipx`, and `uv`.; - Requires an OpenAI API key for certain functionalities. - **Adopt for:** Decision-critical facts for 'llm' - **License detail:** Apache-2.0 ## Choose when ### Choose gateway if… - gateway is primarily TypeScript; llm is Python. - License: gateway is MIT, llm is Apache-2.0. - Tags unique to gateway: ai-agents, anthropic, language-model, llm. - When you need a fully local SDK that supports more than 300 LLMs with a unified interface. ### Choose llm if… - llm is primarily Python; gateway is TypeScript. - License: llm is Apache-2.0, gateway is MIT. - Requirements: - Installation supports multiple methods including `pip`, Homebrew (with caveats noted), `pipx`, and `uv`.; - Requires an OpenAI API key for certain functionalities.. - Tags unique to llm: llms. - - You prioritize command-line interaction over graphical interfaces, as llm is designed to provide a seamless CLI experience with multiple installation methods. ## When NOT to use gateway - If you are looking for a cloud-based service, as Adaline Gateway is fully local and not a proxy. - When you need support for a specific LLM that is not among the 300+ supported by Adaline Gateway. - If you do not require or want the complexity of a fully featured SDK with extensive customization options. - When you prefer a simpler, less extensible solution for calling LLMs. ## When NOT to use llm - - If you require real-time visual feedback or a graphical interface for interacting with language models, as llm is strictly command-line-based. - - If your primary focus is on model training rather than inference or serving, since llm is aimed at accessing and using pre-trained models. ## Common questions ### What is the difference between gateway and llm? gateway: Super SDK for calling over 300 LLMs with a unified interface. llm: Access large language models from the command-line. See the comparison table for live GitHub stats and shared categories. ### When should I choose gateway over llm? Choose gateway over llm when gateway is primarily TypeScript; llm is Python; License: gateway is MIT, llm is Apache-2.0; Tags unique to gateway: ai-agents, anthropic, language-model, llm; When you need a fully local SDK that supports more than 300 LLMs with a unified interface. ### When should I choose llm over gateway? Choose llm over gateway when llm is primarily Python; gateway is TypeScript; License: llm is Apache-2.0, gateway is MIT; Requirements: - Installation supports multiple methods including `pip`, Homebrew (with caveats noted), `pipx`, and `uv`.; - Requires an OpenAI API key for certain functionalities.; Tags unique to llm: llms; - You prioritize command-line interaction over graphical interfaces, as llm is designed to provide a seamless CLI experience with multiple installation methods. ### When should I avoid gateway? If you are looking for a cloud-based service, as Adaline Gateway is fully local and not a proxy. When you need support for a specific LLM that is not among the 300+ supported by Adaline Gateway. If you do not require or want the complexity of a fully featured SDK with extensive customization options. When you prefer a simpler, less extensible solution for calling LLMs. ### When should I avoid llm? - If you require real-time visual feedback or a graphical interface for interacting with language models, as llm is strictly command-line-based. - If your primary focus is on model training rather than inference or serving, since llm is aimed at accessing and using pre-trained models. ### Is gateway or llm more popular on GitHub? llm has more GitHub stars (12,473 vs 607). Stars measure visibility, not whether either tool fits your constraints. ### Are gateway and llm open source? Yes - both are open-source projects on GitHub (gateway: MIT, llm: Apache-2.0). ### Where can I find alternatives to gateway or llm? GraphCanon lists graph-backed alternatives at [gateway alternatives](/tools/adaline-gateway/alternatives) and [llm alternatives](/tools/simonw-llm/alternatives) ([gateway markdown twin](/tools/adaline-gateway/alternatives.md), [llm markdown twin](/tools/simonw-llm/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/adaline-gateway-vs-simonw-llm.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, gateway or llm? gateway: Steady. llm: 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 gateway and llm? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [gateway trust report](/tools/adaline-gateway/trust); [llm trust report](/tools/simonw-llm/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=adaline-gateway`](/api/graphcanon/graph?tool=adaline-gateway) - 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/_