--- title: "aqueduct vs xllm" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/runllm-aqueduct-vs-xllm-ai-xllm" tools: ["runllm-aqueduct", "xllm-ai-xllm"] --- # aqueduct vs xllm *GraphCanon updated Sep 29, 2026* ## Verdict Pick aqueduct if aqueduct is a deprecated Go-based tool for orchestrating LLM and ML workloads across various cloud infrastructures with Kubernetes support; pick xllm if a high-performance inference engine for LLM, VLM, DiT, and REC models by the OpenAtom Foundation. [aqueduct](https://aqueducthq.com) reports 518 GitHub stars, 20 forks, and 11 open issues, last pushed Jun 7, 2023. [xllm](https://xllm-ai.com/) has 1.6k stars, 300 forks, and 211 open issues, last pushed Sep 19, 2026. Figures are from public GitHub metadata via [aqueduct's repository](https://github.com/RunLLM/aqueduct) and [xllm's repository](https://github.com/xLLM-AI/xllm). | | [aqueduct](/tools/runllm-aqueduct.md) | [xllm](/tools/xllm-ai-xllm.md) | | --- | --- | --- | | Tagline | Orchestrate LLM and ML workloads on any cloud infrastructure using Go. | A high-performance inference engine for LLM, VLM, DiT and REC models | | Stars | 518 | 1,577 | | Forks | 20 | 300 | | Open issues | 11 | 211 | | Language | Go | C++ | | Adopt for | Aqueduct is a deprecated Go-based tool for orchestrating LLM and ML workloads across various cloud infrastructures with Kubernetes support. | A high-performance inference engine for LLM, VLM, DiT, and REC models by the OpenAtom Foundation. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | Apache-2.0 | | Categories | Inference & Serving, LLM Frameworks, Model Training | Inference & Serving | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [aqueduct](/tools/runllm-aqueduct.md) | [xllm](/tools/xllm-ai-xllm.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Very active (96%) | | Days since push | 1209d | 0d | | Open issues (now) | 11 | 211 | | Stars delta | +1 (30d) | +84 (30d) | | Open issues delta | 0 (30d) | +20 (30d) | | Full report | [trust report](/tools/runllm-aqueduct/trust.md) | [trust report](/tools/xllm-ai-xllm/trust.md) | ## Decision facts: aqueduct - **Adopt for:** Aqueduct is a deprecated Go-based tool for orchestrating LLM and ML workloads across various cloud infrastructures with Kubernetes support. ## Decision facts: xllm - **Adopt for:** A high-performance inference engine for LLM, VLM, DiT, and REC models by the OpenAtom Foundation. ## Choose when ### Choose aqueduct if… - aqueduct is primarily Go; xllm is C++. - Tags unique to aqueduct: ai, data, data-science, kubernetes. - Also covers LLM Frameworks, Model Training. - When you need to deploy legacy workflows that depend on Aqueduct's specific implementation of custom ops for resource allocation and training. ### Choose xllm if… - xllm is primarily C++; aqueduct is Go. - Tags unique to xllm: deepseek, glm, llm-inference. - When developing applications that require optimized performance on various AI accelerators ## When NOT to use aqueduct - Avoid if active project maintenance or community support is required as Aqueduct is no longer maintained. - Skip this tool for new projects focusing on state-of-the-art ML orchestration, opting instead for actively supported alternatives. ## When NOT to use xllm - If your project strictly requires Python-based inference engines for backend support - In cases preferring proprietary licenses over the Apache-2.0 open-source framework used here ## Common questions ### What is the difference between aqueduct and xllm? aqueduct: Orchestrate LLM and ML workloads on any cloud infrastructure using Go.. xllm: A high-performance inference engine for LLM, VLM, DiT and REC models. See the comparison table for live GitHub stats and shared categories. ### When should I choose aqueduct over xllm? Choose aqueduct over xllm when aqueduct is primarily Go; xllm is C++; Tags unique to aqueduct: ai, data, data-science, kubernetes; Also covers LLM Frameworks, Model Training; When you need to deploy legacy workflows that depend on Aqueduct's specific implementation of custom ops for resource allocation and training. ### When should I choose xllm over aqueduct? Choose xllm over aqueduct when xllm is primarily C++; aqueduct is Go; Tags unique to xllm: deepseek, glm, llm-inference; When developing applications that require optimized performance on various AI accelerators. ### When should I avoid aqueduct? Avoid if active project maintenance or community support is required as Aqueduct is no longer maintained. Skip this tool for new projects focusing on state-of-the-art ML orchestration, opting instead for actively supported alternatives. ### When should I avoid xllm? If your project strictly requires Python-based inference engines for backend support In cases preferring proprietary licenses over the Apache-2.0 open-source framework used here ### Is aqueduct or xllm more popular on GitHub? xllm has more GitHub stars (1,577 vs 518). Stars measure visibility, not whether either tool fits your constraints. ### Are aqueduct and xllm open source? Yes - both are open-source projects on GitHub (aqueduct: Apache-2.0, xllm: Apache-2.0). ### Where can I find alternatives to aqueduct or xllm? GraphCanon lists graph-backed alternatives at [aqueduct alternatives](/tools/runllm-aqueduct/alternatives) and [xllm alternatives](/tools/xllm-ai-xllm/alternatives) ([aqueduct markdown twin](/tools/runllm-aqueduct/alternatives.md), [xllm markdown twin](/tools/xllm-ai-xllm/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/runllm-aqueduct-vs-xllm-ai-xllm.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, aqueduct or xllm? aqueduct: Dormant. xllm: 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 aqueduct and xllm? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [aqueduct trust report](/tools/runllm-aqueduct/trust); [xllm trust report](/tools/xllm-ai-xllm/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=runllm-aqueduct`](/api/graphcanon/graph?tool=runllm-aqueduct) - 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/_