--- title: "semantic-kernel vs awesome-ai-apps" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/microsoft-semantic-kernel-vs-rohitg00-awesome-ai-apps" tools: ["microsoft-semantic-kernel", "rohitg00-awesome-ai-apps"] --- # semantic-kernel vs awesome-ai-apps *GraphCanon updated Aug 12, 2026* ## Verdict Pick semantic-kernel if semantic Kernel is a toolkit for integrating language model technologies into applications, supporting C#, .NET, Python, and Java; pick awesome-ai-apps if awesome-ai-apps offers curated AI application examples with diverse tech stacks including OpenAI, Gemini, and local models. [semantic-kernel](https://aka.ms/semantic-kernel) reports 28k GitHub stars, 4.7k forks, and 256 open issues, last pushed Aug 6, 2026. [awesome-ai-apps](https://agenstskills.com) has 817 stars, 174 forks, and 27 open issues, last pushed Feb 10, 2026. Figures are from public GitHub metadata via [semantic-kernel's repository](https://github.com/microsoft/semantic-kernel) and [awesome-ai-apps's repository](https://github.com/rohitg00/awesome-ai-apps). | | [semantic-kernel](/tools/microsoft-semantic-kernel.md) | [awesome-ai-apps](/tools/rohitg00-awesome-ai-apps.md) | | --- | --- | --- | | Tagline | Integrate cutting-edge LLM technology quickly and easily into your apps | A curated collection of AI Agents and LLM Apps with various tech stacks | | Stars | 28,427 | 817 | | Forks | 4,707 | 174 | | Open issues | 256 | 27 | | Language | C# | HTML | | Adopt for | Semantic Kernel is a toolkit for integrating language model technologies into applications, supporting C#, .NET, Python, and Java. | awesome-ai-apps offers curated AI application examples with diverse tech stacks including OpenAI, Gemini, and local models. | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | AI Agents, LLM Frameworks | AI Agents, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [semantic-kernel](/tools/microsoft-semantic-kernel.md) | [awesome-ai-apps](/tools/rohitg00-awesome-ai-apps.md) | | --- | --- | --- | | Maintenance | Very active (96%) | Slowing (36%) | | Days since push | 1d | 182d | | Open issues (now) | 256 | 27 | | Stars delta | +142 (30d) | Unknown | | Open issues delta | -2 (30d) | Unknown | | Owner type | Organization | User | | Full report | [trust report](/tools/microsoft-semantic-kernel/trust.md) | [trust report](/tools/rohitg00-awesome-ai-apps/trust.md) | ## Decision facts: semantic-kernel - **Adopt for:** Semantic Kernel is a toolkit for integrating language model technologies into applications, supporting C#, .NET, Python, and Java. ## Decision facts: awesome-ai-apps - **Adopt for:** awesome-ai-apps offers curated AI application examples with diverse tech stacks including OpenAI, Gemini, and local models. ## Choose when ### Choose semantic-kernel if… - semantic-kernel is primarily C#; awesome-ai-apps is HTML. - License: semantic-kernel is MIT, awesome-ai-apps is Apache-2.0. - Tags unique to semantic-kernel: artificial-intelligence, openai, sdk. - - When you are looking to integrate cutting-edge language models (LLMs) directly from major providers like Azure OpenAI or OpenAI into your application. ### Choose awesome-ai-apps if… - awesome-ai-apps is primarily HTML; semantic-kernel is C#. - License: awesome-ai-apps is Apache-2.0, semantic-kernel is MIT. - Tags unique to awesome-ai-apps: agents, apps, automation, framework. - For exploring real-world implementations of AI agents across different technologies ## When NOT to use semantic-kernel - - If you require support exclusively in programming languages not currently offered by Semantic Kernel (for example, Ruby, Go). - - When your project strictly avoids frameworks associated with Microsoft technologies and prefers more independent or community-driven alternatives. ## When NOT to use awesome-ai-apps - When seeking detailed implementation steps specific to one technology stack - In scenarios demanding a deep dive into proprietary or less publicly-known application codes ## Common questions ### What is the difference between semantic-kernel and awesome-ai-apps? semantic-kernel: Integrate cutting-edge LLM technology quickly and easily into your apps. awesome-ai-apps: A curated collection of AI Agents and LLM Apps with various tech stacks. See the comparison table for live GitHub stats and shared categories. ### When should I choose semantic-kernel over awesome-ai-apps? Choose semantic-kernel over awesome-ai-apps when semantic-kernel is primarily C#; awesome-ai-apps is HTML; License: semantic-kernel is MIT, awesome-ai-apps is Apache-2.0; Tags unique to semantic-kernel: artificial-intelligence, openai, sdk; - When you are looking to integrate cutting-edge language models (LLMs) directly from major providers like Azure OpenAI or OpenAI into your application. ### When should I choose awesome-ai-apps over semantic-kernel? Choose awesome-ai-apps over semantic-kernel when awesome-ai-apps is primarily HTML; semantic-kernel is C#; License: awesome-ai-apps is Apache-2.0, semantic-kernel is MIT; Tags unique to awesome-ai-apps: agents, apps, automation, framework; For exploring real-world implementations of AI agents across different technologies. ### When should I avoid semantic-kernel? - If you require support exclusively in programming languages not currently offered by Semantic Kernel (for example, Ruby, Go). - When your project strictly avoids frameworks associated with Microsoft technologies and prefers more independent or community-driven alternatives. ### When should I avoid awesome-ai-apps? When seeking detailed implementation steps specific to one technology stack In scenarios demanding a deep dive into proprietary or less publicly-known application codes ### Is semantic-kernel or awesome-ai-apps more popular on GitHub? semantic-kernel has more GitHub stars (28,427 vs 817). Stars measure visibility, not whether either tool fits your constraints. ### Are semantic-kernel and awesome-ai-apps open source? Yes - both are open-source projects on GitHub (semantic-kernel: MIT, awesome-ai-apps: Apache-2.0). ### Where can I find alternatives to semantic-kernel or awesome-ai-apps? GraphCanon lists graph-backed alternatives at [semantic-kernel alternatives](/tools/microsoft-semantic-kernel/alternatives) and [awesome-ai-apps alternatives](/tools/rohitg00-awesome-ai-apps/alternatives) ([semantic-kernel markdown twin](/tools/microsoft-semantic-kernel/alternatives.md), [awesome-ai-apps markdown twin](/tools/rohitg00-awesome-ai-apps/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/microsoft-semantic-kernel-vs-rohitg00-awesome-ai-apps.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, semantic-kernel or awesome-ai-apps? semantic-kernel: Very active. awesome-ai-apps: 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 semantic-kernel and awesome-ai-apps? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [semantic-kernel trust report](/tools/microsoft-semantic-kernel/trust); [awesome-ai-apps trust report](/tools/rohitg00-awesome-ai-apps/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=microsoft-semantic-kernel`](/api/graphcanon/graph?tool=microsoft-semantic-kernel) - 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/_