--- title: "apps vs FastChat" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/hendrycks-apps-vs-lm-sys-fastchat" tools: ["hendrycks-apps", "lm-sys-fastchat"] --- # apps vs FastChat *GraphCanon updated Jul 11, 2026* ## Verdict Pick apps when license: apps is MIT, FastChat is Apache-2.0; pick FastChat when license: FastChat is Apache-2.0, apps is MIT. [apps](https://github.com/hendrycks/apps) reports 536 GitHub stars, 70 forks, and 4 open issues, last pushed Jun 19, 2024. [FastChat](https://github.com/lm-sys/FastChat) has 39k stars, 4.8k forks, and 1.0k open issues, last pushed May 1, 2026. Figures are from public GitHub metadata via [apps's repository](https://github.com/hendrycks/apps) and [FastChat's repository](https://github.com/lm-sys/FastChat). | | [apps](/tools/hendrycks-apps.md) | [FastChat](/tools/lm-sys-fastchat.md) | | --- | --- | --- | | Tagline | APPS: Automated Programming Progress Standard (NeurIPS 2021) | An open platform for training, serving, and evaluating large language models | | Stars | 536 | 39,490 | | Forks | 70 | 4,788 | | Open issues | 4 | 1,027 | | Language | Python | Python | | Adopt for | - | FastChat is a comprehensive open platform for managing large language models (LLMs) that includes capabilities for training, serving, evaluating, and comparing chatbot models via web UIs and RESTful APIs. It powers ChatB | | Persona | - | - | | Runtime | - | - | | License | MIT | Apache-2.0 | | Categories | Evaluation & Observability, Model Training, Vector Databases | Evaluation & Observability, Inference & Serving, LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [apps](/tools/hendrycks-apps.md) | [FastChat](/tools/lm-sys-fastchat.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Steady (60%) | | Days since push | 752d | 71d | | Open issues (now) | 4 | 1.0k | | Owner type | User | Organization | | Security scan | 77 low (77 low) | No lockfile | | Full report | [trust report](/tools/hendrycks-apps/trust.md) | [trust report](/tools/lm-sys-fastchat/trust.md) | ## Decision facts: FastChat - **Adopt for:** FastChat is a comprehensive open platform for managing large language models (LLMs) that includes capabilities for training, serving, evaluating, and comparing chatbot models via web UIs and RESTful APIs. It powers ChatB ## Choose when ### Choose apps if… - License: apps is MIT, FastChat is Apache-2.0. - Tags unique to apps: code-generation, program-synthesis, python. - Also covers Vector Databases. ### Choose FastChat if… - License: FastChat is Apache-2.0, apps is MIT. - Tags unique to FastChat: chatbots, distributed serving, evaluation system, large-language-models. - Also covers Inference & Serving, LLM Frameworks. - - You are looking to train and evaluate state-of-the-art models such as Vicuna or MT-Bench. ## When NOT to use apps - Last GitHub push was 753 days ago (dormant maintenance, Jun 19, 2024). Validate activity before betting a new project on apps. - Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. - 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. ## When NOT to use FastChat - - You require a proprietary or closed-source framework; FastChat is open-source under Apache-2.0 license and its use might be unsuitable for environments requiring proprietary solutions. - - Your chatbot evaluation needs do not align with the types of data used in FastChat's datasets (e.g., human votes, MT-Bench evaluations). - - You prefer a more user-friendly setup without the need to clone a repository and manually install dependencies; FastChat requires installation from source with additional steps for Rust and CMake on - + Mac. ## Common questions ### What is the difference between apps and FastChat? apps: APPS: Automated Programming Progress Standard (NeurIPS 2021). FastChat: An open platform for training, serving, and evaluating large language models. See the comparison table for live GitHub stats and shared categories. ### When should I choose apps over FastChat? Choose apps over FastChat when License: apps is MIT, FastChat is Apache-2.0; Tags unique to apps: code-generation, program-synthesis, python; Also covers Vector Databases. ### When should I choose FastChat over apps? Choose FastChat over apps when License: FastChat is Apache-2.0, apps is MIT; Tags unique to FastChat: chatbots, distributed serving, evaluation system, large-language-models; Also covers Inference & Serving, LLM Frameworks; - You are looking to train and evaluate state-of-the-art models such as Vicuna or MT-Bench. ### When should I avoid apps? Last GitHub push was 753 days ago (dormant maintenance, Jun 19, 2024). Validate activity before betting a new project on apps. Evaluation & Observability: Defer heavyweight eval infra only until you have real traffic - never skip it once users depend on answers. 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. ### When should I avoid FastChat? - You require a proprietary or closed-source framework; FastChat is open-source under Apache-2.0 license and its use might be unsuitable for environments requiring proprietary solutions. - Your chatbot evaluation needs do not align with the types of data used in FastChat's datasets (e.g., human votes, MT-Bench evaluations). - You prefer a more user-friendly setup without the need to clone a repository and manually install dependencies; FastChat requires installation from source with additional steps for Rust and CMake on + Mac. ### Is apps or FastChat more popular on GitHub? FastChat has more GitHub stars (39,490 vs 536). Stars measure visibility, not whether either tool fits your constraints. ### Are apps and FastChat open source? Yes - both are open-source projects on GitHub (apps: MIT, FastChat: Apache-2.0). ### Where can I find alternatives to apps or FastChat? GraphCanon lists graph-backed alternatives at [apps alternatives](/tools/hendrycks-apps/alternatives) and [FastChat alternatives](/tools/lm-sys-fastchat/alternatives) ([apps markdown twin](/tools/hendrycks-apps/alternatives.md), [FastChat markdown twin](/tools/lm-sys-fastchat/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/hendrycks-apps-vs-lm-sys-fastchat.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, apps or FastChat? apps: Dormant. FastChat: 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 apps and FastChat? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [apps trust report](/tools/hendrycks-apps/trust); [FastChat trust report](/tools/lm-sys-fastchat/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=hendrycks-apps`](/api/graphcanon/graph?tool=hendrycks-apps) - 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/_