--- title: "FastChat vs heretic" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/lm-sys-fastchat-vs-p-e-w-heretic" tools: ["lm-sys-fastchat", "p-e-w-heretic"] --- # FastChat vs heretic *GraphCanon updated Aug 16, 2026* ## Verdict Pick FastChat if 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; pick heretic if heretic is a Python-based tool that removes censorship from language models automatically. [FastChat](https://github.com/lm-sys/FastChat) reports 40k GitHub stars, 4.8k forks, and 1.0k open issues, last pushed May 1, 2026. [heretic](https://heretic-project.org) has 28k stars, 3.0k forks, and 74 open issues, last pushed Aug 14, 2026. Figures are from public GitHub metadata via [FastChat's repository](https://github.com/lm-sys/FastChat) and [heretic's repository](https://github.com/p-e-w/heretic). | | [FastChat](/tools/lm-sys-fastchat.md) | [heretic](/tools/p-e-w-heretic.md) | | --- | --- | --- | | Tagline | An open platform for training, serving, and evaluating large language models | Fully automatic censorship removal for language models | | Stars | 39,517 | 27,709 | | Forks | 4,788 | 2,997 | | Open issues | 1,038 | 74 | | 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 | Heretic is a Python-based tool that removes censorship from language models automatically. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | AGPL-3.0 | | Categories | Evaluation & Observability, Inference & Serving, LLM Frameworks, Model Training | Evaluation & Observability, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [FastChat](/tools/lm-sys-fastchat.md) | [heretic](/tools/p-e-w-heretic.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Very active (96%) | | Days since push | 98d | 2d | | Open issues (now) | 1.0k | 74 | | Stars delta | Unknown | +1.3k (30d) | | Open issues delta | Unknown | +2 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/lm-sys-fastchat/trust.md) | [trust report](/tools/p-e-w-heretic/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 ## Decision facts: heretic - **Adopt for:** Heretic is a Python-based tool that removes censorship from language models automatically. ## Choose when ### Choose FastChat if… - License: FastChat is Apache-2.0, heretic is AGPL-3.0. - Tags unique to FastChat: chatbots, distributed-serving, evaluation system, large language models. - Also covers Inference & Serving, Model Training. - - You are looking to train and evaluate state-of-the-art models such as Vicuna or MT-Bench. ### Choose heretic if… - License: heretic is AGPL-3.0, FastChat is Apache-2.0. - Tags unique to heretic: abliteration, llm, transformer. - Use Heretic if your work involves uncovering full capabilities of censored or restricted language models. Heretic excels in tasks requiring the removal of such restrictions. ## 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. ## When NOT to use heretic - Avoid Heretic if operating within jurisdictions where removing censorship from language models is illegal or against organizational policies. This could result in regulatory violations. - If your project does not benefit from uncensored content produced by language models (e.g., compliance-driven applications that require filtering mechanisms), using Heretic might be unnecessary. ## Common questions ### What is the difference between FastChat and heretic? FastChat: An open platform for training, serving, and evaluating large language models. heretic: Fully automatic censorship removal for language models. See the comparison table for live GitHub stats and shared categories. ### When should I choose FastChat over heretic? Choose FastChat over heretic when License: FastChat is Apache-2.0, heretic is AGPL-3.0; Tags unique to FastChat: chatbots, distributed-serving, evaluation system, large language models; Also covers Inference & Serving, Model Training; - You are looking to train and evaluate state-of-the-art models such as Vicuna or MT-Bench. ### When should I choose heretic over FastChat? Choose heretic over FastChat when License: heretic is AGPL-3.0, FastChat is Apache-2.0; Tags unique to heretic: abliteration, llm, transformer; Use Heretic if your work involves uncovering full capabilities of censored or restricted language models. Heretic excels in tasks requiring the removal of such restrictions. ### 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. ### When should I avoid heretic? Avoid Heretic if operating within jurisdictions where removing censorship from language models is illegal or against organizational policies. This could result in regulatory violations. If your project does not benefit from uncensored content produced by language models (e.g., compliance-driven applications that require filtering mechanisms), using Heretic might be unnecessary. ### Is FastChat or heretic more popular on GitHub? FastChat has more GitHub stars (39,517 vs 27,709). Stars measure visibility, not whether either tool fits your constraints. ### Are FastChat and heretic open source? Yes - both are open-source projects on GitHub (FastChat: Apache-2.0, heretic: AGPL-3.0). ### Where can I find alternatives to FastChat or heretic? GraphCanon lists graph-backed alternatives at [FastChat alternatives](/tools/lm-sys-fastchat/alternatives) and [heretic alternatives](/tools/p-e-w-heretic/alternatives) ([FastChat markdown twin](/tools/lm-sys-fastchat/alternatives.md), [heretic markdown twin](/tools/p-e-w-heretic/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/lm-sys-fastchat-vs-p-e-w-heretic.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, FastChat or heretic? FastChat: Slowing. heretic: 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 FastChat and heretic? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [FastChat trust report](/tools/lm-sys-fastchat/trust); [heretic trust report](/tools/p-e-w-heretic/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=lm-sys-fastchat`](/api/graphcanon/graph?tool=lm-sys-fastchat) - 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/_