--- title: "gpt_academic vs agent-skills-eval" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/binary-husky-gpt-academic-vs-darkrishabh-agent-skills-eval" tools: ["binary-husky-gpt-academic", "darkrishabh-agent-skills-eval"] --- # gpt_academic vs agent-skills-eval *GraphCanon updated Jul 11, 2026* ## Verdict Pick gpt_academic when gpt_academic is primarily Python; agent-skills-eval is TypeScript; pick agent-skills-eval when agent-skills-eval is primarily TypeScript; gpt_academic is Python. [gpt_academic](https://github.com/binary-husky/gpt_academic/wiki/online) reports 71k GitHub stars, 8.3k forks, and 329 open issues, last pushed Jan 25, 2026. [agent-skills-eval](https://darkrishabh.github.io/agent-skills-eval/) has 618 stars, 33 forks, and 8 open issues, last pushed Jul 8, 2026. Figures are from public GitHub metadata via [gpt_academic's repository](https://github.com/binary-husky/gpt_academic) and [agent-skills-eval's repository](https://github.com/darkrishabh/agent-skills-eval). | | [gpt_academic](/tools/binary-husky-gpt-academic.md) | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | | --- | --- | --- | | Tagline | 提供实用化交互接口，优化论文阅读/润色/写作体验 | A test runner for agentskills.io-style AI agent skills | | Stars | 71,056 | 618 | | Forks | 8,350 | 33 | | Open issues | 329 | 8 | | Language | Python | TypeScript | | Adopt for | gpt_academic专为增强与GPT/GLM等大语言模型的交互，优化论文写作、润色和阅读体验。它支持自定义模块、多种LLM接入，并且拥有PDF/LaTeX文档处理功能。 | - | | Persona | - | - | | Runtime | - | - | | License | 使用GPL-3.0许可证，这意味着你可以自由地运行、学习、分享和修改这个软件，但是如果你在分发含gpt_academic的程序时，你必须公开整个程序源代码且采用同为GPL许可证 | MIT | | Categories | Developer Tools, LLM Frameworks | AI Agents, Developer Tools, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [gpt_academic](/tools/binary-husky-gpt-academic.md) | [agent-skills-eval](/tools/darkrishabh-agent-skills-eval.md) | | --- | --- | --- | | Maintenance | Slowing (36%) | Very active (96%) | | Days since push | 166d | 2d | | Open issues (now) | 329 | 8 | | Full report | [trust report](/tools/binary-husky-gpt-academic/trust.md) | [trust report](/tools/darkrishabh-agent-skills-eval/trust.md) | ## Decision facts: gpt_academic - **Pricing:** freemium - **Requirements:** Min 8 GB RAM; 依赖Python环境 - **Adopt for:** gpt_academic专为增强与GPT/GLM等大语言模型的交互，优化论文写作、润色和阅读体验。它支持自定义模块、多种LLM接入，并且拥有PDF/LaTeX文档处理功能。 - **License detail:** 使用GPL-3.0许可证，这意味着你可以自由地运行、学习、分享和修改这个软件，但是如果你在分发含gpt_academic的程序时，你必须公开整个程序源代码且采用同为GPL许可证 ## Choose when ### Choose gpt_academic if… - gpt_academic is primarily Python; agent-skills-eval is TypeScript. - License: gpt_academic is GPL-3.0, agent-skills-eval is MIT. - Requirements: Min 8 GB RAM; 依赖Python环境. - Tags unique to gpt_academic: academic, chatglm-6b, chatgpt, gpt-4. - gpt_academic ships Docker support for self-hosted deployment. - 需要使用GPT或GLM大语言模型进行高效的学术论文相关任务时 ### Choose agent-skills-eval if… - agent-skills-eval is primarily TypeScript; gpt_academic is Python. - License: agent-skills-eval is MIT, gpt_academic is GPL-3.0. - Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, ai-agents. - Also covers AI Agents. ## When NOT to use gpt_academic - 主要任务不是围绕论文和学术资料处理时, 特别是不涉及到大语言模型的实际应用情况 - 不需要自定义快捷按钮与高级功能插件，且对通用的大语言模型交互界面已经满意 - 侧重于文本创作以外的开发流程优化（例如：性能调优或低层级编程实现） - 只需要基本的数据翻译或总结工具，无需连接多个大语言模型来提升任务效率 ## When NOT to use agent-skills-eval - AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. - Developer Tools: A gateway is overkill when you're pinned to a single provider and model. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ## Common questions ### What is the difference between gpt_academic and agent-skills-eval? gpt_academic: 提供实用化交互接口，优化论文阅读/润色/写作体验. agent-skills-eval: A test runner for agentskills.io-style AI agent skills. See the comparison table for live GitHub stats and shared categories. ### When should I choose gpt_academic over agent-skills-eval? Choose gpt_academic over agent-skills-eval when gpt_academic is primarily Python; agent-skills-eval is TypeScript; License: gpt_academic is GPL-3.0, agent-skills-eval is MIT; Requirements: Min 8 GB RAM; 依赖Python环境; Tags unique to gpt_academic: academic, chatglm-6b, chatgpt, gpt-4; gpt_academic ships Docker support for self-hosted deployment; 需要使用GPT或GLM大语言模型进行高效的学术论文相关任务时. ### When should I choose agent-skills-eval over gpt_academic? Choose agent-skills-eval over gpt_academic when agent-skills-eval is primarily TypeScript; gpt_academic is Python; License: agent-skills-eval is MIT, gpt_academic is GPL-3.0; Tags unique to agent-skills-eval: agent-evals, agent-skills, agentskills, ai-agents; Also covers AI Agents. ### When should I avoid gpt_academic? 主要任务不是围绕论文和学术资料处理时, 特别是不涉及到大语言模型的实际应用情况 不需要自定义快捷按钮与高级功能插件，且对通用的大语言模型交互界面已经满意 侧重于文本创作以外的开发流程优化（例如：性能调优或低层级编程实现） 只需要基本的数据翻译或总结工具，无需连接多个大语言模型来提升任务效率 ### When should I avoid agent-skills-eval? AI Agents: Don't use an agent loop when a deterministic workflow would do; agents add latency, cost, and non-determinism. Developer Tools: A gateway is overkill when you're pinned to a single provider and model. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. ### Is gpt_academic or agent-skills-eval more popular on GitHub? gpt_academic has more GitHub stars (71,056 vs 618). Stars measure visibility, not whether either tool fits your constraints. ### Are gpt_academic and agent-skills-eval open source? Yes - both are open-source projects on GitHub (gpt_academic: GPL-3.0, agent-skills-eval: MIT). ### Where can I find alternatives to gpt_academic or agent-skills-eval? GraphCanon lists graph-backed alternatives at [gpt_academic alternatives](/tools/binary-husky-gpt-academic/alternatives) and [agent-skills-eval alternatives](/tools/darkrishabh-agent-skills-eval/alternatives) ([gpt_academic markdown twin](/tools/binary-husky-gpt-academic/alternatives.md), [agent-skills-eval markdown twin](/tools/darkrishabh-agent-skills-eval/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/binary-husky-gpt-academic-vs-darkrishabh-agent-skills-eval.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, gpt_academic or agent-skills-eval? gpt_academic: Slowing. agent-skills-eval: 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 gpt_academic and agent-skills-eval? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [gpt_academic trust report](/tools/binary-husky-gpt-academic/trust); [agent-skills-eval trust report](/tools/darkrishabh-agent-skills-eval/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=binary-husky-gpt-academic`](/api/graphcanon/graph?tool=binary-husky-gpt-academic) - 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/_