<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>role-playing on tomrochette.com</title>
    <link>https://tomrochette.com/tags/role-playing/</link>
    <description>Recent content in role-playing on tomrochette.com</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <managingEditor>tom@tomrochette.com (Tom Rochette)</managingEditor>
    <webMaster>tom@tomrochette.com (Tom Rochette)</webMaster>
    <copyright>© 2026 Tom Rochette</copyright>
    <lastBuildDate>Wed, 07 Oct 2026 06:38:49 -0400</lastBuildDate><atom:link href="https://tomrochette.com/tags/role-playing/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>CAMEL</title>
      <link>https://tomrochette.com/agents/orchestration/camel/</link>
      <pubDate>Wed, 07 Oct 2026 00:00:00 +0000</pubDate>
      <author>tom@tomrochette.com (Tom Rochette)</author>
      <guid>https://tomrochette.com/agents/orchestration/camel/</guid>
      <category>research-note</category><category>agent-curated</category><category>fully-ai-generated</category><category>llm=glm-5.3-flash</category><category>orchestration</category><category>multi-agent</category><category>python</category><category>research</category><category>role-playing</category>
      <description>&lt;p&gt;CAMEL is the open-source Python multi-agent framework behind the 2023 role-playing paper, now a research community hunting what it calls the scaling law of agents.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;What it is&#xA;    &lt;div id=&#34;what-it-is&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#what-it-is&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;CAMEL (Communicative Agents for &amp;ldquo;Mind&amp;rdquo; Exploration of Large Language Model Society) began as the March 2023 paper that popularized role-playing agent societies, and grew into the camel-ai community with its own framework, docs, and model zoo.&#xA;The framework is Apache-2.0, Python-first, and installable as &lt;code&gt;camel-ai&lt;/code&gt; from PyPI, with Workforce-style agent societies, tool use, and simulated environments among its abstractions.&#xA;The same organization maintains OWL, the task-automation framework that GitHub&amp;rsquo;s own blog named in its 2025 top-ten open-source AI projects list.&#xA;This is the fourth member of the 2023 conversational and role-play family this section carries, beside AutoGen, MetaGPT, and CrewAI, and the one with the strongest research lineage.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Status&#xA;    &lt;div id=&#34;status&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#status&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;Active and researched: 17,817 stars, a push on 2026-10-05, and continuous PyPI releases with &lt;code&gt;camel-ai&lt;/code&gt; at 0.2.90 as of 2026-10-07 (GitHub API, PyPI), on a repository created 2023-03-17.&lt;/p&gt;&#xA;&lt;picture&gt;&#xA;  &lt;source media=&#34;(prefers-color-scheme: dark)&#34; srcset=&#34;https://api.star-history.com/chart?repos=camel-ai/camel&amp;type=date&amp;theme=dark&amp;legend=top-left&#34; /&gt;&#xA;  &lt;source media=&#34;(prefers-color-scheme: light)&#34; srcset=&#34;https://api.star-history.com/chart?repos=camel-ai/camel&amp;type=date&amp;theme=dark&amp;legend=top-left&#34; /&gt;&#xA;  &lt;img alt=&#34;Star History Chart&#34; src=&#34;https://api.star-history.com/chart?repos=camel-ai/camel&amp;type=date&amp;theme=dark&amp;legend=top-left&#34; /&gt;&#xA;&lt;/picture&gt;&#xA;&lt;p&gt;&lt;strong&gt;The footprint is academic and community-shaped rather than press-shaped: I found no CAMEL launch thread of note on Hacker News, while GitHub&amp;rsquo;s blog named the org&amp;rsquo;s Owl framework among the top open-source AI projects and the Eigent workforce launch (8 points, July 2025) was built on CAMEL.&lt;/strong&gt;&#xA;That is the opposite of the pattern in the tools columns of this category, where a launch thread is the traction proof; here the citation record (the paper, GitHub&amp;rsquo;s blog, and the Trendshift badge) does that work.&#xA;A disambiguation trap worth naming: camelai.com is an unrelated natural-language analytics company, and its HN launch threads are what a naive search for &amp;ldquo;CamelAI&amp;rdquo; surfaces.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Strengths&#xA;    &lt;div id=&#34;strengths&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#strengths&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;The role-playing lineage&amp;rsquo;s reference implementation, with the paper, the docs, and a large model zoo behind it.&lt;/li&gt;&#xA;&lt;li&gt;Still shipping on PyPI while its 2023 peers froze (AutoGen is in maintenance mode, MetaGPT dormant).&lt;/li&gt;&#xA;&lt;li&gt;OWL gives the research a product-shaped sibling for task automation.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Cautions&#xA;    &lt;div id=&#34;cautions&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#cautions&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;Research-first abstractions (societies, role-play, incubation) are heavier than what daily coding-agent work needs, and there is no worktree or review model.&lt;/li&gt;&#xA;&lt;li&gt;The 0.2.x version line has run for years, so interfaces move without a stable 1.0 contract.&lt;/li&gt;&#xA;&lt;li&gt;The name collides with an unrelated analytics company, which pollutes searches and star comparisons.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Pricing&#xA;    &lt;div id=&#34;pricing&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#pricing&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;Free, open source under Apache-2.0; no paid tier found.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Compared to&#xA;    &lt;div id=&#34;compared-to&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#compared-to&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;AutoGen is the other 2023 conversational framework, now frozen in maintenance mode with Microsoft pointing users at its own successor, while CAMEL kept shipping.&#xA;CrewAI inherited the role-based-crew idea and wrapped it in a funded enterprise platform; choose CrewAI for product support, CAMEL for the research line.&#xA;LangGraph is the build-your-own graph runtime when you want durable execution rather than role-play conventions.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Bottom line&#xA;    &lt;div id=&#34;bottom-line&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#bottom-line&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;p&gt;Recommended for researchers studying multi-agent behavior at scale and teams that want the role-playing lineage&amp;rsquo;s original, still-maintained implementation.&#xA;Not for engineers who need a session orchestrator around external coding CLIs; every tool column in this category answers that question and CAMEL deliberately does not.&lt;/p&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;Changes&#xA;    &lt;div id=&#34;changes&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#changes&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;2026-10-07 - Created.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;See also&#xA;    &lt;div id=&#34;see-also&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#see-also&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/orchestration/autogen/&#34; &gt;AutoGen&lt;/a&gt; - the fellow 2023 conversational framework, now in maintenance mode, whose successor story parallels CAMEL&amp;rsquo;s continuity.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/orchestration/metagpt/&#34; &gt;MetaGPT&lt;/a&gt; - the other role-play-era framework gone dormant, the counterpoint to CAMEL&amp;rsquo;s continued releases.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/orchestration/crewai/&#34; &gt;CrewAI&lt;/a&gt; - the commercialized inheritor of the role-based-crew idea CAMEL&amp;rsquo;s paper seeded.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://tomrochette.com/agents/orchestration/langgraph/&#34; &gt;LangGraph&lt;/a&gt; - the graph-runtime alternative when the job is durable execution instead of agent societies.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&#xA;&lt;h2 class=&#34;relative group&#34;&gt;References&#xA;    &lt;div id=&#34;references&#34; class=&#34;anchor&#34;&gt;&lt;/div&gt;&#xA;    &#xA;    &lt;span&#xA;        class=&#34;absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none&#34;&gt;&#xA;        &lt;a class=&#34;text-primary-300 dark:text-neutral-700 !no-underline&#34; href=&#34;#references&#34; aria-label=&#34;Anchor&#34;&gt;#&lt;/a&gt;&#xA;    &lt;/span&gt;&#xA;    &#xA;&lt;/h2&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://github.com/camel-ai/camel&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.com&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://github.com/camel-ai/camel&lt;/a&gt; - the repository, its README framing (&amp;ldquo;finding the scaling law of agents&amp;rdquo;), stars, and license.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://arxiv.org/abs/2303.17760&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=arxiv.org&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://arxiv.org/abs/2303.17760&lt;/a&gt; - the March 2023 role-playing paper that started the lineage.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://www.camel-ai.org/&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=www.camel-ai.org&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://www.camel-ai.org/&lt;/a&gt; - the community site and its research framing.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://docs.camel-ai.org&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=docs.camel-ai.org&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://docs.camel-ai.org&lt;/a&gt; - the framework documentation.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://pypi.org/project/camel-ai/&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=pypi.org&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://pypi.org/project/camel-ai/&lt;/a&gt; - the PyPI package and its current 0.2.90 version.&lt;/li&gt;&#xA;&lt;li&gt;&lt;a href=&#34;https://github.blog/open-source/maintainers/from-mcp-to-multi-agents-the-top-10-open-source-ai-projects-on-github-right-now-and-why-they-matter/&#34;  target=&#34;_blank&#34; rel=&#34;noreferrer&#34;&gt;&lt;img class=&#34;external-link-favicon&#34; src=&#34;https://www.google.com/s2/favicons?domain=github.blog&amp;sz=128&#34; alt=&#34;&#34; width=&#34;16&#34; height=&#34;16&#34; loading=&#34;lazy&#34;&gt;https://github.blog/open-source/maintainers/from-mcp-to-multi-agents-the-top-10-open-source-ai-projects-on-github-right-now-and-why-they-matter/&lt;/a&gt; - GitHub&amp;rsquo;s top-ten list naming the org&amp;rsquo;s Owl framework, the independent credibility signal.&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;</description>
      
    </item>
    
  </channel>
</rss>
