What you can do with Misaka Agent

3 use cases

• Run a research question across several branches

  Turn one humanities question into a reviewed research graph and a sourced research article.

  • Misaka Agent
  • Research
  • Intermediate
  View prompt

  Use the Luciole-Studio/Misaka-Agent repo to run /research on this question: <research question>. Expected output: a research article written into the project folder, with each citation tied to a file and page. Verify that you approved the plan before any Sister began work.

  Share Save

• Check each research claim against its source page

  Audit every finding in a MISAKA conclusion against the file, page and quotation it names.

  • Misaka Agent
  • Research
  • Intermediate
  View prompt

  In the Luciole-Studio/Misaka-Agent project folder <project folder>, open the card and conclusion Markdown files and check that each cited claim matches the file, page and quotation it names. Expected output: a list of citations that match and a list of those that do not. Verify that every finding includes a quotation from its source.

  Share Save

• Expose the unstated premises in a draft argument

  Use a red-team review to find what a conclusion leaves unsaid yet relies on.

  • Misaka Agent
  • Research
  • Intermediate
  View prompt

  Use the Luciole-Studio/Misaka-Agent repo to run /research on this draft argument: <draft argument>. Expected output: a red-team review and a divergence review listing unstated premises and gaps in the conclusion. Verify that each listed presupposition has a recorded response in the node's files.

  Share Save

How to use Misaka Agent

1. Check you have what it needs: uv, git, ripgrep, fd and poppler installed, or the prebuilt release archive for macOS, Linux or Windows; Access to a model provider: an API key, or a ChatGPT or GitHub Copilot subscription; A working folder under Documents, not the root directory.
2. Open Luciole-Studio/Misaka-Agent on GitHub and read the README and license.
3. Run uv tool install "misaka[providers] @ git+https://github.com/Luciole-Studio/Misaka-Agent.git".
4. Run mkdir ~/Documents/my-research and then cd ~/Documents/my-research.
5. Run misaka setup to sign in, choose a model and create your first two Sisters.
6. Run misaka, then type /research and answer the parameter prompts, or give them on one line such as /research --depth 2 --max-nodes 12 QUESTION.

These steps come from our top use case, Run a research question across several branches, which also has a copy-paste agent prompt.

Misaka Agent alternatives · Best AI repos for Research

About this repo

• Who it is forHumanities and social science researchers and students who need a sourced, revisable answer to a question that has several defensible readings.
• Why it is hot
• LanguagePython
• Sourcegithub.com/Luciole-Studio/Misaka-Agent · Back to Hot repos

Requirements

• uv, git, ripgrep, fd and poppler installed, or the prebuilt release archive for macOS, Linux or Windows
• Access to a model provider: an API key, or a ChatGPT or GitHub Copilot subscription
• A working folder under Documents, not the root directory

Related repos

• #5 this week Scientific Agent Skills A library of 177 Agent Skills that give AI agents documented, validated guidance for scientific packages, databases, and research workflows.
• Trended earlier Speaker Mem R1 SpeakerMem-R1 is a Python research repo with a speaker-centered memory package, benchmark runners, writer-training recipes, and evaluation outputs for multi-party dialogue.
• Trended earlier DSH Council A DSH Council plugin that asks several AI models to answer a question independently, review each other's answers anonymously, and produce one inspectable final recommendation inside DeepSeek Harness.