Skip to content
View Caffa's full-sized avatar

Block or report Caffa

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Caffa/README.md

Hi there 👋

I build tools for my own workflows. I like Python, pretty visualizations, and "lazy" automations.

What I do: Build tools to reduce digital overwhelm. For writing, daily interstitial journalling, zettelkasten sense-making, article writing and agentic coding. How I do this: Make workflows more convenient (with shortcuts). Make better visual interfaces with cute blob character representations (because fun is important).

If it is easy and enjoyable to do, people will do it. If not, we won't.

I use Alfred, Keyboard Maestro, and Python to automate anything requiring multiple steps. If I can launch it with a keyword, I will. I love hacking solutions together to keep my setup fast and low-effort.

  • 🇸🇬 I'm currently living in my Obsidian vaults and exploring agentic coding in OpenCode.

alt text alt text alt text

  • 🔭 I'm currently reading: Tiny Experiments by Anne-Laure Le Cunff. A System for Writing by Bob Doto. The Pathless Path by Paul Miller.
  • 🌱 I'm currently learning: How to make AI agents easier to work with. (Openclaw is so hyped, and yet the ideas behind the agent harness are really interesting. Memory, search, preference saving and how to make your AI assistant smarter + less expensive to run)
  • 👯 I'm looking to collaborate on: Blob Office (Opencode Plugin), feedback and pull-requests please.
  • 💬 Talk to me about: Obsidian Zettelkasten systems, Roam book clubs (non-fiction) or Alfred workflows.

You should look at my favourite projects:

Tokscale Stats

Backstory: In 2025, I completed my PhD in Multi-Agent Reinforcement Learning (MARL) with a focus on how multi-agent teams (of AI agents) can learn to collaborate.

Substack | YouTube | Twitter

Pinned Loading

  1. kimaki kimaki Public

    Forked from remorses/kimaki

    Kimaki with parakeet for voice transcription instead of gemini

    TypeScript

  2. Session-Character-Visualizer Session-Character-Visualizer Public

    A pretty representation. Use animated blob characters to show the status of opencode sessions

    TypeScript 16 1

  3. Vault-Linker Vault-Linker Public

    Connect multiple obsidian vaults together with links and embeds that work across vaults

    TypeScript 7

  4. links-coloring links-coloring Public

    Colors the links differently to help differentiate the links and give them a consistent color scheme.

    TypeScript 1