Skip to content
View palamim's full-sized avatar

Block or report palamim

Report abuse

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

Report abuse
palamim/README.md

Hi, I'm Leo (Palamim)

Independent AI researcher & builder. I measure what agent systems do, and build from what I find.

Best way to know what I'm working on: (1) read my work page; (2) read my blog.

Find me: X • leopalamim@gmail.com

Pinned Loading

  1. starboard starboard Public

    A terminal that's always beside your Dock — not a Quake-style hotkey overlay, a permanent fixture

    Swift 376 14

  2. port port Public

    Read-only macOS panel showing live Claude Code agent session state, glued to the Dock's bottom-left corner

    Swift 1

  3. usagent usagent Public

    macOS menu bar app showing Claude subscription usage (5-hour + weekly limits) at a glance

    Swift

  4. swe-chat-audit swe-chat-audit Public

    An independent audit of the reliability of the session_success metric published in the SWE-chat dataset (Baumann et al., 2026).

    Jupyter Notebook

  5. magent-lab magent-lab Public

    An offline evaluation and regression-testing suite for LLM-as-judge systems. Versioned criteria and prompts, replicate runs, agreement measured against human labels, statistics implemented from scr…

    TypeScript

  6. magent magent Public

    A planner/executor architecture with its own tool-calling loop, session orchestration, git integration, and a UI built for reviewing agent output before it ships.

    TypeScript