Skip to content
View SufficientDaikon's full-sized avatar
💭
I love making software ❤️
💭
I love making software ❤️

Highlights

  • Pro

Block or report SufficientDaikon

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.

Content in all repositories owned by your account will be closed.
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
SufficientDaikon/README.md

Ahmed Taha

I build AI that builds software, agent systems that plan, write, debug, and ship production code. i was a victim of AI psychosis, so i have a ton of personal AI tools that i made to help me let the ai do work fully hands off my favorite is an mcp server i made so claude can send screen shots to gemini to ask for help with design (this was before opus had good vision)

i made a shitton of mcp servers and tools, most aren't on the hub cause i cant be asked publishing them, if you're interested HMU and i'll share them with you.

Opensource

Core-engine work on PowerShell, Microsoft's cross-platform shell (50k+ stars):

Some of what i'm Building

  • Archon a skills engine for AI agents: one skill library with complexity routing from trivial to expert, deployable to Claude Code, GitHub Copilot, and other agent platforms without rewriting a skill.
  • Axon an ML-first systems language in Rust. Tensor shapes verified at compile time, memory safety from ownership instead of a garbage collector. Lexer, parser, and borrow checker written from scratch.
  • Aether multi-agent orchestration across 28 subsystems: a three-tier Master/Manager/Worker hierarchy with context-aware routing and durable workflows, built on Bun and TypeScript.
  • dissector-agent reverse-engineers any codebase into human and Ai agent readable documents through 13 analysis phases, covering architecture, conventions, APIs, testing, and security.

Smaller, sharper things pr-to-course, which turns any pull request into an interactive course; daedalus-debugger, which interrogates its own runtime and writes up the report live in the full repo list.


tahaa755@gmail.com · LinkedIn

Pinned Loading

  1. archon archon Public

    The Virtuoso Engine for AI Agents. 83 skills, 10 agents, 5 cognitive synapses, enforced guardrails. Write once, deploy on 5 AI platforms. MIT licensed.

    Python 8

  2. Axon Axon Public

    ML/AI-first systems programming language — compile-time tensor shapes, ownership-based safety, native GPU execution

    Rust 1