Skip to content
View davidkimai's full-sized avatar
💭
optimizing my reward function
💭
optimizing my reward function

Block or report davidkimai

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
Showing results

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

Shell 4,190 317 Updated Apr 28, 2026

A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.

TypeScript 10,218 861 Updated Apr 22, 2026
Python 4 1 Updated Apr 26, 2026

The agent that grows with you

Python 125,386 18,714 Updated Apr 30, 2026

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

100,555 9,838 Updated Apr 20, 2026

Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw

TypeScript 4,487 371 Updated Apr 29, 2026
Swift 5,177 957 Updated Apr 28, 2026

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Python 11,817 1,366 Updated Apr 23, 2026

Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps

HTML 7,781 529 Updated Apr 27, 2026

Repository with text of DMCA takedown notices as received. GitHub does not endorse or adopt any assertion contained in the following notices. Users identified in the notices are presumed innocent u…

DIGITAL Command Language 6,248 1,373 Updated Apr 28, 2026

Research on Coding Agents

11,761 19,742 Updated Apr 1, 2026

From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration with MCP and live tracing. Three runtime dependencies.

TypeScript 5,977 2,326 Updated Apr 29, 2026

Your favorite Terminal Coding Agent, now in Rust

Rust 9,357 7,796 Updated Apr 27, 2026

The original nirholas/claude-code before DMCA and take down. Once everything is cleared, it will return. Working with Anthropic and Github to get everything back.

6,327 4 Updated Apr 16, 2026

OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

TypeScript 26,929 2,189 Updated Apr 30, 2026

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Rust 189,273 109,517 Updated Apr 30, 2026

Autonomous experiment loop extension for pi

TypeScript 6,296 360 Updated Apr 29, 2026

Typecript version of https://github.com/openai/symphony

TypeScript 486 31 Updated Mar 13, 2026

Slimmed, cleaned and fine-tuned oh-my-opencode fork, consumes much less tokens

TypeScript 3,638 255 Updated Apr 29, 2026

A CLI for Twitter/X — feed, bookmarks, and user timeline in terminal

Python 2,338 205 Updated Apr 29, 2026

A research tool for visually exploring Bureau of Labor Statistics Occupational Outlook Handbook data. This is not a report, a paper, or a serious economic publication — it is a development tool for…

HTML 1,570 321 Updated Mar 16, 2026

AI agents running research on single-GPU nanochat training automatically

Python 77,927 11,364 Updated Mar 26, 2026

Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.

Python 523 60 Updated Apr 26, 2026

An implementation of StrongDM's Attractor using pi.dev

TypeScript 17 4 Updated Feb 12, 2026

nlspec of StrongDM's Attractor, a non-interactive Coding Agent sufficient for use in a Software Factory

1,125 175 Updated Mar 17, 2026

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Elixir 19,376 1,618 Updated Apr 27, 2026

An AI-powered agentic red team framework that automates offensive security operations, from reconnaissance to exploitation to post-exploitation, with zero human intervention.

Python 1,824 385 Updated Apr 29, 2026

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Go 16,130 2,188 Updated Apr 28, 2026

Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities bef…

TypeScript 40,835 4,583 Updated Apr 28, 2026
Next