deslop

The agent IDE that builds itself

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

Claude Code, Codex, Pi, OpenCode, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

My macOS environment: zsh, Git, Visual Studio Code, etc.

A high-performance, enterprise-grade Next.js 16 application for mission-focused non-profit organizations. Built for high impact teams.

My coding agent config

Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it.

An elegant, information-rich status, menu, and side bar for Pi Agent.

Kuu's Claude Code utils for myself

.

✨ Dotfiles for human agency

A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo'

Config files for OSX (master) and archlinux (archlinux)

中文网文写作工具包 · Chinese web-novel writing toolkit (23 skills) — a Claude Code plugin, also works in ChatGPT / DeepSeek / Gemini

—

Outline-Driven Development for Claude Code - 46 agents, 25+ skills, diagram-first methodology, AST-based editing, atomic commits.

Claude, Cursor, Codex skills and commands

Set of scripts/config/utils so I can have all my computers on the same page

🦀 Claude Code toolkit for self improving skills, performance and mcp-essentials

🛠️ Composable AI agent toolkit — skills, agents, loops, and MCP templates for Claude Code, Cursor, OpenCode, Copilot, Windsurf, and Pi

—

:octocat: + ~/. = ❤️. These are my dotfiles, feel free to hack them! 😄

Highly-opinionated setup for AI safety research with coding agents

tooling

Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.

A repo contains the different tutorials I write for my use and to share with others.

My ever evolving dotfiles

Pstack for Codex and Claude Code, with cross-provider routing and automatic failover. Devin, Cursor, Antigravity, OpenCode, and Grok subagents available. All using your own subscriptions.

Modular Claude Code configuration with rules, agents, skills, hooks, and commands for academic research workflows