Provider-neutral control plane for long-horizon AI agent work across Codex, Claude Code, and other harnesses, with durable goals, typed todos, evidence, gates, quota, recovery, and verifiable hando…

An AI-powered process mining suite that converts natural language to process models and uses autonomous agents to analyze event logs and generate actionable process insights.

Official public repository for PM4Py (Process Mining for Python) — an open-source library for exploring, analyzing, and optimizing business processes with Python.

A self-improving agent harness for open models — brain, hands, and super legs for any LLM, frontier or local.

A curated reading list on harness engineering for recursive self-improvement of LLM agents (EN/ZH).

🥷 Engineering habits you already know, turned into skills Claude can run.

Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.

Train and deploy ML models in the cloud

Agent skills for useful HTML artifacts, wireframes, interactive prototypes, plans, and diagrams.

🔥Highlighting the top ML papers every week.

The best ChatGPT that $100 can buy.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

"FutureShow: Can AI Predict the Future? Live Real-World Forecasting"

Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against regressions.

Reference code for the Meta-Harness paper.

EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale.

Offical Implementation for "Recursive Multi-Agent Systems"

Academic Research Skills for Claude Code: research → write → review → revise → finalize

Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents with minimal human input.

New state-of-the-art bounds for open problems

LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐

The open-source agent-serving project

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

The agent that grows with you

"Vibe-Trading: Your Personal Trading Agent"

🎥 Make videos programmatically with React

Garry's Opinionated OpenClaw/Hermes Agent Brain

Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitasking, organization, and programmability.