Ajan Pazaryeri

Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch

[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

A Massively Parallel Large Scale Self-Play Framework

A comprehensive set of LLM benchmark scores and provider prices. (deprecated, read more in README)

Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.

Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

(JAIR'2022) A mini-scale reproduction code of the AlphaStar program. Note: the original AlphaStar is the AI proposed by DeepMind to play StarCraft II. JAIR = Journal of Artificial Intelligence Research.

terminally online

[Successor: Hive — https://hivehq.dev] Original neutral orchestration layer for Claude Code, Codex CLI, Gemini CLI, OpenCode, Qwen Code. New work continues in Hive.

AEO Automation Framework for Claude Code One-click, beginner friendly automation for GitHub. Includes a dedicated fleet of AEO sub-agents handling planning, execution, reports, actionable items, and executive summaries. Trigger work instantly with AEO slash-commands. Fully integrated as a Claude Code Skill and usable across Claude AI App

Use agent to learn agent - A skeleton course on how to design, build, and operate production AI agents

Build organizations of OpenClaw agents that coordinate work across Codex, Claude Code, Cursor, OpenCode, and more 🐐 🐐 🐐

CAIPE: Community AI Platform Engineering Multi-Agent Systems

Repo for AI Agents The Definitive Guide

Open-source autonomous AI agent — runs on Claude-web, Gemini-web, Kimi-web, Deepseek-web and more for free and Every paid model via liteLLM. No API key required.

Autonomous AI pentesting engine performing continuous offensive security across web, cloud, AD and Kubernetes. Uses agentic reasoning, real exploit execution and attack path analysis to deliver proof-based vulnerabilities.

First Principles Framework (FPF): Pattern language and core specification for admissible action in problematic engineering, research, and mixed human/AI work.

MineStudio: A Streamlined Package for Minecraft AI Agent Development

potato: the portable annotation tool

A CLAUDE.md Generator and Maintenance tool for for Claude Code to create high-quality CLAUDE.md instruction files — aligned with Anthropic’s best practices for Claude Code.

AI agent tooling for data engineering workflows.

Flink Agents is an Agentic AI framework based on Apache Flink

Odyssey: Empowering Minecraft Agents with Open-World Skills

One task, one agent, delivered. The open-source platform for task-driven autonomous AI agents.OpenCow assigns an autonomous AI agent to every task — features, campaigns, reports, audits — and delivers them in parallel. Full context. Full control. Every department. 🐄