AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.

Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

Multi-Agent Harness for Production AI

Let Your AI Play Detroit：Become Human

Research and scraping agent skeleton: tool loop, loadable skills, fallback chains. No data included, configured via .env.

Opinionated AI coding agent and dev environment automation for macOS

Self-hosted agent OS with skills, workflows, MCP, and second brain storage.

Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.

Governance standard and reference toolset for LLM-maintained knowledge corpora

Local-first game design OS for AI agents: turn sessions into evidence, experiments, reviewable decisions, and durable project memory—Human Gates and rollback.

Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions

Adam Framework for OpenClaw — 5-layer persistent memory and identity architecture for AI agents. Production-validated over 353+ sessions. First documented case of emergent values in persistent AI, quantum-verified on IBM hardware.

AtlasAgent - an auditable AI agent control plane: evidence-backed memory, governed tool runtime, checkpoint DAG recovery, and a 55-chapter engineering tutorial. FastAPI / Next.js PWA / Textual TUI