Intelligence that compounds. Every single day.

The workflow harness for Codex: typed gates, validated evidence, controlled transitions, repair paths, and inspectable logs for any workflow.

The agent harness you steer — structured context, automatic staleness gates, and block-by-block review, all bound to your code. Local-first, MCP-native, open source.

"Local LLM agent framework in Rust — native tool-role support, tmux session persistence, two-tier summarization, and ShareGPT logging. Works with any OpenAI-compatible backend."

Give any repo a canonical AI control plane. One prompt, any AI — Codex, Claude, Copilot, Cursor.

A compact, schema-first standard for the boundary between cognition and execution.

The open source runtime enforcement for AI agents.

A cognition-aware context and harness orchestration framework that combines Graph DBs, Vector DBs, and LLMs to build structured, memory-consistent, and scalable AI systems.

Open standard for responsible human–AI co‑working (six pillars: Economic Accountability, Social Fairness, Psychological Safety, IP & Cognition Ownership, Ecological Sustainability, Meaningful & Responsible Use).

A full fledged kit to yield 80% better results and cost aware vibe code development. Make the best usage of Claude Code AND Codex, inspired by the heavily used antigravity-kit by vudovn, feel free to experiment, raise issues and contribute.

Demo to showcase Temporal as the Durable OS layer for Agentic AI underneath an autonomous OpenAI-Agents-SDK trading agent.

Rest Assured skill pack for designing, implementing, documenting, and reporting API tests in Java and CI workflows.

End-to-end Playwright skill pack for planning, authoring, debugging, documenting, and operationalizing test automation.

Plans, executes, and analyzes safe performance testing for APIs, web apps, services, and distributed systems.

Test app to simultaneously build frontend harness

Generates epics, backlog-ready user stories, and importable story packs from requirements, discovery notes, or codebases.

Transforms requirements and business rules into structured software test artifacts using the right black-box design technique.

Generates realistic synthetic datasets for tests and demos with seeded, locale-aware, and distribution-shaped data.

Plans and runs responsive frontend testing across devices and screen sizes, with normalized reporting outputs.

tool that runs every check in the right sequence, pulls in the latest outputs automatically, and guarantees each release is consistent, reliable, and locked in.