harness-execution-layer

Your Company Agentic Operating System

Approving is an open-source, self-hostable platform for turning coding agents into visual, reviewable, and recoverable delivery workflows. Agents run in real Docker sandboxes, exchange structured artifacts, and pause for human Approve at critical nodes.

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.

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

"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.

Harness-kk-god5.0

End-to-end engineering harness for Claude Code — go from planning to building to reviewing in one workflow. 8 agents with multiple modes. In-built GUI to visualise your PRDs and todos. Ship with AI confidently. MIT.

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.

The open source runtime enforcement for AI agents.

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.

A free VRAM calculator for AI models. Not just for LLMs: text generation, embeddings, vision, multimodal, image diffusion, video, audio, and tabular workloads, across inference, LoRA/QLoRA fine-tuning, and full training. Every calculation runs in the browser. Demo app to simultaneously build frontend harness.

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

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

Drop in any model. Get a harness. Offline-first CLI + TUI that detects model type, runs the right harness, serves HTTP, and scaffolds plugins — for tabular, embeddings, LLMs, vision, diffusion, computer use, and more.

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

Self-hosted governance plane for coding agents: sandboxed sessions on your own Kubernetes, metered budgets, policy checks, audit trail

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

This is the corresponding code for the O'Reilly book: Harness Engineering