Comet: agent skill harness for turning ideas into evaluated workflows
-
Updated
Aug 20, 2026 - JavaScript
Comet: agent skill harness for turning ideas into evaluated workflows
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes.
Terminal-first AI workspace with coding agents, workflows and built-in web UI.
The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.
Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.
Starter kit for OpenCode agent orchestration with product-development workflows, Open Design integration, Superpowers, Docker, and docs.
Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven, evidence-gated, parallel feature voyages.
A human-governed AI coding workflow that distills ephemeral session context into persistent project memory—making work traceable, reviewable, and resumable.
Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+ best practices. Bootstrap with one command.
天工开物 — 朝廷框架Harness Engineering。三省六部制CLI版。
Agentic Testing Harness
Uncensor Qwen 3.8 27B with a pre-baked system pack for Ollama, plus GGUF download links.
Open-source, self-hosted AI-assisted operations for Kubernetes and Linux. Start here for source, architecture, deployment, and contributions.
Run Claude Code like a specialist software team: planning, implementation, QA, fix/retest loops, and durable .harness state for long-running project delivery.
Scaffold a 0-1 product harness for AI-assisted research, PRD, planning, architecture, build, test, and feedback loops
Make any project AI-agent-ready in one command. Adaptive tech stack detection (7 languages × 14 frameworks × 61 components), auto-generates AGENTS.md, docs skeleton, CI/CD, and testing infrastructure. 一句话让任何项目具备 AI 开发能力。
Local Codex MCP harness: contracts, persistent RAG memory, raw traces, verification records, governance policy and PASS/FLAG/BLOCK audits, observability reports, harness profiles, eval runs, Meta-Harness-lite promotion records, natural-language harness specs, MCP resources/prompts, multi-client installer, and completion gates.
Runtime-agnostic AI R&D control plane for observable, recoverable, and governable delivery.
Harness layer for Claude Code & Codex: plan-first development, independent review, durable long-running orchestration, and knowledge capture — ten composable plugins.
Add a description, image, and links to the harness-engineering topic page so that developers can more easily learn about it.
To associate your repository with the harness-engineering topic, visit your repo's landing page and select "manage topics."