Open-source orchestration for coding agents. Define your own workflows, reviewers and repair loops. zeroshot enforces the process you configure.

A self-hosted 2D AI workspace for AI Agents

The open-source design agent and harness, better than Claude Design on academic communication artifacts production. This DesignHarness can also be used with any coding harness you like ( Codex/Claude Code/Kimi Code/Pi/OpenCode etc..) and any agentic model you want.

Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementation of Meta-Harness (Lee et al. 2026).

A Rust-based agent orchestrator enabling a swarm of Claude Code instances building software.

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

The guide for AI meta harnesses

FH is a meta-harness for Claude Code: it helps you build harnesses and skills — the rules, gates and memory a project needs — and checks them before they ship.

Meta-harness optimization loop wired onto Islo sandboxes. POC: 0/5→5/5 in four proposer steps. Built on islo.dev.

Open-source meta-harness for Claude Code, OpenAI Codex, and Gemini CLI coding agents

Open-source search engine that automatically evolves your AI agent's prompts, tools, and harness logic through iterative evaluation — plug in Claude Code, Codex, Hermes, or any CLI agent.

Persistent, federated meta-harness for AI agents. Continue, delegate, fork and merge work across Claude Code, Codex, Cursor, Kimi, OpenClaw and more.

The meta-harness for AI software engineering — 15 specialist personas, 24 stack packs, Adaptive SDD, compounding memory, and an optional autonomous fleet for Claude Code, GitHub Copilot CLI, and Google Antigravity.

Project page for Meta-harness on Islo (POC). https://zozo123.github.io/meta-harness-on-islo-page/

A reasoning harness for human-AI collaboration. Preserves what's understood, not just what's said. Open-source skill for Claude Projects. Patent pending.

A modified Meta-Harness where agents propose, test, challenge, and adjudicate coding harnesses for iterative improvement.

Plug-and-play multi-agent orchestration framework. 7 personas, 13 sensors (v1.13.0), 24 invariants, gmh CLI, validated on mandai-v2 (Hermes Agent). 27 releases.

Spine AI/ML Edition (arch-ml) — доменный метахарнесс AI/ML-исследователя над кодовыми харнессами: спайн-инварианты, fitness-гейты, рубрики, handoff-контракт · Domain agent meta-harness for AI/ML researchers (RU/EN)

작업 해석·도메인팩·에이전트 바인딩·검증 계약을 정의하는 문서형 메타 하네스 | Documented meta-harness for task interpretation, domain packs, agents, and validation

Provider-neutral agent orchestration layer (meta-harness) for Claude Code and the Codex CLI: a principal classifies and delegates bounded work to contained workers and independent reviewers. Kernel-enforced read-only reviews, evidence-gated merges, consent-gated fallback, bounded plan review, leave-no-trace cleanup.