#harness

Installs, reselects, restores and removes a complete Claude Code harness configuration in a caller-named target directory.

Installs, reselects, restores and removes a complete Codex harness configuration in a caller-named target directory.

Installs, reselects, restores and removes a complete Grok Build harness configuration, and owns the program lifecycle.

A .NET version of test262 ECMAScript test harness

An open-source build system that compiles your specs and architecture into working code.

Moonshot kimi k3 terminal based coding agent & harness running on your own Cloudflare account.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

Installs, reselects, restores and removes a complete OpenCode harness configuration, and owns the program lifecycle.

Installs, reselects, restores and removes a complete Pi harness configuration, and owns the program lifecycle.

Framework-agnostic agent-harness doctor: deterministic checks for good agent-harness practices

A temporal context graph, a memory API, retrieval primitives, and a multiple-platform integration mesh — designed to be embedded into any host process.

An AI assistant runtime for coding and team workflows, with DingTalk AI Cards, sub-agents, memory, and tasks.

Test harness and Phalcon bootstrapping for PHPUnit and beyond - the part of Phalcon that catches the bugs.

TAP-inspired unit test library for Node, Deno, Bun, and browsers. ES modules, TypeScript, zero dependencies.

🩺 Doctor for your repo's AI harness — audit, merge & drift-guard scattered agent configs (AGENTS.md / CLAUDE.md / .cursorrules) into one source of truth. Real evals: 6/28 → 28/28 correct, −27% latency. Field-tested on react, vscode, n8n + 11 more. Claude Code · Codex · Cursor · Gemini

El repositorio no publica descripción.

Secure, Modular Postgres for Teams

An opinionated full-stack agent harness with native memories, long running tasks, and multi-agent relay

Kensa turns agent traces into evals that run in CI.

Multi-agent collaboration platform for persistent, proactive AI agents across rooms, workspaces, skills, and external services.

Lovable for your terminal: a frontend harness on top of Claude Code, Codex, and 6 other coding agents.

Git-native context engineering CLI and MCP server for AI coding agents. Keep specs, ADRs, rules, plans, and project knowledge in Git.

A tiny testable, self hosted, provider neutral agent runtime for teams that want control, conformance, and no framework lock-ins.

Model-agnostic agentic runtime for the terminal — any local model becomes a capable agent. The intelligence lives in the harness, not the weights.

🎸 A project-level orchestrator for AI coding agents — Go & Charm stack implementation of OpenAI's Symphony

One canonical source of truth for skills, agents, MCP servers, LLM endpoints, and global instructions across every LLM harness on your machine.

A simulated interaction and evaluation loop over oneharness: drive a harness through a multi-turn conversation and score the transcript.

Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

minimal agentic harnez

Harness-agnostic toolkit for AI coding agents: detect the harness (Claude, Codex, Cursor, Cline, Gemini, Aider...) and run a pure policy core. One Bun-native package.