#harness

No repository description published.

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.

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

The agent harness: sandbox any agent, verify each step by replaying it against real state, and keep a deterministic trace.

Telegram runtime adapter for Pi

Installable AI governance harness for Codex, Cursor, Claude, Gemini, Copilot, Engram, and Graphify.

A typed maintenance surface for the Claude Code harness — the Rust of agentic harnesses: declare a contract, gate on conformance.

Claude Code plugin that turns LLM coding into a loop you control — plan first, build in small steps, pause for your approval before each commit.

Collaborate with your Agents in the bazaar across compute nodes, through any interface, with any harness runtime.

Production-grade Harness Engineering Framework for multi-developer AI coding agents — guardrails, state persistence, direction alignment, and self-correction across 6 IDEs. Zero dependencies.

A tiny testable, Go-native agent runtime for teams that want control, conformance, and no framework lock-ins.

Stop degrading your model's reasoning. A minimal, zero-config AI coding agent. Enforced ephemeral subagents keep context pure. From tiny local models up to Sol, Fable and Kimi K3.

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

Make AI actually work for you - A personal agent that writes its own tools and repairs itself.

天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层和信息素（Stigmergy）自衰减记忆构建，让 AI 成为有独立判断与认知防护的“开发伙伴”。

Harness multi-agente portable: instala la config JorgeX (agentes, skills, hooks, Engram, MCPs) en Claude Code, Codex CLI y OpenCode

Project VoidRift: Local-first Agentic Development Framework

klyd: the harness that stops terminal coding agents from silently drifting your architecture. Extracts, stores, and enforces design decisions across sessions.

No repository description published.

Autonomous development pipeline for Cursor & Claude Code. Type `aa:` and a persistent SQLite knowledge graph auto-records patterns, decisions and verified contracts every cycle. 54 MCP tools, AST impact analysis, preservation gates & audit mode.

Portable agentic development workbench for evidence-backed, resumable AI-assisted software workflows.

Python-side witness stack for the official DeepSeek Harness (Node). Five `dsh doctor --node` probes each report something the Node runtime will not. `pip install deepseek-harness-cli` first

Composable AI agent teams defined in YAML. Roles, skills, subagents & collaboration — no code required.

P2P multi agent orchestration harness, universal automation system and IDE

A private reasoner for your terminal. Direct conversation or grounded multi-agent research, GPU-native and fully local. No API keys, no inference servers.