walkinglabs/learn-harness-engineering
- Source
- GitHub
- First trending
- Category
- Agents
- GitHub stars
- 15,301
- Main language
- TypeScript
This page introduces an external open-source repository. It is not an HDATF product.
What it does
A project-based course on harness engineering, covering the environment, state management, verification and control that make AI coding agents work reliably. It also breaks down the harness designs of Pi, Claude Code, Codex and DeepSeek.
How it helps ATF
Its framework of instructions, tools, environment, state and feedback is worth comparing with how Harness keeps state and checks results with evidence. The Claude Code and Codex breakdowns could help, since Harness hands work to those executors.
License
MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.
More in this category
- chaitanyagiri/munder-difflin
A local desktop multi-agent harness that wraps terminal coding CLIs such as Claude Code, Codex and Gemini CLI. Each agent gets long-term memory and a mailbox, and a coordinating agent routes work between them on a 2D office view. - deepseek-ai/deepseek-harness
DeepSeek Harness (dsh) is an open-source agent harness from DeepSeek AI built on an everything-is-a-plugin architecture using Cordis. It runs a local web UI and is in developer preview with breaking changes expected. - truefoundry/trueforge
TrueForge is an open-source agent harness that handles model calls, MCP tools, skills, sandboxing, approvals, context management and session state. It offers a chat UI, an HTTP API with a TypeScript SDK, and an embeddable UI SDK. - awesome-dsh-plugin/awesome-dsh-plugin
A curated list of plugins for DeepSeek Harness, also called dsh. - yjh051108/dsh-routing-suite
A plugin suite for DSH: a runtime injector with hot reload, a task-aware reasoning-mode router, and a two-level task protocol with planned steps, check-ins, a red-team gate and final verification.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.