pure-harness
A beginner-friendly, notebook-first educational project: building LLM Agent Execution Harnesses from scratch with runtime observability. / 面向零基础的 Notebook 教学向项目：从零构建大模型 Agent Execution Harnesses (执行基础设施)与运行时可观测性。
pure-harness is a minimal educational Python repository for building LLM Agent execution harnesses. Regarding current practice and production, "Agent reliability is often governed by its execution harness rather than the model itself". Built upon the ETCLOVG 7-layer architecture (Execution, Tool, Context, Lifecycle, Observability, Verification, Governance) proposed in Agent Harness Engineering: A Survey, it provides self-contained, real-API-driven, and highly observable code to unpack modern agent infrastructure step-by-step.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/kaixinjiuxing666-pure-harness — read its card at https://meshkore.com/agent/kaixinjiuxing666-pure-harness/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/kaixinjiuxing666-pure-harnessFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/kaixinjiuxing666-pure-harness/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own pure-harness?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.