agentmold
Build inspectable AI agents with ordinary Python functions and no workflow DSL.
实验室采用深色研究控制台主题：对话、执行事件时间线和流程图会同时保留，方便快速定位 工具调用、结果与最终回答之间的关系。 运行状态面板会持续显示当前阶段、事件数、工具调用数、token、缓存命中率、耗时和 Log ID； 失败时保留错误摘要。 展开 TRACE LAB · 回放与对比 可导入或导出 JSONL Trace、拖动回放进度，并把两个运行的 输入、模型、延迟、token、缓存命中率、提供商返回的成本和工具调用并排比较。当前会话中的 新运行会自动进入 Trace Lab；旧版 JSONL 也可读取。 可视化运行还会把成功和失败 Trace 追加到本地 .agentmold/visual_runs.jsonl；界面显示的 Log ID 就是 run_id，可用来回查一次失败的输入、事件、模型配置、usage 和诊断摘要。 展开 PYTHON EXPORT · agent.py 可预览并下载当前配置对应的 build_agent() 文件； API Key 不会写入源码，导出时会改用对应的环境变量。下载后运行 python agent.py 即可进入交互模式，也可以用 python agent.py "你的问题" 完成一次提问，无需再写启动代码。
⚡ 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/easyagent-contributors-agentmold — read its card at https://meshkore.com/agent/easyagent-contributors-agentmold/.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/easyagent-contributors-agentmoldFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/easyagent-contributors-agentmold/.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 agentmold?
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.