9 tagged ai platform, measured the same way as everything else here.
Browse within: ai-development 8
Agent
Delegation through registerAgentTool is synchronous: the supervising agent's loop blocks on each worker, so four investigations cost four times one investigation and the supervisor sits idle while each runs.
Agent
A long-running agent has to run real commands — a build, a test suite, a linter whose output is the evidence for a finding. The two obvious shapes both fail: bashTool blocks the loop, hands the model a shell, and truncates its own output at 100 KB; a childprocess call with a command string is a shell injection with…
Agent
This document describes all configuration options for the Multi-Agent Networks feature in NeuroLink.
Agent
Agent "AGENTS" from fengzhizi715/OpenVitamin, covering agents.md — model agents governance, 1. 模块定位（module purpose）, 2. 设计边界（strict boundaries）, 2.1 model agent 必须做的事 ✅ and 2.2 model agent 严禁做的事 ❌.