Unverified50% confidenceFactExact time
Agenthof splits the system into two completely independent programs: agenthof is the governance engine, responsible for apply, run, audit, and investigate, never embedding the Agent and never deciding how the Agent thinks; the Agent is a separate program (a small LangChain Agent in the repository), agenthof calls it over a socket and drives it with the model door, tool door, execution door, and spawn door.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedIn Agenthof's demonstration, a real model is given the Agent's actual capabilities as tools and decides round by round what to call; when the Agent oversteps, what stops it is the door, not a script; model-driven operation does not require adding new door types.76% similarUnverifiedAgenthof is an open-source governance plane licensed under Apache-2.0, whose core claim is that the Agent is never trusted, but every request must pass through a door, and the door authorizes, injects credentials, and writes the ledger.75% similarUnverifiedOpenCode adopts a two-tier architecture that divides agents into two categories: Primary Agent and Subagent.68% similarUnverifiedThe independent inspection layer outside the Agent is similar to defense in depth and policy enforcement points in security engineering; its principle is to insert an independent policy engine between the Agent and external systems, and all high-risk operations must pass validation before they can be executed.68% similarUnverifiedAgentSky 的差异化在于其「运行框架无关」的中立定位，不绑定特定运行时而提供统一管理平面67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1038800API
curl https://kongchang.com/api/v1/knowledge/claims/1038800MCP
get_claim(id=1038800)