dongsheng123132

Benxiang Protocol · One Source, Infinite Shadows: Preserve the original form, project on demand. A persistent object representation layer for AI—AI only submits semantic transactions, which are validated by a deterministic compiler before being committed. Every field can answer "why". ShadowBench-W benchmark results (Run #27, post-probe fix, n=6 each): W3 state accuracy 95.8% vs bare model 52.1% vs vector RAG.

Provides a task passport system for handoff across AI harnesses, enabling users to list, open, create, and checkpoint tasks with stable IDs and verified state.

MCP server for auditing DeepSeek Harness evidence. Enables inspection and verification of content-addressed audit manifests with fail-closed validation.

MCP server for verifying narrative consistency and querying story-state facts in DeepSeek Harness, exposing read-only ledger tools for canonical evidence and co

Enables verification of content-addressed settlement receipts for DSH Loader activation, injection closure, and tool schema settlement.

Lets users inspect and verify content-addressed schema migration evidence offline, checking idempotence, reversible rollback, required invariants, and explicit

Content-addressed DSH configuration origin and shadowing evidence