CommonTrustProtocol
Theory repository for the Common Trust Protocol (Intelligentics v3.4). README states the repository holds the protocol's theoretical layer, while the DeepSeek Harness plugin implementation lives in the separate repository FuRongJun-1999/dsh-memory (npm: @furongjun1999/dsh-memory). It describes the Lingshu AEIS engineering layer: an MCP server for trustworthy agent memory and knowledge graphs, five-layer memory, condition-routed knowledge cards, an eight-step self-iteration loop, roleplay engine,
Installation
No reliable install command was detected. Check the project README for installation instructions.
Overview
Theory repository for the Common Trust Protocol (Intelligentics v3.4). README states the repository holds the protocol's theoretical layer, while the DeepSeek Harness plugin implementation lives in the separate repository FuRongJun-1999/dsh-memory (npm: @furongjun1999/dsh-memory). It describes the Lingshu AEIS engineering layer: an MCP server for trustworthy agent memory and knowledge graphs, five-layer memory, condition-routed knowledge cards, an eight-step self-iteration loop, roleplay engine,
- README describes an MCP server (stdio JSON-RPC) started via aeis-mcp, exposing 77 tools for memory, cognition, knowledge, validation and flywheel functions.
- README describes five-layer memory: anchor (unforgettable), structural (traceable), contextual (decaying), knowledge (high weight) and self (continuously update
- Knowledge cards carry condition-space declarations (KCCS): effective conditions, subgraph, not-applicable conditions and execution instructions.
- README states a 3,048-node knowledge graph (56 subject cards, 2,846 knowledge points) with 99.9% KCCS annotation coverage.
- White-box retrieval described as deterministic: translation table, annotation index, subject routing and card recursion, with DeepSeek LLM fallback and whitebox
- aeis/skills is described as a package of 688 Agent Skills across six domains, each skill adding not-applicable conditions alongside the standard fields.
- Roleplay engine with self anchor, trigger-conditioned values, cross-session memory, world-book import and noun substitution; REST endpoints for roles and chat.
- README lists installation from an aeis-0.5.0 wheel on GitHub Releases, editable install of aeis/ (Python 3.10+), and benchmark reproduction via tools/repro_gate