Plugins

Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

AGI long-term memory base: multi-agent spatiotemporal memory graph, self-evolving knowledge flywheel, self-cognition, and auditable trust guardrails.

One memory layer for every AI tool and agent: Context Bundle injection, prompt-time recall, MCP tools, and turn-end DSH thread capture.

A read_graph tool backed by a codebase knowledge graph (CONTAINS / EXPORTS / IMPORTS / IMPORTS_SYMBOL relations).

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

Dual knowledge-graph RAG for Markdown notes: prerequisite + similarity graphs (P/S-Agent traversal), paragraph chunking, n-gram/embedding hybrid search, and an explicit weight feedback loop — via MCP.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

A typed, inference-capable ontology (TBox + ABox) plugin for DeepSeek Harness — durable domain knowledge the agent can define, assert against, and query under schema constraints.