Plugins

LLM-überwachtes persistentes Gedächtnis für KI-Agenten — graphbasierter Abruf, sitzungsübergreifendes Wissen, einzelne Binärdatei. Funktioniert mit DeepSeek Harness, Claude Code, OpenClaw und jeder Agent-Runtime.

Tiefe Mnemon-Integration: lokales dreistufiges Gedächtnis (Runtime Memory, abrufbare Documents, überwachte Memory Spaces).

Cross-session memory engine for DeepSeek Harness: SQLite store + human-editable Markdown mirror, autoDream consolidation, offline semantic search (local vector/rerank/clustering), entity-attribute-timeline, Sleep Mode, custom-model autoSummarize, and 7 memory tools.

Raumzeitlicher Gedächtnisgraph für mehrere Agenten mit sitzungsübergreifender Persistenz und wichtigkeitsgesteuertem Abruf.

Local-first persistent memory infrastructure for DeepSeek Harness: bounded hot-memory bootstrap, explainable cold recall (exact + Chinese BM25), lease-lock transactional writes, read-only governance, and trajectory review. Pure Python + Markdown, zero ext

Biomimetic memory system for DeepSeek Harness: plain-Markdown data layer, memory tools, frozen-snapshot injection, graded approval gating, structured audits, memory metabolism (dream), memory pins, semantic recall, /memory command, and cross-session retrieval.

Native StrataGate layered long-term memory for DeepSeek Harness

Automatic, local-first cross-session memory for DeepSeek Harness: layered Event/Element cards, evidence-gated recall, and expansion back to original turns and tool results.

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.