OpenClaw memory plugin backed by memory-decay engine
Sulcus — thermodynamic memory + Apache AGE knowledge graph for OpenClaw agents. v6.0: Multi-signal recall (semantic + hot-context + entity-graph + profile), configurable guardrails (outputGuard + toolGuard), token budget enforcement, context rebuild post-
OpenClaw native memory plugin powered by NEXO Brain — Atkinson-Shiffrin cognitive memory, semantic RAG, trust scoring, and metacognitive guard.
OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, long-context chunking, and management CLI
Give your OpenClaw agent lasting memory: structured facts, semantic search, auto-capture & recall, decay, optional credential vault. Part of Hybrid Memory v3.
OpenClaw LanceDB-backed long-term memory plugin with auto-recall, auto-capture, and vector search.
Biologically-inspired memory system for AI agents. Decay by default, strength through use.
OpenClaw long-term memory plugin backed by Alibaba Zvec (dense vector ANN)
Multi-channel AI gateway with extensible messaging integrations
Agent memory - local-first knowledge infrastructure for AI agents
Workflow runtime for AI agents - deterministic pipelines with approval gates
OpenClaw adapter for Remnic memory with bundled @remnic/core runtime
<div align="center"> <img src="./docs/assets/libravdb-logo.svg" alt="LibraVDB" width="640"> </div>
On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.
Soul-aware OpenClaw fork — enhanced memory search and contained runtime
OpenClaw plugin adapter for connecting a DKG V10 node and chat bridge to an OpenClaw agent
Capability-style filesystem roots for Node.js apps that handle untrusted relative paths.
PLUR memory plugin for OpenClaw — persistent learning across sessions
Deprecated compatibility shim for Engram installs. Re-exports @remnic/plugin-openclaw and forwards engram-access to @remnic/core.
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
Four-layer local memory system plugin for OpenClaw — auto-captures, structures, and profiles conversational knowledge using local LLM + SQLite vector search (L0→L1→L2→L3 pipeline)
OpenClaw plugin for Cortex memory — Auto-Recall, Auto-Capture, and agent memory tools
HY Memory backend for OpenClaw — self-hosted intelligent agent memory with LLM-driven extraction, evolution chains, and multi-layer recall
Headless CLI client for the Agent Client Protocol (ACP) — talk to coding agents from the command line