memory▌

Persistent, searchable memory bank for AI agents with automatic project documentation sync. \n \n Provides four core MCP tools: memory_search for querying by text/type/tags, memory_write for recording knowledge and decisions, memory_read for retrieving specific entries, and memory_stats for usage analytics \n Organizes memories by type (architecture, patterns, decisions) and supports custom tagging for flexible retrieval and organization \n Runs as an MCP server that syncs with your project work

Daily briefing of active focus areas, priorities, and recent knowledge changes for cross-session continuity. \n \n Load at the beginning of each session to understand current context and recent work across tools \n Surfaces active focus areas ranked by recent activity, flagged priorities, and unresolved contradictions or stale information \n Works via nmem wm read CLI command for both local and remote knowledge bases, with fallback to local file access \n Includes deep links to specific memories

Persistent memory systems for LLM conversations with tiered storage and intelligent retrieval. \n \n Implements three memory types: short-term (immediate context), long-term (historical facts), and entity-based (facts about specific entities) \n Provides memory retrieval and consolidation capabilities to surface relevant memories without overwhelming context windows \n Addresses critical concerns including unbounded memory growth, retrieval relevance, and strict user isolation to prevent cross-u

Configure persistent memory search for Moltbot/Clawdbot agents to retain context across sessions. \n \n Add memorySearch config block with provider (Voyage, OpenAI, or local), sources (memory files and/or sessions), and relevance thresholds \n Create a workspace structure with MEMORY.md for curated long-term facts and memory/logs/ for daily timestamped logs \n Supports three embedding providers; Voyage recommended but local option available without API keys \n Includes troubleshooting for common

Consolidates mature learnings from domain memory files into instruction files with quality-assured merging. \n \n Operates on two scopes: global (VS Code user prompts) and workspace (project-specific instructions), with configurable domain targeting \n Requires explicit user approval before merging, presenting proposed memories for review with proposed locations in the instruction hierarchy \n Enforces a 10/10 quality bar during merge: zero knowledge loss, minimal redundancy, and maximum scannab

Systematic memory management for agents through daily logging, session preservation, and knowledge extraction.

Comprehensive techniques for acquiring, analyzing, and extracting artifacts from memory dumps for incident response and malware analysis.

Multi-store memory with natural language triggers, knowledge graphs, decay-based forgetting, reflection consolidation, philosophical evolution, multi-agent support, and full audit trail.

Value: Feedback -- accumulated knowledge creates compound feedback loops across sessions. What you learn today should accelerate tomorrow's work.

Memory issues manifest as crashes after prolonged use. Core principle 90% of memory leaks follow 3 patterns (retain cycles, timer/observer leaks, collection growth). Diagnose systematically with Instruments, never guess.