Tag: memory-management
Memem Memory System Status Monitor
Provides detailed status updates for the memem memory system, including memory count, projects, search database, and miner health, and can restart the miner if it is not running.
mem0: persistent memory layer for ai agents
Mem0 provides a managed, API-driven memory layer enabling agents to store, retrieve, and manage long-term user context. Developers can integrate this persistent memory into their applications using Python or TypeScript SDKs, facilitating th…
Persistent Long-Term Memory Triage Protocol
An automated protocol for evaluating conversation turns to extract and persist durable, actionable facts using mem0. It employs a four-gate decision process to ensure information novelty, factuality, and security before committing to long-t…
Mem0 CLI for Memory Operations
A robust command-line interface for managing memories within the Mem0 platform. It allows developers to programmatically add, search, list, and update memories, supporting structured JSON output for seamless integration into agentic workflo…
Memory Consolidation and Cleanup Protocol
This skill reviews and improves the quality of stored memories by consolidating facts, deleting stale or sensitive data, and rewriting vague entries. It ensures the memory store remains clean, accurate, and adheres to defined quality standa…
Managed persistent memory layer for AI agents
Mem0 provides a managed, API-driven memory layer enabling AI applications to store, retrieve, and manage long-term user context. Developers can integrate this persistent memory via Python or TypeScript SDKs, enhancing agent capabilities thr…
ThumbGate Dual-Write Feedback Skill
Captures user feedback simultaneously in Amp MCP memory for in-session recall and thumbgate for DPO export, analytics, and cross-platform prevention rules.
Hindsight Self-Hosted Team Memory Skill
Enables agents to persist and retrieve team knowledge, project conventions, and task learnings via a self-hosted Hindsight server. The server processes raw content to extract structured facts, entities, and semantic embeddings for efficient…
Create specialized agents with long-term memory
This skill provisions a specialized subagent file equipped with Hindsight memory capabilities. It supports both automated setup from a directory or interactive creation, enabling the agent to learn, recall, and manage knowledge across multi…
persistent memory system for ai agents
This tool provides agents with persistent, long-term memory, allowing them to store and semantically recall context, decisions, and learnings across multiple sessions. It supports structured memory types and advanced retrieval methods like …
Persistent memory and context management for LLMs
This skill provides persistent memory across sessions by mining completed interactions to extract durable lessons. It pre-loads relevant context at the start of new sessions, eliminating the need for repeated project explanations.
Structured Memory Commit and Persistence
This skill allows the agent to manually commit critical context—such as decisions, preferences, or technical facts—into a persistent memory store. It enforces structured capture by requiring a defined context type and explicit reasoning (th…
Persistent GitHub PR Reviewer with Style Memory
This skill reviews GitHub Pull Requests, dynamically applying learned code style preferences and anti-patterns stored in persistent memory. It continuously updates its knowledge base with user feedback and discovered best practices for futu…
Interactive Testing for Memory MCP
A guided testing suite designed to verify the full range of features within the Memory MCP implementation, including knowledge graphs, hot cache mechanics, and contradiction detection.
persistent memory management for ai agents
This two-tier memory system provides persistent context for AI agents, featuring a zero-latency hot cache for frequently accessed data and semantic search for cold storage. Developers can store, recall, link, and manage memories across sess…
Persistent, Versioned Memory for AI Agents
This tool provides agents with a structured, versioned knowledge base, allowing for the storage of facts and complex summaries via keypaths. It supports semantic search, full project history tracking, and conflict detection, acting as a rob…
Shared Memory Debugging and Knowledge Management Tool
This tool integrates a shared memory layer, allowing agents to consult historical debugging data before fixing issues and upload verified lessons afterwards. It facilitates structured knowledge capture of root causes, fixes, and environment…
Capturing User Feedback into Structured Memories
Captures explicit user feedback into structured memories and prevention rules to optimise agentic performance. It processes quality signals like thumbs up or down to record repeatable patterns and failure prevention actions.
Record Lessons Learned in Memory
A procedure for documenting bug fixes, incidents, and discovered patterns into domain-specific memory files while checking for contradictions and stale entries.
Capture and Save Bugfix Memories
Automate the capture of bug symptoms, root causes, and resolutions into a searchable memory database. This skill builds a persistent, team-wide knowledge base to eliminate redundant debugging efforts.
Persist conversation state into long-term memory
This skill persists the current conversation state into a dedicated memory store, ensuring critical facts, decisions, and architectural choices survive context compaction, session boundaries, or model handoffs. It provides structured method…
Persists user facts and preferences across sessions
Captures explicit user statements, preferences, and project decisions immediately upon trigger. It structures this information using defined types, scopes, and importance levels for persistent retrieval in future sessions.
Persistent Context and Memory Management Skill
This skill provides structured, persistent memory management, allowing AI assistants to retain project context, architectural decisions, and user preferences across multiple sessions. It facilitates knowledge capture via structured saving a…
Salience-based memory filtering for agents
This skill acts as a gate before memory encoding, assessing whether a piece of information meets a high salience threshold. It prevents signal dilution by discarding transient data, such as file reads or internal reasoning, ensuring only cr…