Results for “memory”

Rebalances context across Memory, Custom Instructions, knowledge files, and User Preferences in Claude Projects. Audits Memory for redundancy, staleness, and misplacement; prescribes optimization including Codification of stable Memory patterns into explicit User Preferences or Project CI rules. Use when user says "optimize my memory," "what should be in my memory," "trim my knowledge files," "reduce my context usage," "rebalance my project," "what should be in my preferences vs memory," or asks whether something belongs in Memory, a knowledge file, or User Preferences. Also trigger on symptom-phrased: "my project feels bloated," "Claude keeps forgetting things," "my context window keeps hitting limits." Activate whenever Memory-layer balance is the primary concern. Do NOT use for full Project audits (use rootnode-project-audit if available), single-prompt evaluation (use rootnode-prompt-validation if available), or global-layer audits that don't touch Project Memory (use rootnode-global-audit if available).

The English summary is being prepared. Showing the original description.

Append a session/state snapshot to MEMORY.md (regardless of where it lives — for this repo it's `founder/MEMORY.md`). Use when the user says "snapshot memory", "save state to memory", "/memory-snapshot", "log what happened in MEMORY", or otherwise asks to record the current session's outcomes for the next orchestrator. Locates the project's MEMORY.md, prepends a dated entry above the previous snapshot (newest first), preserves every existing entry (NEVER overwrites or truncates), and reports back the file path + byte delta. Not for one-off feedback memories (use the user-level memory system at ~/.claude/.../memory/ for those). Not for trimming or deleting old entries.

The English summary is being prepared. Showing the original description.

Write and review Rust, C++, and C code with safer memory and resource management. Covers ownership, automatic cleanup tied to scope, and smart pointers to help prevent leaks, double frees, and access to freed memory.

• Design safer memory management in systems code
• Review cleanup of files, sockets, and memory
• Investigate memory leaks and access to freed memory

Gives AI agents persistent project memory for architecture, implementation patterns, and decisions. Supports saving, searching, and retrieving knowledge, automatically syncing it with project documentation, and viewing memory usage through a dashboard.

• Save architecture decisions for later reference
• Search saved implementation patterns by type or tag
• Retrieve a specific design record by key

Helps agents choose the right agentmemory tool through MCP, a protocol for connecting agents to tools. It explains tool roles and points to parameter references for saving, retrieving, organizing, and maintaining stored knowledge.

• Choosing a tool to save or retrieve knowledge
• Checking tool names and required parameters
• Reviewing available memory management operations

Review an agent’s saved memory alongside project and personal instructions. Receive proposed destinations for useful entries and a cleanup report covering duplicates, outdated facts, conflicts, and unclear items, with approval required before changes.

• Turning saved memory into shared project instructions
• Separating personal instructions from project conventions
• Finding duplicate or outdated memory

Add persistent memory to AI coding agents — file-based, vector, and semantic search memory systems that survive between sessions. Use when a user asks to "remember this", "add memory to my agent", "persist context between sessions", "build a knowledge base for my agent", "set up agent memory", or "make my AI remember things". Covers file-based memory (MEMORY.md), SQLite with embeddings, vector databases (ChromaDB, Pinecone), semantic search, memory consolidation, and automatic context injection.

The English summary is being prepared. Showing the original description.

Memory systems specialist for hierarchical memory, consolidation, and outcome-based learningUse when "memory system, memory hierarchy, memory consolidation, forgetting strategy, salience learning, outcome feedback, temporal memory levels, entity resolution, memory, zep, graphiti, mem0, letta, hierarchical, consolidation, salience, forgetting, ml-memory" mentioned.

The English summary is being prepared. Showing the original description.

Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory or memory benchmarks (LoCoMo, LongMemEval).

The English summary is being prepared. Showing the original description.

Plan and implement a unified AgentDB memory backend for agents. Migrate SQLite and Markdown data, add HNSW indexing for similarity search, and support shared memory and SONA learning patterns while preserving compatibility with existing systems.

• Consolidating separate agent memory systems
• Migrating SQLite and Markdown data to AgentDB
• Finding stored information with similar meaning

Plan and implement a unified AgentDB memory backend for agents. Migrate SQLite and Markdown data, add HNSW indexing for similarity search, and support shared memory and SONA learning patterns while preserving compatibility with existing systems.

• Consolidating separate agent memory systems
• Migrating SQLite and Markdown data to AgentDB
• Finding stored information with similar meaning

Plan memory use and monitor long training jobs on NVIDIA DGX Spark. It guides troubleshooting for out-of-memory failures, tracks temperature and power alongside training logs, and helps assess competition between training and inference workloads.

• Estimating available memory before training
• Troubleshooting out-of-memory failures
• Investigating slowdowns during long training jobs

Consolidate established lessons from domain memory files into reusable agent instructions. Review proposed additions before merging, preserve details while reducing duplication, and remove merged entries from the memory file afterward.

• Turn accumulated lessons into reusable instructions
• Consolidate overlapping guidance
• Maintain project-specific instructions

Analyze captured RAM with Volatility to investigate suspicious processes, injected code, network connections, and other evidence of compromise. The skill guides memory investigations and organizes findings into timelines and reports, including malware traces absent from disk.

• Investigating fileless malware after an endpoint alert
• Finding hidden processes and injected code
• Linking suspicious processes to network connections

Design memory systems that help AI agents retrieve relevant past information. Choose short-term and long-term memory structures, compare vector storage options, and review document splitting and retrieval strategies for different kinds of knowledge and experience.

• Design memory for information used across conversations
• Choose storage for experiences, facts, and procedures
• Review retrieval when an agent misses saved information

Retrieve past work, decisions, and lessons from agentmemory using keyword, meaning, and relationship searches. It expands selected records, groups findings by session, and prioritizes important observations so earlier context can inform the current task.

• Recalling an earlier decision and its context
• Finding how a similar issue was handled
• Reviewing one project's or agent's history

Helps reduce GPU memory use by loading large language models in 4-bit or 8-bit formats, a technique called quantization. Covers bitsandbytes configuration, memory checks, QLoRA fine-tuning, and training with memory-saving optimizers.

• Load a larger model within available GPU memory
• Compare 4-bit and 8-bit quantization settings
• Fine-tune a quantized model with QLoRA

[omh] Project fact to remember across future sessions: capture one bounded durable project or product memory candidate through explicit remember, refuse, or defer review; for existing Hermes memory use omh-memory-sync, and for a past decision use decision-recall. Use when the user says: memory-new, new memory, project memory, product memory, remember this project, remember this product, do not save, do not save this token.

The English summary is being prepared. Showing the original description.

Optimize Python code for reduced memory usage and improved memory efficiency. Use when asked to reduce memory footprint, fix memory leaks, optimize data structures for memory, handle large datasets efficiently, or diagnose memory issues. Covers object sizing, generator patterns, efficient data structures, and memory profiling strategies.

The English summary is being prepared. Showing the original description.

Use at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.

The English summary is being prepared. Showing the original description.

End-of-session pass that persists durable facts from the CURRENT session into .claude/memory/. Runs IN-SESSION in the main agent (never via Task — a subagent starts cold with no transcript), prompted by the Stop hook's nudge. Triggers on "persist durable facts from this session", "run memory-extraction", "flush session memory", or "extract memory before close". Reads the in-context transcript plus existing memory, applies the durable-fact predicate below, and writes one file per fact plus one MEMORY.md index line — append-or-update, never clobbering a consumer's existing memory.

The English summary is being prepared. Showing the original description.

Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for static/dynamic facts, and RAG for semantic search. Perfect for chatbots, assistants, and knowledge-intensive applications.

The English summary is being prepared. Showing the original description.

Orchestrate persistent agent memory across coding sessions, repos, and tools. Load when the user asks to remember, recall context, save project memory, create a handoff, manage global memory, update memory, compact memory, audit memory, forget memory, continue from prior sessions, or before commit/push/git operations that checkpoint project state.

The English summary is being prepared. Showing the original description.

Check a Bot’s connection to Hindsight and set up dedicated and shared memory stores. The skill also creates a user knowledge summary when needed and reports which other memory stores are available to read.

• Setting up Hindsight for a Bot’s first use
• Checking the connection after a memory tool fails
• Separating project memories from shared knowledge