Results for “memo”

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Drafts a Stormwater Pollution Prevention Plan (SWPPP) compliant with 40 CFR Part 122, EPA Construction General Permit (CGP), and applicable state NPDES requirements for construction projects disturbing one or more acres. Use when drafting SWPPPs, construction stormwater permits, erosion control plans, NPDES compliance documents, or BMP selection memoranda.

IP networking fundamentals for Zephyr RTOS. Covers IoT protocol selection (LwM2M, CoAP, MQTT), IP stack configuration and trimming (IPv4/IPv6, UDP/TCP), and professional SDK integration as Zephyr modules using West manifests. Trigger when building cloud-connected applications, optimizing network memory usage, or integrating external cloud SDKs.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Manage memory in long projects and summarize the current state to prevent agent context loss. Use when starting a new session on a long-running project, resuming work after a break, switching contexts between tasks, or when context window is approaching limits. Ensures continuity and consistency across sessions.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Convert C code to idiomatic Rust. Use when migrating C projects to Rust, translating C patterns to idiomatic Rust, or refactoring C codebases. Extends meta-convert-dev with C-to-Rust specific patterns covering manual memory management to ownership, pointer safety, type system enhancements, and modernization strategies.

Perform runtime iOS app security assessments using Objection and Frida to inspect keychain, filesystem, and memory, bypass client-side protections, and evaluate data storage, network, and authentication controls during authorized penetration tests.

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

Use DuDuClaw — a self-hosted AI-employee platform — for cross-session memory, team-shared wiki knowledge, task boards, and messaging humans over LINE/Telegram/Discord/Slack. Applies when the user mentions DuDuClaw, asks their agent to remember things durably, or wants to reach people on messaging channels from an agent.

Detect process injection techniques (T1055) including classic DLL injection, process hollowing, and APC injection by analyzing Sysmon events for cross-process memory operations, remote thread creation, and anomalous DLL loading patterns.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Use when designing or auditing AI product human-in-the-loop — write approval, proposal accept/reject, action confirm, spend caps, run detail, memory capture, or any AI action with irreversible blast radius. Trigger on confirmation UX, undo, cost-before-act, show-the-plan, citations, or keeping the owner in control.

Data pipeline specialist for ETL design, data quality, CDC patterns, and batch/stream processingUse when "data pipeline, etl, cdc, data quality, batch processing, stream processing, data transformation, data warehouse, data lake, data validation, data-engineering, etl, cdc, batch, streaming, data-quality, dbt, airflow, dagster, data-pipeline, ml-memory" mentioned.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Load bounded working context at the start of a coding session. FIRES ON EVERY FIRST USER MESSAGE in a fresh session, regardless of content — including bare greetings ("hi", "hello", "hey"), task-only openers, or "let's start". Also triggers on: "fresh session", "session start", "first message in a new thread", "new chat", "cold start", "begin work in this repo", "starting work", "continue from prior session", "what were we working on", "resume", "what happened last time", "load memory", "recall context", "create a handoff", "prior session context", "latest handoff", "current state", "decision context". Skip ONLY if the user explicitly says "fresh start" or "ignore prior context". Self no-ops if invoked mid-session when context is already loaded.

Composite skill — query, capture, improve, and persist knowledge in one workflow. Chains recall (RAG query) → sync-memories (write durable note) → rag-curate (improve weak retrievals) → handoff (durable snapshot if session-ending). Use when the work involves "what did we decide", "remember this", "save where we are", or any closing checkpoint.

Generate, review, and optimize natural language instructions for Business Central agents (Designer or SDK). Triggers on: agent instructions, InstructionsV1.txt, InstructionsV2.txt, MEMORIZE, qualification rules, agent behavior, instruction keywords, agent task instructions, iterate instructions, or improve agent accuracy. Follows the Responsibilities-Guidelines-Instructions framework with official BC agent runtime keywords.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (`npx duduclaw onboard` to set up).

Reference for foundational C++ patterns covering core syntax, classes, templates, RAII, move semantics, and modern C++ features (C++11/14/17/20). Use when writing C++ code, understanding the type system, memory management, or needing guidance on which specialized C++ skill to use.

Foundational Objective-C patterns covering classes, protocols, categories, memory management (ARC/retain-release), blocks, GCD, and Foundation framework. Use when writing Objective-C code, working with Cocoa/Cocoa Touch APIs, bridging to Swift, or needing guidance on Apple platform development patterns. This is the entry point for Objective-C development.

Detects fileless malware and in-memory attacks that execute entirely in RAM without writing persistent files to disk, evading traditional antivirus. Provides detection rules for PowerShell-based attacks, reflective DLL injection, WMI persistence, and registry-resident malware.

Executes malware samples in Cuckoo Sandbox to observe runtime behavior including process creation, file system modifications, registry changes, network communications, and API calls. Generates comprehensive behavioral reports for malware classification and IOC extraction.

Two-layer memory architecture for board meeting decisions. Manages raw transcripts (Layer 1) and approved decisions (Layer 2). Use when logging decisions after a board meeting, reviewing past decisions with /cs:decisions, or checking overdue action items with /cs:review. Invoked automatically by the board-meeting skill after Phase 5 founder approval.