Results for “mem”

Injects up to 1 million tokens of external context into AI agent memory, auto-summarizes conversations with tone and intent preservation, and compresses multi-turn history into dense token sequences.

Builds persistent multi-agent workflows on Claude Code using a kernel config, specialist agents, slash commands, file-based memory, and scheduled automation without external databases.

Inspect local project structure, git state, docs, and relevant governed memory.

Prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.

Analyzes prompt injection, retrieval poisoning, memory contamination, planner drift, and tool-boundary abuse in agentic systems, mapping trust boundaries and proving exploit chains.

Search and analyze news articles with media bias context, get balanced perspectives, access live stock/ETF/crypto data with AI analysis, and find memes by semantic meaning.

Search real-time news with bias scoring, get live stock/ETF/crypto data with AI analysis, ML options pricing, balanced news synthesis, and meme search via the Helium MCP server.

Runs an autonomous multi-agent software development pipeline that takes a PRD through to production with zero human intervention, using model-tiered agents, memory, and verification cycles.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications

Review docs, tool output, skills, and memory candidates for prompt-injection risk.

跨多个存储层（本地文件、MCP memory、向量存储、Git 仓库）的知识库管理、摄取、同步和检索。在用户想要保存、组织、同步、去重或跨知识系统搜索时使用。

Content Factory Graphify wrapper. Use for codebase map, “where does X live”, how modules connect, architecture orientation, or when graphify.mdc applies. Query graphify-out/ before grepping or reading giant markdown brains. Does not replace Mem0, Hindsight, or product Memory Service RAG.

Detect model stealing, model inversion, and membership inference performed through inference-API abuse by monitoring query patterns, applying output perturbation, and red-teaming your own model's extractability.

Quantize LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss using bitsandbytes. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers.

Route active project/repo memory requests into one honest packet: memory-layer choice, load-context, search-context, store-conclusions, setup-integration, or repo-packer route-out. Use when agents need searchable decisions, manifests, stable links, handoff notes, and small “read this first” packets across sessions. Route long-lived markdown knowledge bases to `llm-wiki`, structural graph memory to `graphify`, human-authored vault organization to note/vault skills, and one-shot repo packing to tools like Repomix, Gitingest, or Code2Prompt.

Create a daily business brief from local docs, memory, tasks, and safe web context.

Describe and summarize the current dataset in memory. Optionally inspect a specific variable with codebook.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.

Adds a persistent pattern or rule that Ralph will remember and apply to future stories.

Orchestrates multi-agent workflows defined in YAML piece files, delegating tasks to team members and managing state transitions.

Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.

`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.

Watches conversations continuously and compresses them into prioritized notes, consolidating and recovering missed sessions with multiple redundancy layers.

`analysis-agent`/`task-agent`/`review-agent`: use when latency, throughput, bundle, memory, CPU, query, rendering, or resource cost needs a budget; skip without performance risk.

Scale pandas and NumPy workflows to larger-than-memory datasets using parallel and distributed computing.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Drive mex (`mex-agent`), persistent project memory and code graphs for AI coding agents. One command scaffolds a living wiki, builds a deterministic code graph, and installs a project anchor file (CLAUDE.md, root AGENTS.md, .cursorrules, .windsurfrules, copilot-instructions.md, or .opencode/opencode.json) that your agent auto-loads as a standing rule document. Use when the user wants to `mex setup` a new project, build a symbol-grounded wiki, keep knowledge connected to implementation, route relevant context to agents, or run drift detection (`mex check`, `mex sync`). Triggers on: "mex setup", "project memory", "code graphs", "codebase documentation", "drift detection", "agent memory", "structured scaffolds", "architectural context", "living wiki", "project anchor file".

Build LLM-powered applications with modular components for chains, agents, memory, and retrieval, supporting Python and JavaScript frameworks.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.