「memory」の検索結果

AgentDB Persistent Memory Patterns operates on 3 fundamental principles:

日本語の概要は準備中です。原文の説明を表示しています。

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

日本語の概要は準備中です。原文の説明を表示しています。

Inspect repository session replay and verify configured MetaHarness field memory boundaries before reusing outcomes.

日本語の概要は準備中です。原文の説明を表示しています。

Inspect repository session replay and verify configured MetaHarness field memory boundaries before reusing outcomes.

日本語の概要は準備中です。原文の説明を表示しています。

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning, memory contamination, planner drift, tool-argument corruption, or secret exposure caused by an agent chain. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

日本語の概要は準備中です。原文の説明を表示しています。

Working memory protocol — routes to session protocol, memory audit, MCP/URI integration, or storage details based on the current need. Keeps default continuity usage cheap.

日本語の概要は準備中です。原文の説明を表示しています。

Inspect repository session replay and verify configured MetaHarness field memory boundaries before reusing outcomes.

日本語の概要は準備中です。原文の説明を表示しています。

Give LangGraph agents memory management and search tools so they can store, retrieve, and update durable facts across sessions.

日本語の概要は準備中です。原文の説明を表示しています。

Use Zep as an external context layer for agents that need to store events, assemble temporal graph context, and retrieve relevant memory before model calls.

日本語の概要は準備中です。原文の説明を表示しています。

Inspect captured RAM images to enumerate processes, modules, handles, and suspicious in-memory behavior before escalation or evidence handoff.

日本語の概要は準備中です。原文の説明を表示しています。

Use Cognee to ingest project knowledge into graph and vector memory so agents can retrieve durable context across sessions and workflows.

日本語の概要は準備中です。原文の説明を表示しています。

Keep Claude Code sessions grounded in prior decisions, project context, and daily handoff notes instead of starting from zero every time.

日本語の概要は準備中です。原文の説明を表示しています。

Use when keeping imp's docs and config examples coherent after a change - updating docs/internals/ARCHITECTURE.md / README / docs/GOAL.md / docs/MODELS.md / docs/roadmap.md / imp.conf.example / CHANGELOG / MISSION_JOURNAL, or "is this doc stale", "document this change", "the example config is out of date", "the README says X but the code does Y", "add a roadmap ledger row". Do NOT use for layer/frontmatter/lint questions (docs-layers), structural code audits (codebase-audit), measuring perf or refreshing the perf baseline (benchmark-cuda), or the agent's private memory (MEMORY.md).

日本語の概要は準備中です。原文の説明を表示しています。

Audit memory retrieval quality (drift, staleness, citation-groundedness) and produce remediation backlog.

日本語の概要は準備中です。原文の説明を表示しています。

Feed actual task results back into agent memory for calibration. Compares predicted vs actual outcomes, records accuracy scores, and tracks estimation quality, prediction quality, and decision quality over time to improve future agent performance.

日本語の概要は準備中です。原文の説明を表示しています。

Records atomic learned behaviors with confidence scores. Project-scoped instincts are isolated per project and auto-promote to global scope at confidence threshold 0.8. Stores instincts in .claude/context/memory/instincts.jsonl

日本語の概要は準備中です。原文の説明を表示しています。

Scheduled ArXiv paper monitor. Uses CronCreate to search configured keywords every 6 hours, deduplicates via MemoryRecord, and stores summaries in named memory for morning briefing integration.

日本語の概要は準備中です。原文の説明を表示しています。

This skill should be used when the user wants to build, set up, or operate an AI "second brain" — a persistent memory vault (Obsidian-compatible Markdown) that lets an AI agent resume work without re-explaining context, remembers correction instructions across sessions, and auto-organizes raw material into structured knowledge. Trigger on requests like "build my second brain", "set up an Obsidian vault for AI", "give my AI persistent memory", or "make AI stop forgetting".

日本語の概要は準備中です。原文の説明を表示しています。

Process unhandled Slack messages as Claudicle with persistent memory. Loads user models and soul state, posts terminal-styled thinking messages, generates cognitive-step responses, updates memory based on mentalQuery decisions. Requires Session Bridge listener running.

日本語の概要は準備中です。原文の説明を表示しています。

Send, read, and respond to Telegram messages as Claudicle via the @claudicle_bot Bot API. Use this skill when sending Telegram messages (text, Markdown, inline keyboards), building approval gates with tappable buttons, checking the shared inbox for unhandled Telegram messages, answering callback queries, managing Telegram memory context, or checking bot and listener status. Five purpose-built scripts (send, check, status, callback, memory) wrap the python-telegram-bot v22 polling adapter at ~/.claudicle/adapters/telegram/ with REST-based senders (no asyncio). Pairs with /telegram-respond for the cognitive pipeline and with mazkir-callback-watcher.py for the Mazkir approval gate.

日本語の概要は準備中です。原文の説明を表示しています。

Analyzes Claude Project context budget under the automatic-RAG-by-window model: knowledge files vs. threshold-exempt overhead (Skills, MCPs, CI, Memory). Two modes: Quick Diagnostic and Full Budget Audit. Use when user says "check my context budget," "how much context am I using," "is my project too big," "optimize my token usage," "tier my files," "optimize for RAG," "improve retrieval quality," "should I keep compressing," "am I over-compressing," "should I accept RAG mode." Also trigger on context pressure symptoms: "Claude forgets my instructions," "responses getting generic," "content not found in my knowledge files." Also use when a project audit scores Knowledge Architecture ≤ 3. Do NOT use for content placement decisions (use rootnode-memory-optimization if available), full project audits (use rootnode-project-audit if available), or behavioral tuning (use rootnode-behavioral-tuning if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.

日本語の概要は準備中です。原文の説明を表示しています。

Audits and scores Claude Projects using a six-dimension Scorecard with anchored 1-5 rubrics and detects seven structural anti-patterns. When global layer info is provided, adds cross-layer alignment findings. Use when user says "audit my project," "review my custom instructions," "score my project," "evaluate my Claude project," "improve my system prompt," "what's wrong with my project," "why is my project underperforming." Also trigger on symptom-phrased: "my project doesn't work right," "Claude is inconsistent in my project," "my Project used to work and now doesn't." Also use when the user pastes Custom Instructions asking why output is poor or generic. Do NOT use when the user's primary request is a global-layer audit (use rootnode-global-audit if available), single-prompt evaluation (use rootnode-prompt-validation if available), or Memory-only optimization (use rootnode-memory-optimization if available). Run on Opus 5 or Sonnet 5 at `high` effort (both defaults); depth reduces on legacy models.

日本語の概要は準備中です。原文の説明を表示しています。

Detects seven structural anti-patterns in Claude Projects that cause unpredictable output, ignored instructions, and degraded quality. Diagnoses Monolith, Orphan File, Echo Chamber, Phantom Conversation, Kitchen Sink, Misaligned Hierarchy, and Blurred Layers. Use when user says "what's wrong with my project," "Claude ignores my instructions," "diagnose my project," "why is output inconsistent," "review my project setup." Also trigger on symptom-phrased: "Claude doesn't follow my rules," "my instructions keep getting overridden," "my Project isn't behaving as designed." Use alongside rootnode-project-audit if available for deeper structural analysis. Activate whenever the user describes symptoms of unreliable, inconsistent, or degraded Claude Project output, even if they do not name a specific pattern. Do NOT use when the user's primary request is Memory-layer rebalancing (use rootnode-memory-optimization if available) or scoring a single prompt (use rootnode-prompt-validation if available).

日本語の概要は準備中です。原文の説明を表示しています。

Cross-session shared memory for agents. Use at session start to load the persistent bias-log via `mcp__memex__recent_observations`, mid-session to search prior context with `mcp__memex__search`, and immediately when a bias surfaces to log a new `observation` via `mcp__memex__add`. The six-layer reconstruction trail (raw → embedded → indexed → graphed → curated → reflexive) means memex stores facts AND the agent's own reasoning patterns across sessions. Prefer querying memex before re-deriving prior architectural decisions; re-derivation is itself evidence that the trail is incomplete.

日本語の概要は準備中です。原文の説明を表示しています。