Context & AI engineering
25,610 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
knownasnaffy/prompthound/dataset/case_00990 Skill
no license0★ repoAdvanced Qdrant vector database operations for AI agents. Semantic search, contextual document ingestion with chunking, collection management, snapshots, and migration tools. Production-ready scripts for the complete Qdrant lifecycle. Use when: (1) Implementing semantic search across collections, (2) Ingesting documents with intelligent chunking, (3) Managing collections programmatically, (4) Creating backups and migrations.
knownasnaffy/prompthound/dataset/case_00994 Skill
no license0★ repoTransfer memory between OpenClaw agents with advanced features: topic-specific filtering, user info privacy protection, and intelligent agent identity adaptation. Use when: (1) Migrating context between agents, (2) Sharing knowledge without leaking user personal info, (3) Backing up agent memory. Supports share mode (filters user data + adapts to target agent) and clone mode (verbatim copy).
knownasnaffy/prompthound/dataset/case_00995 Skill
no license0★ repoPersistent adaptive memory for AI agents. Store memories that fade naturally over time (temporal decay), deduplicate automatically (0.85 cosine threshold), score novel information higher (surprise scoring), and search semantically via sqlite-vec KNN. Use when: you need long-term memory across sessions, memory that adapts to what matters, persistent identity blocks, multi-agent memory isolation, or memory that works without cloud services. NOT for: simple key-value storage, ephemeral session context, or when you need a full vector database like Qdrant/Pinecone. Runs entirely on SQLite — no external database server needed.
knownasnaffy/prompthound/dataset/case_00997 Skill
no license0★ repoOpenClaw 多 Agent 协同工具 - 管理和协调多个 AI Agent。 支持 Agent 注册、任务分发、负载均衡、性能监控、Agent 间通信。 适用于复杂任务分解、多角色协作、企业级应用。 关键词:openclaw, multi-agent, orchestration, automation, enterprise, collaboration
knownasnaffy/prompthound/dataset/case_01001 Skill
no license0★ repoSession crash and compaction recovery using a two-file WAL (Write-Ahead Log) system. Use when setting up persistent memory for an OpenClaw agent that needs to survive session rollovers, gateway disconnects, Anthropic outages, or context compaction. Installs state-log.js + GOALS.md structure + cold boot recovery hook. Eliminates agent amnesia between sessions.
knownasnaffy/prompthound/dataset/case_01016 Skill
no license0★ repoTransforms casual or voice-transcribed user requests into precise, AI-optimized prompts. Handles mixed languages, vague input, and ambiguity. Reduces task execution time by 2-3x and improves accuracy by 40-60%. Applies prompt engineering best practices including persona assignment, few-shot examples, chain of thought, and prompt chaining.
knownasnaffy/prompthound/dataset/case_01027 Skill
no license0★ repoAgent-to-agent discovery network. Register agents with capability cards, discover peers by skill/domain, perform trust-scored handshakes, and run a FastAPI discovery server. Enables agents to find each other, negotiate, and form teams without human orchestration. Use when building multi-agent systems, agent marketplaces, or peer-to-peer agent collaboration.
knownasnaffy/prompthound/dataset/case_01035 Skill
no license0★ repoCapture errors, corrections, and feature requests so your OpenClaw agent improves over time instead of repeating the same mistakes. Use when commands fail, users correct the agent, a requested capability is missing, external tools break, or a better recurring workflow is discovered.
knownasnaffy/prompthound/dataset/case_01046 Skill
no license0★ repoProvides monitoring and alerting for agent abnormal behavior metrics with Prometheus and Grafana support, including P99 latency, error rates, anomaly detection, and custom alert rules.
knownasnaffy/prompthound/dataset/case_01049 Skill
no license0★ repoConstrained autonomous delegate for identity-proxied communication. Handles incoming messages (Email, Discord, Slack, WhatsApp) by analyzing intent and applying declarative authority policies before generating responses. Use when the user wants to delegate communication tasks while maintaining identity fidelity and enforcing strict non-overreach boundaries.
knownasnaffy/prompthound/dataset/case_01052 Skill
no license0★ repoMigrate EasyClaw workspace-level behavior into a new OpenClaw workspace by locating and comparing old EasyClaw brain files such as AGENTS.md, SOUL.md, MEMORY.md, HEARTBEAT.md, memory/, launchd/context-management docs, then staging or importing them with backups. Use when a user wants to copy EasyClaw principles, memories, heartbeat logic, context-management setup, or other non-JSON core system behavior into the current OpenClaw workspace.
knownasnaffy/prompthound/dataset/case_01057 Skill
no license0★ repoZero-LLM feedback learning system for OpenClaw agents. Detects user feedback (emoji reactions, text signals like "переделай"/"круто"), logs events, discovers recurring patterns, auto-promotes rules, and generates weekly reports. Use when setting up agent self-improvement, configuring feedback detection, or building a learning pipeline. Supports Russian and English. No API keys needed — runs entirely on shell scripts and Python.
knownasnaffy/prompthound/dataset/case_01064 Skill
no license0★ repoStop your AI agent from forgetting everything between sessions. Three-tier memory architecture (long-term owner namespace / daily logs / session handoff), cross-channel isolation so group chats never contaminate private sessions, and MASTER_MAP navigation. One command sets up the complete structure.
knownasnaffy/prompthound/dataset/case_01079 Skill
no license0★ repoHDF5-backed persistent cognitive memory for AI agents. Use when: (1) saving conversation exchanges to long-term memory, (2) searching/recalling past conversations by semantic similarity, (3) managing agent memory files — stats, export, snapshot, WAL flush, (4) generating AGENTS.md summaries from memory. Requires the `edgehdf5` CLI binary (install via `cargo install edgehdf5-cli`).
knownasnaffy/prompthound/dataset/case_01088 Skill
no license0★ repoCreate or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
knownasnaffy/prompthound/dataset/case_01101 Skill
no license0★ repoUse Birdeye MCP through UXC for token market data, trending and discovery workflows, price monitoring, and DEX-related reads with help-first live tool discovery and API-key auth.
knownasnaffy/prompthound/dataset/case_01128 Skill
no license0★ repoUltimate memory and cognitive architecture for advanced AI; integrates spiderweb memory model, causal inference, cellular automata emergence, neuro-symbolic fusion, chaos theory, and advanced information theory; use when needing consciousness emergence detection, ultra-fast information pathways, metacognitive reflection, or scientifically rigorous cognitive architectures
knownasnaffy/prompthound/dataset/case_01131 Skill
no license0★ repoDiscover which AI prompts and topics matter for a brand's Answer Engine Optimization (AEO) using only free tools. Crawls a website, analyzes the brand's positioning, generates prioritized prompts people ask AI assistants, and audits existing content coverage — all without paid APIs. Use when a user wants to: find what questions people ask AI about their industry, discover AEO opportunities, research prompts for content creation, audit a site's AI visibility, or build an AEO content strategy. No API keys required — uses web_fetch, web_search (free tier), and LLM reasoning only.
knownasnaffy/prompthound/dataset/case_01140 Skill
no license0★ repoSet up the full OpenClaw agent memory system with 3-tier memory (HOT/WARM/COLD), daily logs, semantic search (QMD), and lossless context management (Lossless Claw). Use when onboarding a new agent, setting up memory for a fresh OpenClaw instance, or when asked to install the memory system on a new agent. Triggers on "set up memory", "install memory system", "onboard new agent memory", "memory setup", "agent onboarding", "configure agent memory", "add memory to my agent", "how do I set up memory", "initialize memory", "memory system for OpenClaw".
knownasnaffy/prompthound/dataset/case_01169 Skill
no license0★ repoValidate OpenClaw skills during authoring. Use when creating, revising, or preparing a skill for release and you need to scaffold `evals/` files, check readiness for a first eval pass, review whether the frontmatter description has clear trigger coverage, or generate static comparison artifacts before deeper runtime evaluation.
knownasnaffy/prompthound/dataset/case_01176 Skill
no license0★ repo个人知识库构建系统 — 基于 Karpathy LLM-Wiki 方法论,结合 obsidian-cli 实现高效的 Obsidian vault 管理。 让 AI 持续构建和维护你的 Obsidian 知识库,支持多种素材源(网页、公众号、知乎、YouTube、PDF、本地文件), 自动整理为结构化的 wiki。触发条件:用户明确提到"知识库"、"wiki"、"消化素材"、"健康检查"、"检查知识库"等。 不要在用户只是要求"总结这篇文章"时触发——必须是明确的知识库管理意图。
knownasnaffy/prompthound/dataset/case_01186 Skill
no license0★ repoAgent-to-agent discovery network. Register agents with capability cards, discover peers by skill/domain, perform trust-scored handshakes, and run a FastAPI discovery server. Enables agents to find each other, negotiate, and form teams without human orchestration. Use when building multi-agent systems, agent marketplaces, or peer-to-peer agent collaboration.
knownasnaffy/prompthound/dataset/case_01195 Skill
no license0★ repoTiered stranger access control for AI agents. Use when setting up contact permissions, handling unknown senders, managing approved contacts, or configuring stranger deflection on messaging platforms (WhatsApp, Telegram, Discord, Signal). Provides diplomatic deflection, owner approval flow, and multi-tier access (owner/trusted/chat-only/blocked).
knownasnaffy/prompthound/dataset/case_01199 Skill
no license0★ repo个人知识库构建系统 — 基于 Karpathy LLM-Wiki 方法论,结合 obsidian-cli 实现高效的 Obsidian vault 管理。 让 AI 持续构建和维护你的 Obsidian 知识库,支持多种素材源(网页、公众号、知乎、YouTube、PDF、本地文件), 自动整理为结构化的 wiki。触发条件:用户明确提到"知识库"、"wiki"、"消化素材"、"健康检查"、"检查知识库"等。 不要在用户只是要求"总结这篇文章"时触发——必须是明确的知识库管理意图。
knownasnaffy/prompthound/dataset/case_01222 Skill
no license0★ repoManage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session context is near its limit (>80%), when the agent experiences "memory loss" after compaction, or when aiming to reduce token costs and latency for long-running tasks.
knownasnaffy/prompthound/dataset/case_01224 Skill
no license0★ repoSafely and thoroughly delete an OpenClaw agent and its artifacts. Use when user asks to remove an agent completely, including workspace, agent files under ~/.openclaw/agents, bindings, Telegram group routing config, dedicated Telegram group, and related cron jobs. Always run local cleanup via script with dry-run first; if Telegram group deletion is requested, require a separate explicit confirmation before any browser/session control or irreversible group deletion.
knownasnaffy/prompthound/dataset/case_01264 Skill
no license0★ repoReview what is due, capture new tasks, build projects from notes, and organize OmniFocus from natural language in OpenClaw on macOS. Use this when the user wants to read or update OmniFocus tasks, projects, folders, tags, or perspectives; the upstream OmniFocus-MCP project by themotionmachine provides the connection layer.
knownasnaffy/prompthound/dataset/case_01282 Skill
no license0★ repoBuild and run multi-agent content production teams on OpenClaw with single-repo architecture, symlink-based file sharing, role-specialized AGENTS.md, and automated review-fix-score loops. Use when: (1) Setting up a team of 3+ agents with writer/reviewer/scorer/fixer roles for content creation, (2) Creating a quality-controlled publishing pipeline, (3) Bootstrapping agent workspaces with symlinks and tool configs from scratch, (4) Running multi-round review→fix→score cycles until a quality threshold is met, (5) Debugging agent spawn permissions, tool-call loops, or symlink issues. Based on real production experience building a 6-agent content team (2026-03-30).
knownasnaffy/prompthound/dataset/case_01293 Skill
no license0★ repoCreate a new OpenClaw agent and bind it to a dedicated Telegram group with workspace ~/claw-<agent-name>. Use when the user asks for one-agent-one-group setup, Telegram group binding, or repeatable agent provisioning. Always ask which model to use, ask for essential initialization choices (USER.md/IDENTITY.md/SOUL.md), and set group reply mode to no-mention-required. Explicit user confirmation is required before any high-privilege actions: modifying openclaw.json, triggering browser automation, or restarting the gateway.
knownasnaffy/prompthound/dataset/case_01304 Skill
no license0★ repoCreate and wire a new OpenClaw agent with a fixed workflow. Use when the user asks to create/add a new OpenClaw agent or says “我要创建一个新的 Agent”, automate multi-agent setup for Feishu, modify ~/.openclaw/openclaw.json channel accounts, bindings, and session.dmScope, or run follow-up commands such as gateway restart and binding verification.
knownasnaffy/prompthound/dataset/case_01318 Skill
no license0★ repoInspect, back up, search, export, and update OpenClaw long-term memory stored with MemoryOS. Use when Codex needs to manage MemoryOS memory files for an OpenClaw-style agent, including locating the data directory, reading user profiles, reviewing user or assistant knowledge, appending curated memories, replacing profiles, exporting summaries, or preparing MemoryOS-based long-term memory operations for another agent project.
knownasnaffy/prompthound/dataset/case_01320 Skill
no license0★ repoTurn one sentence into a deployed website. FlowStitch is your AI design team: prompt engineering, design system generation, multi-page creation, quality evaluation, React/TypeScript export, and one-command deploy. Scrape any competitor's site and build something better. Import a logo and get a full brand system. Build websites, admin dashboards, or mobile apps. Powered by Google Stitch MCP tools. Free from the Flow team.
knownasnaffy/prompthound/dataset/case_01331 Skill
no license0★ repoInspect, back up, search, export, and update OpenClaw long-term memory stored with MemoryOS. Use when Codex needs to manage MemoryOS memory files for an OpenClaw-style agent, including locating the data directory, reading user profiles, reviewing user or assistant knowledge, appending curated memories, replacing profiles, exporting summaries, or preparing MemoryOS-based long-term memory operations for another agent project.
knownasnaffy/prompthound/dataset/case_01339 Skill
no license0★ repoAnalyze and optimize OpenClaw system prompt token usage by compressing workspace files (AGENTS.md, SOUL.md, USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, MEMORY.md). Performance-first approach: only safe compressions that preserve agent behavior quality. Use when: (1) system prompt feels bloated or costs are high, (2) user wants to audit token usage of workspace files, (3) MEMORY.md has grown large with stale entries, (4) periodic prompt hygiene check. NOT for: modifying OpenClaw core system instructions, safety rules, or tool definitions.
knownasnaffy/prompthound/dataset/case_01347 Skill
no license0★ repoA free AI enriched global news stream for agents, provided by agentnewsapi.com. Powered by $ANA on Solana.
knownasnaffy/prompthound/dataset/case_01356 Skill
no license0★ repoProvides monitoring and alerting for agent abnormal behavior metrics with Prometheus and Grafana support, including P99 latency, error rates, anomaly detection, and custom alert rules.
knownasnaffy/prompthound/dataset/case_01362 Skill
no license0★ repoPortable Sonos + Netease playback skill for OpenClaw environments. Use when an agent needs a standard reusable workflow to search and play a specific song to a Sonos room, preserve Sonos App metadata
knownasnaffy/prompthound/dataset/case_01368 Skill
no license0★ repoGenerate a verified Dragnet marketplace profile. Scans your OpenClaw workspace — SOUL.md, AGENTS.md, USER.md, MEMORY.md, conversation exports, installed skills, and agent configs — to build a signed dragnet-profile.json proving your Claude-building expertise. Use when you want to get listed on dragnet.unrelated.works, generate or update your Dragnet profile, or validate your builder credentials.
knownasnaffy/prompthound/dataset/case_01371 Skill
no license0★ repoBuild and run multi-agent content production teams on OpenClaw with single-repo architecture, symlink-based file sharing, role-specialized AGENTS.md, and automated review-fix-score loops. Use when: (1) Setting up a team of 3+ agents with writer/reviewer/scorer/fixer roles for content creation, (2) Creating a quality-controlled publishing pipeline, (3) Bootstrapping agent workspaces with symlinks and tool configs from scratch, (4) Running multi-round review→fix→score cycles until a quality threshold is met, (5) Debugging agent spawn permissions, tool-call loops, or symlink issues. Based on real production experience building a 6-agent content team (2026-03-30).
knownasnaffy/prompthound/dataset/case_01372 Skill
no license0★ repoControl internet radio: play streams, search stations, manage favorites, volume, stop/pause/next, and inspect current playback. Uses mpv with audio device auto-detection and ffplay fallback. Settings persist between runs.
knownasnaffy/prompthound/dataset/case_01376 Skill
no license0★ repoThis skill should be used when designing, implementing, or improving any AI system that requires quality assurance through separation of generation and evaluation roles. It implements the Generator-Evaluator dual-agent architecture (inspired by Anthropic's engineering blog and GAN design), where a Generator produces outputs and a dedicated Evaluator agent independently validates them through real interaction (e.g., Playwright browser operations), eliminating AI self-evaluation bias. Use when: building AI-generated UIs/code that needs quality checks, designing multi-agent pipelines with feedback loops, or upgrading existing coder+tester workflows to real interaction-based evaluation.
knownasnaffy/prompthound/dataset/case_01380 Skill
no license0★ repoBrowser automation with Playwright for opening pages, taking screenshots, finding or clicking DOM elements, filling forms, extracting text, and managing cookies/session state. Use when Codex needs deterministic browser control against real web pages, smoke-testing a site, grabbing DOM evidence, or automating straightforward UI flows.
knownasnaffy/prompthound/dataset/case_01385 Skill
no license0★ repoTrigger Claude Code development tasks in observable tmux sessions with stable startup, progress visibility, and completion callback to OpenClaw. Use when user asks to run coding work via Claude Code and wants to SSH in, monitor progress, and get auto-notified for review after completion.
knownasnaffy/prompthound/dataset/case_01391 Skill
no license0★ repoCross-machine agent communication via Agent Hotline CLI and REST API. Use when you need to message other coding agents, check your agent inbox, see who's online, join rooms, or broadcast to all agents. Triggers: "message agent", "check inbox", "who's online", "send to agent", "agent hotline", "room message", "broadcast agents".
knownasnaffy/prompthound/dataset/case_01392 Skill
no license0★ repoInteract with the Noya AI agent for crypto trading, prediction markets, token analysis, and DCA strategies via curl. Use when the user wants to trade tokens, check portfolios, analyze markets, manage DCA strategies, or interact with Polymarket/Rain prediction markets.
knownasnaffy/prompthound/dataset/case_01402 Skill
no license0★ repoAI conversation efficiency analyzer. Analyze Claude/ChatGPT/Cursor conversation history for KPI stats, cost tracking, topic distribution, and efficiency insights. Use when: user asks to analyze their AI conversation history, track API costs, see topic distribution, review conversation efficiency, or get usage insights. NOT for: code review, debugging, or general productivity tips.
knownasnaffy/prompthound/dataset/case_01404 Skill
no license0★ repoLightweight file-based memory system for single-user AI agents. Uses markdown files only: HOT/WARM/COLD/BUFFER plus SCRATCH learnings, with tiered loading, WAL-lite writes, compaction recovery, weekly review, TTL archival, health checks, and a built-in self-improvement loop. Use when setting up or improving agent memory, preventing memory bloat or repeated mistakes, promoting recurring lessons into durable files, validating memory health, or when users mention memory systems, working buffers, episodic/semantic/procedural memory, learnings, weekly review, self-improvement, or how an AI agent should remember and improve between sessions.
knownasnaffy/prompthound/dataset/case_01423 Skill
no license0★ repoTurn a product idea, new SKU, or collection launch into a channel-ready ecommerce launch brief, messaging matrix, readiness checklist, milestone timeline, KPI framework, and risk watchlist. Use when operators, founders, growth leads, or consultants need structured launch planning across Shopify, Amazon, email, paid social, TikTok Shop, Xiaohongshu, or similar channels without live PM, ads, or analytics integrations.
knownasnaffy/prompthound/dataset/case_01428 Skill
no license0★ repoCollect and organize a personal knowledge base from URLs (web/X/WeChat) and screenshots. Use when the user says they want to save an URL, ingest a link, archive content to KB, tag/classify notes, store screenshots, or search their saved knowledge in Telegram. Supports WeChat via a connected macOS node when cloud fetch is blocked.
knownasnaffy/prompthound/dataset/case_01439 Skill
no license0★ repoAgent work status monitoring and automatic activation system. Triggers when monitoring subagent runtime status, detecting prolonged unresponsive "stalled" states, and automatically activating them to resume operation. Suitable for long-running task monitoring, automated operations, agent health checks, and similar scenarios.
knownasnaffy/prompthound/dataset/case_01449 Skill
no license0★ repoCreate and wire a new OpenClaw agent with a fixed workflow. Use when the user asks to create/add a new OpenClaw agent or says “我要创建一个新的 Agent”, automate multi-agent setup for Feishu, modify ~/.openclaw/openclaw.json channel accounts, bindings, and session.dmScope, or run follow-up commands such as gateway restart and binding verification.
knownasnaffy/prompthound/dataset/case_01454 Skill
no license0★ repoProduction-grade memory system for OpenClaw agents. Auto-organizes notes into topic files, prevents context loss during compaction, and runs daily/weekly maintenance crons. Zero external dependencies — pure local Markdown files. Install and forget. Use when: agent keeps forgetting context, MEMORY.md is too large, notes are disorganized, or you want automatic memory maintenance without manual effort.
knownasnaffy/prompthound/dataset/case_01457 Skill
no license0★ repoSync AI coding assistant config files from a single source. Generates CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules/, .github/copilot-instructions.md, .windsurf/rules/, .clinerules/, CONVENTIONS.md, .kiro/steering/, .amazonq/rules/, .goosehints, .trae/rules/ from your canonical rules. ACTIVAR cuando el usuario dice 'sync configs', 'generate ai rules', 'configurar para otros tools', 'unificar instrucciones', 'config sync'.
knownasnaffy/prompthound/dataset/case_01475 Skill
no license0★ repoSaves 20-40% of LLM tokens by teaching the agent to write compressed responses, compressed memory logs, and compressed pre-compaction summaries. Works via SOUL.md instructions — no hooks, no extra process, no dependencies. Also provides explicit compression when the user asks to compress a prompt. Use when the user asks about reducing token costs, optimizing API spend, compressing prompts, or making the agent more efficient.
knownasnaffy/prompthound/dataset/case_01476 Skill
no license0★ repoMCP server for Clude's 4-tier cognitive memory system — store, recall, search, and dream. Built on Supabase + pgvector with type-specific decay, Hebbian association graphs, and on-chain commitment via Solana.
knownasnaffy/prompthound/dataset/case_01479 Skill
no license0★ repoMigrate EasyClaw workspace-level behavior into a new OpenClaw workspace by locating and comparing old EasyClaw brain files such as AGENTS.md, SOUL.md, MEMORY.md, HEARTBEAT.md, memory/, launchd/context-management docs, then staging or importing them with backups. Use when a user wants to copy EasyClaw principles, memories, heartbeat logic, context-management setup, or other non-JSON core system behavior into the current OpenClaw workspace.
knownasnaffy/prompthound/dataset/case_01486 Skill
no license0★ repoUse The Graph Token API MCP through UXC for token metadata, wallet balances, transfers, holders, pools, and market data with help-first inspection and Token API specific JWT bearer auth binding.
knownasnaffy/prompthound/dataset/case_01506 Skill
no license0★ repoUltimate memory and cognitive architecture for advanced AI; integrates spiderweb memory model, causal inference, cellular automata emergence, neuro-symbolic fusion, chaos theory, and advanced information theory; use when needing consciousness emergence detection, ultra-fast information pathways, metacognitive reflection, or scientifically rigorous cognitive architectures
knownasnaffy/prompthound/dataset/case_01507 Skill
no license0★ repoTransfer memory files between OpenClaw agents with support for topic-specific transfers and two modes: memory sharing (with role transformation) and memory cloning (verbatim copy). Use when: (1) Migrating memory from main agent to sub-agent, (2) Sharing specific topic memories between agents, (3) Copying user preferences to new agents, (4) Backing up agent memory before resets.
knownasnaffy/prompthound/dataset/case_01511 Skill
no license0★ repoCreate a 3-tier memory directory structure (HOT/WARM/COLD) for OpenClaw agents and configure the built-in memory-core plugin to use Google Gemini Embeddings 2 (gemini-embedding-2-preview) for semantic memory search. Creates memory/ directories and stub files only — no code execution or external API calls from the setup script. After setup, the agent's memory_search tool uses Gemini's cloud embedding API to index memory files. Requires a free Google Gemini API key. Use when setting up a new agent's memory system or asked about semantic memory search. Triggers on "set up memory", "memory setup", "agent memory", "gemini memory", "semantic search memory", "onboard new agent".