--- title: "Glosario — StudioMeyer Academy" description: "Aprende a usar la IA en tu día a día y en el trabajo. Lecciones y playbooks gratuitos. Guarda tu progreso con una cuenta." canonical: "https://studiomeyer.academy/es/dashboard/glossar" language: es markdown_versions: ["https://studiomeyer.academy/dashboard/glossar.md", "https://studiomeyer.academy/en/dashboard/glossar.md", "https://studiomeyer.academy/es/dashboard/glossar.md"] publisher: "StudioMeyer Academy, https://studiomeyer.academy (llms.txt: https://studiomeyer.academy/llms.txt)" --- # Glosario Consulta términos y entiende sus conexiones. La colección actual se dirige sobre todo a personas con interés técnico. [Todo](https://studiomeyer.academy/es/dashboard/glossar) [/](https://studiomeyer.academy/es/dashboard/glossar?letter=%2F) [A](https://studiomeyer.academy/es/dashboard/glossar?letter=A) [B](https://studiomeyer.academy/es/dashboard/glossar?letter=B) [C](https://studiomeyer.academy/es/dashboard/glossar?letter=C) [G](https://studiomeyer.academy/es/dashboard/glossar?letter=G) [H](https://studiomeyer.academy/es/dashboard/glossar?letter=H) [K](https://studiomeyer.academy/es/dashboard/glossar?letter=K) [L](https://studiomeyer.academy/es/dashboard/glossar?letter=L) [M](https://studiomeyer.academy/es/dashboard/glossar?letter=M) [P](https://studiomeyer.academy/es/dashboard/glossar?letter=P) [S](https://studiomeyer.academy/es/dashboard/glossar?letter=S) [Z](https://studiomeyer.academy/es/dashboard/glossar?letter=Z) [~](https://studiomeyer.academy/es/dashboard/glossar?letter=~) Este contenido existente está en inglés. [**/rewind (Claude Code)**Built-in Claude Code command (also aliased /checkpoint) that rolls back code AND conversation to an earlier point. Session-level safety net.](https://studiomeyer.academy/es/dashboard/glossar/git_rewind) [**~/.claude/settings.json**JSON config for hooks, permissions, env vars. User-scoped. Auto-merged with project ./.claude/settings.json.](https://studiomeyer.academy/es/dashboard/glossar/settings_json) [**~/.codex/config.toml**Codex equivalent of Claude Code's ~/.claude.json. TOML format. MCP servers, projects, features.](https://studiomeyer.academy/es/dashboard/glossar/codex_config_toml) [**AGENTS.md**Cross-tool variant of CLAUDE.md. Codex reads it. Cursor reads it. Symlink one to the other for one source of truth.](https://studiomeyer.academy/es/dashboard/glossar/agents_md) [**Auto-Dream (Claude Code)**Background subagent that consolidates memory files every 24 hours. Deduplicates, removes outdated info, rewrites relative dates as absolute.](https://studiomeyer.academy/es/dashboard/glossar/auto_dream) [**Auto-Memory (Claude Code)**Default-on since March 2026. Claude writes notes to local memory files in the background while you work. Toggle via autoMemoryEnabled in settings.json.](https://studiomeyer.academy/es/dashboard/glossar/auto_memory) [**Branch-per-Ask**Every meaningful AI task gets its own Git branch. Tiny merge surface, instant rollback when bad, clean merge when good.](https://studiomeyer.academy/es/dashboard/glossar/branch_per_ask) [**brave-search MCP**Brave's own crawled search index as an MCP server. Free 2k queries/month.](https://studiomeyer.academy/es/dashboard/glossar/brave_search_mcp) [**claude mcp add**CLI command that registers an MCP server in ~/.claude.json.](https://studiomeyer.academy/es/dashboard/glossar/mcp_install) [**CLAUDE.md**Markdown file Claude Code reads at session start as system context. The single biggest leverage point in your setup.](https://studiomeyer.academy/es/dashboard/glossar/claude_md) [**codebase-memory-mcp**Indexes your repo into a Postgres-backed knowledge graph. 14 tools.](https://studiomeyer.academy/es/dashboard/glossar/codebase_memory_mcp) [**codegraph**Deep code analysis on top of a code knowledge graph. 34 tools.](https://studiomeyer.academy/es/dashboard/glossar/codegraph) [**Confidence decay (FadeMem)**Time-based reduction of confidence on memories not accessed recently. Keeps the graph from drowning in stale beliefs without manual archival.](https://studiomeyer.academy/es/dashboard/glossar/confidence_decay) [**Context pollution**Memory loaded too greedily floods every prompt with marginally-relevant context. AI loses focus, misses the point, hallucinates trying to integrate everything.](https://studiomeyer.academy/es/dashboard/glossar/context_pollution) [**context7**Up-to-date library + framework docs as MCP tools. No API key needed.](https://studiomeyer.academy/es/dashboard/glossar/context7) [**Git as the AI safety net**Git is mandatory when building with AI. AI changes 8 files in seconds, editor undo cannot save you, only commits give you a working rollback target.](https://studiomeyer.academy/es/dashboard/glossar/git_safety_net) [**github MCP**Official GitHub MCP server. 30+ tools for issues, PRs, code search, reviews.](https://studiomeyer.academy/es/dashboard/glossar/github_mcp) [**Hooks**Deterministic shell commands that run on Claude Code events. Hard guarantees the model cannot bypass.](https://studiomeyer.academy/es/dashboard/glossar/hooks) [**Knowledge graph**Memory stored as entities and relationships rather than flat text. Enables multi-hop reasoning ("who works at the company that supplies X").](https://studiomeyer.academy/es/dashboard/glossar/knowledge_graph) [**Letta (formerly MemGPT)**OS-inspired tiered memory architecture (Core + Archival + Recall). Apache 2.0, full self-host. LongMemEval not published.](https://studiomeyer.academy/es/dashboard/glossar/letta) [**LongMemEval benchmark**Academic standard for measuring memory accuracy. Tests temporal queries, multi-hop reasoning, knowledge updates, casual mentions in long conversations.](https://studiomeyer.academy/es/dashboard/glossar/longmemeval) [**MCP basics**Model Context Protocol — open standard for connecting AI clients (Claude, Codex, Cursor) to external tools.](https://studiomeyer.academy/es/dashboard/glossar/mcp_basics) [**mcp-nex (StudioMeyer Memory)**Memory MCP server with 56 tools — sessions, learnings, decisions, knowledge graph, skills tracking.](https://studiomeyer.academy/es/dashboard/glossar/mcp_nex) [**Mem0**Open-source memory platform with 21+ framework integrations. Apache 2.0 client, cloud SaaS proprietary. LongMemEval 49% on independent eval.](https://studiomeyer.academy/es/dashboard/glossar/mem0) [**Memory basics**Persistent context across sessions. Default: ~/.claude/projects/\/memory/. Better: a memory MCP server.](https://studiomeyer.academy/es/dashboard/glossar/memory_basics) [**Permissions**Allow- and deny-lists in settings.json that auto-clear or block tool calls without prompting.](https://studiomeyer.academy/es/dashboard/glossar/permissions) [**Safe AI rollback (no git reset --hard)**Three safe paths to undo: GUI revert, /rewind in Claude Code, or explicit checkout with named commit. Never give vague "undo it" prompts to the AI.](https://studiomeyer.academy/es/dashboard/glossar/ai_rollback_pattern) [**Skills**Markdown files Claude loads on demand based on natural-language triggers. Like slash commands but smarter.](https://studiomeyer.academy/es/dashboard/glossar/skills) [**Stale facts in memory**You change your address, role, or project. The memory keeps the old fact. Without contradiction detection, you have a hallucination source.](https://studiomeyer.academy/es/dashboard/glossar/stale_facts) [**Subagents**Markdown files in ~/.claude/agents/ that spin up an isolated agent context for specific tasks.](https://studiomeyer.academy/es/dashboard/glossar/subagents) [**Sycophancy amplification**Documented LLM behaviour of adapting to user opinion. Memory makes it worse — the AI accumulates user preferences as facts and confirms them forever.](https://studiomeyer.academy/es/dashboard/glossar/sycophancy) [**Zep / Graphiti**Bi-temporal knowledge graph memory backed by the open-source Graphiti framework. SOC 2 Type II + HIPAA BAA. LongMemEval 63-71% depending on setup.](https://studiomeyer.academy/es/dashboard/glossar/zep) ## Sitemap Páginas públicas de este sitio como Markdown: [sitemap](https://studiomeyer.academy/sitemap.md). Punto de entrada curado: [llms.txt](https://studiomeyer.academy/llms.txt), texto completo: [llms-full.txt](https://studiomeyer.academy/llms-full.txt).