> ## Documentation Index
> Fetch the complete documentation index at: https://chatcli.edilsonfreitas.com/llms.txt
> Use this file to discover all available pages before exploring further.

# ChatCLI

> A CLI que une o poder dos LLMs ao seu terminal. Multi-provedor, modo agente, coder mode, K8s watcher e muito mais.

**O terminal vira um engenheiro de IA.** O **ChatCLI** traz os maiores modelos de linguagem (LLMs) direto para o seu shell — ele entende o contexto do seu projeto, edita código, executa comandos e automatiza tarefas complexas, sem você nunca sair da linha de comando. Um único binário em **Go**: rápido, portátil e self-contained.

<Frame caption="ChatCLI em ação — modo interativo com contexto e agent mode">
  <img src="https://mintcdn.com/encom/jXe34OctYqDbxuDm/images/chatcli-demo.gif?s=9e1e37199807ada6c61d9fd78bda0cf8" alt="Demo do ChatCLI" width="852" height="480" data-path="images/chatcli-demo.gif" />
</Frame>

<Snippet file="pt/badges.mdx" />

<CardGroup cols={4}>
  <Card title="14 provedores" icon="shuffle">
    OpenAI, Claude, Gemini, Grok, Ollama e mais — numa só interface.
  </Card>

  <Card title="200+ modelos" icon="layer-group">
    Um catálogo unificado. Troque de modelo a qualquer momento.
  </Card>

  <Card title="32 tools nativas" icon="wand-magic-sparkles">
    `@coder`, `@lsp`, `@proc`, `@http`, `@knowledge`, `@memory` e muito mais.
  </Card>

  <Card title="7 padrões de qualidade" icon="sparkles">
    ReAct · Reflexion · CoVe · RAG+HyDE · Self-Refine…
  </Card>
</CardGroup>

Na prática, o terminal do dia a dia vira isto:

```console theme={"system"}
$ chatcli

› @git  gere a mensagem de commit a partir do diff staged
  ⮑  feat(api): adiciona paginação ao endpoint /users

› /agent  corrija o teste que está falhando em ./cli/plugins
  ⮑  plano: rodar testes → localizar a falha → editar → revalidar ✓

› @diagram gomod root=. output=~/arch.svg
  ⮑  Diagrama renderizado → ~/arch.svg (SVG, 245 KB)
```

<Tip>
  A **CLI é o produto principal** — funciona 100% local, sem precisar de servidor. O servidor e o operator são opcionais para cenários de equipe e Kubernetes. Todas as versões são publicadas automaticamente a cada release via GitHub Actions. Confira o histórico completo em [Releases](https://github.com/diillson/chatcli/releases) ou no [ArtifactHub](https://artifacthub.io/packages/search?ts_query_web=chatcli\&sort=relevance\&page=1).
</Tip>

***

## Arquitetura

O ChatCLI é distribuído em três artefatos que **funcionam isolados ou juntos**: a CLI local, o servidor gRPC e o operator Kubernetes. Você pode usar apenas a CLI no seu terminal, ou montar uma topologia completa com servidor + operator para equipes e ambientes de produção.

<Snippet file="architecture-diagram.mdx" />

***

## Versões atuais

<CardGroup cols={2}>
  <Card title="ChatCLI (Cliente)" icon="terminal" href="/pt/getting-started/installation">
    **1.152.0** — O binário que você instala e usa no seu terminal. Modo interativo, agente, coder, contexto inteligente e conexão remota a servidores. <br />
    `brew install chatcli` · `go install` · [binário](https://github.com/diillson/chatcli/releases)
  </Card>

  <Card title="Servidor gRPC" icon="server" href="/pt/features/server-mode">
    **1.152.0** — Deploy centralizado para equipes. Clientes conectam via `chatcli connect` e compartilham provedores LLM, sessões e plugins. <br />
    `ghcr.io/diillson/chatcli:1.152.0`
  </Card>

  <Card title="Operator AIOps" icon="dharmachakra" href="/pt/features/k8s-operator">
    **1.152.0** — Detecção autônoma de incidentes, análise com IA e remediação automática em clusters Kubernetes. 17 CRDs, 54+ ações. <br />
    `ghcr.io/diillson/chatcli-operator:1.152.0`
  </Card>

  <Card title="Helm Charts" icon="cube" href="/pt/features/artifacthub">
    **1.152.0** — Distribuídos via ArtifactHub e registro OCI no GHCR. <br />
    `oci://ghcr.io/diillson/charts/chatcli` <br />
    `oci://ghcr.io/diillson/charts/chatcli-operator`
  </Card>
</CardGroup>

***

## Início rápido

<Steps>
  <Step title="Instalar" icon="download">
    <Snippet file="pt/install-quickstart.mdx" />
  </Step>

  <Step title="Configurar um provedor" icon="key">
    <Snippet file="pt/configure-provider.mdx" />
  </Step>

  <Step title="Usar!" icon="rocket">
    ```bash theme={"system"}
    chatcli
    ```

    Pronto — você está conversando com um LLM no seu terminal, com acesso a todo o contexto do seu projeto.
  </Step>
</Steps>

***

## Destaques

Quatro pilares que definem o ChatCLI:

<CardGroup cols={2}>
  <Card title="Modo Agente" icon="robot" href="/pt/core-concepts/agent-mode" horizontal>
    Delegue tarefas com {'/agent'}: a IA planeja, executa com a sua aprovação e se auto-corrige — com segurança integrada contra ações perigosas.
  </Card>

  <Card title="Modo Coder" icon="code" href="/pt/core-concepts/coder-mode" horizontal>
    Engenharia de software com {'/coder'}: lê, edita, aplica patches e roda testes em loop com rollback automático.
  </Card>

  <Card title="Multi-provedor" icon="shuffle" href="/pt/reference/supported-models" horizontal>
    14 provedores e 200+ modelos — OpenAI, Claude, Gemini, Grok, Ollama… troque a qualquer momento, numa só interface.
  </Card>

  <Card title="Harness de Qualidade" icon="sparkles" href="/pt/features/quality/overview" horizontal>
    7 padrões de confiabilidade (ReAct, Reflexion, CoVe, RAG+HyDE, Self-Refine…) opt-in via `/config quality`.
  </Card>
</CardGroup>

E ainda, no mesmo binário:

<CardGroup cols={2}>
  <Card title="Tools Atômicos" icon="wand-magic-sparkles" href="/pt/features/atomic-tools">
    {'@read'}, {'@search'}, {'@tree'} narrow read-only + {'@todo'} (TodoWrite parity) + {'@coder multipatch'} transacional. Paridade arquitetural com Claude Code.
  </Card>

  <Card title="Contexto inteligente" icon="eye" href="/pt/core-concepts/context-commands">
    Injete contexto com {'@file'}, {'@git'}, {'@command'}, {'@env'} e {'@history'}. Seu ambiente direto no prompt da IA.
  </Card>

  <Card title="Multi-agent" icon="network-wired" href="/pt/features/multi-agent-orchestration">
    12 agents especialistas embarcados (File, Coder, Shell, Git, Search, Planner, Reviewer, Tester...) em paralelo.
  </Card>

  <Card title="Agentes customizáveis" icon="user-gear" href="/pt/features/customizable-agents">
    Crie personas com skills reutilizáveis em Markdown. Versionáveis no Git, compartilháveis entre equipes.
  </Card>

  <Card title="K8s Watcher e AIOps" icon="dharmachakra" href="/pt/features/k8s-watcher">
    Monitore workloads K8s em tempo real. Operator com 17 CRDs, 54+ ações de remediação, análise de logs e métricas.
  </Card>

  <Card title="Scheduler durável" icon="calendar" href="/pt/features/scheduler">
    Cron, wait-until, DAG e daemon mode. Jobs sobrevivem ao reiniciar a CLI. Agents agendam os próprios follow-ups.
  </Card>

  <Card title="ArtifactHub" icon="cube" href="/pt/features/artifacthub">
    Helm charts publicados no ArtifactHub com CI/CD automatizado, 17 CRDs documentadas e registro OCI.
  </Card>

  <Card title="Controle de conversa" icon="clock-rotate-left" href="/pt/features/conversation-control">
    {'/compact'} compacta o histórico preservando o essencial. {'/rewind'} e Esc+Esc voltam a qualquer ponto.
  </Card>

  <Card title="Hooks e Web Tools" icon="webhook" href="/pt/features/hooks-system">
    Hooks lifecycle (pre/post tool, session start/end), WebFetch e WebSearch nativos para enriquecer contexto.
  </Card>
</CardGroup>

***

## Problemas que o ChatCLI resolve

<CardGroup cols={2}>
  <Card title="Copiar e colar interminável" icon="copy">
    Chega de `cat arquivo.js`, selecionar, Ctrl+C, abrir o navegador, colar e digitar a pergunta. Use `@file` direto no terminal.
  </Card>

  <Card title="Commits genéricos" icon="code-commit">
    `@git` + uma pergunta = commit message perfeita baseada no diff real do seu código.
  </Card>

  <Card title="Análise de logs intimidante" icon="scroll">
    Pipe direto para a IA: `cat error.log | chatcli -p "causa raiz?"` — diagnóstico instantâneo.
  </Card>

  <Card title="Curva de aprendizagem" icon="graduation-cap">
    `@file ./src --mode smart` e pergunte: "como funciona o auth?" — onboarding em minutos.
  </Card>
</CardGroup>

***

## Para quem é o ChatCLI?

<CardGroup cols={2}>
  <Card title="Desenvolvedores" icon="laptop-code">
    Depurar código, entender codebases, gerar testes, refatorar e documentar — tudo sem sair do terminal.
  </Card>

  <Card title="DevOps / SREs" icon="gears">
    Analisar logs K8s, automatizar deploys, diagnosticar incidentes com IA e monitorar clusters.
  </Card>

  <Card title="Entusiastas de CLI" icon="terminal">
    Turbinar o terminal, criar aliases poderosos e explorar novas formas de interagir com IA.
  </Card>

  <Card title="DBAs / Eng. de Dados" icon="database">
    Automatizar tarefas repetitivas, analisar queries, gerenciar bancos e pipelines de dados.
  </Card>
</CardGroup>

***

## Próximos passos

<CardGroup cols={2}>
  <Card title="Guia de instalação completo" icon="download" href="/pt/getting-started/installation">
    Homebrew, binário, go install, código-fonte, Docker e OAuth.
  </Card>

  <Card title="Uso básico" icon="terminal" href="/pt/core-concepts/basic-usage">
    Comandos essenciais, modos e navegação no prompt interativo.
  </Card>

  <Card title="Cookbook" icon="kitchen-set" href="/pt/cookbook/agent-refactoring">
    Receitas práticas: refatoração com agente, debug de logs, monitoramento K8s, AIOps em produção.
  </Card>

  <Card title="API Reference" icon="code" href="/pt/reference/api/overview">
    Endpoints REST do servidor e operator: incidents, SLOs, runbooks, analytics, federation.
  </Card>
</CardGroup>

***

## Atualizações recentes

<Info>
  Aqui mostramos apenas as versões **major** e **minor**. Patches e hotfixes vão para o [GitHub Releases](https://github.com/diillson/chatcli/releases) — fonte de verdade do changelog completo.
</Info>

<Update label="1.151" description="2026-07-03">
  * **tools** — expose MCP tools through the @tools catalog
</Update>

<Update label="1.150" description="2026-07-02">
  * **agent** — defer the tool catalog — index plus on-demand @tools describe
  * **compress** — harden CCR reversibility and add runtime profiles
  * **http** — structured HTTP client for the agent as the @http tool
  * **lsp** — expose semantic code navigation to the agent as the @lsp tool
  * **proc** — background-process supervision for the agent as the @proc tool
  * **ctxmgr** — harden knowledge-mode durability, UTF-8 boundaries and retrieval cost
  * **lint** — zero both module baselines and enforce full-module linting
  * **memory** — eliminate silent memory-loss vectors and harden retrieval
</Update>

<Update label="1.149" description="2026-07-01">
  * **models** — Claude Sonnet 5 + GLM-5.2 + Bedrock Fable 5/Sonnet 5 support
</Update>

<Update label="1.148" description="2026-06-28">
  * **graphview** — interactive grap-style, graph in agent, coder and chat
</Update>

<Update label="1.147" description="2026-06-26">
  * live telemetry in agent/coder + on-demand CCR curation
</Update>

<Update label="1.146" description="2026-06-25">
  * self-evolution engine, in-core knowledge graph and memory quality
</Update>

<Update label="1.145" description="2026-06-22">
  * native context compression, image compression and output-token reduction
</Update>

<Update label="1.144" description="2026-06-21">
  * **plugins** — add @diagram builtin for embedded Graphviz rendering
  * **plugins** — add selectable system/embedded Graphviz backend to @diagram ([3ea68b5](https://github.com/diillson/chatcli/commit/3ea68b5f140db7b47e93ea5b9843e88f07ed3b53))
</Update>

<Update label="1.143" description="2026-06-18">
  * multimodal vision input + multi-provider image editing
</Update>

<Update label="1.142" description="2026-06-17">
  * **docs-flatten** — ingest code and infra repos into knowledge bases
  * **coder** — recover stdin after Ctrl+C at a security confirmation
</Update>

<Update label="1.141" description="2026-06-15">
  * full @context parity + @registry-tags sort/last
</Update>

<Update label="1.140" description="2026-06-14">
  * **context** — autonomous knowledge-base management via @context
  * **plugins** — add @registry-tags and @wikipedia builtins
</Update>

<Update label="1.139" description="2026-06-13">
  * **transcription** — pure-Go OGG/Opus decoding and actionable ffmpeg guidance
</Update>

<Update label="1.138" description="2026-06-12">
  * **plugins** — bring @docs-flatten in as a builtin tool
</Update>

<Update label="1.137" description="2026-06-11">
  * **tls** — global corporate TLS trust overrides for all outbound clients
</Update>

<Update label="1.136" description="2026-06-10">
  * **context** — [knowledge mode](/pt/features/knowledge-base): index-card attach + keyless hybrid retrieval (BM25 + embeddings) + @knowledge pull tool (agent/coder/chat)
  * **i18n** — stop x/text from stamping MISSING into argless lookups
</Update>

<Update label="1.135" description="2026-06-10">
  * **transcription** — embedded offline Whisper STT via sherpa-onnx
</Update>

<Update label="1.134" description="2026-06-09">
  * **webfetch** — render JS pages via headless browser escalation
  * **websearch** — keyless fallback providers + Claude Fable 5 in catalog
  * **embedding** — rebuild embedding provider on /reload
  * **operator** — resolve all 82 open gosec findings
</Update>

<Update label="1.133" description="2026-06-09">
  * **context** — semantic passage retrieval for /context attach
  * **memory** — blend cosine, lexical and temporal signals in retrieval ranking
</Update>

<Update label="1.132" description="2026-06-06">
  * **gateway** — voice replies, embedded TTS and memory resilience
</Update>

<Update label="1.131" description="2026-06-06">
  * **imagegen** — Z.AI + MiniMax image backends, model-aware auto, and /model-image
</Update>

<Update label="1.130" description="2026-06-04">
  * proactive messaging, productivity skills pack, and multimodal agent tools
</Update>

<Update label="1.129" description="2026-06-03">
  * **gateway** — voice messages (transcription) + conversational replies
</Update>

<Update label="1.128" description="2026-06-01">
  * add interactive ask\_user tool for agent, coder and chat
</Update>

<Update label="1.127" description="2026-05-31">
  * **cli** — interactive command palette overlay
</Update>

<Update label="1.126" description="2026-05-30">
  * **cli** — gateway runtime model, /model + /max-tokens, 9 new themes
  * **gateway** — list stop in the /gateway usage hint
</Update>

<Update label="1.125" description="2026-05-29">
  * **ui** — unified color theme system + indentation-safe rendering
</Update>

<Update label="1.124" description="2026-05-29">
  * **catalog** — add Claude Opus 4.8 with adaptive thinking and fast mode
</Update>

<Update label="1.123" description="2026-05-27">
  * **gateway** — messaging gateway — Telegram, Slack, Discord, WhatsApp, Webhook
  * **hub** — cross-channel conversation continuity via shared hub
  * **lsp** — language server diagnostics via /lsp
  * memory hybrid capture, security & multi-provider robustness (Tiers A+B+partial C)
  * **rpcserve** — MCP server + ACP agent over stdio
</Update>

<Update label="1.122" description="2026-05-23">
  * **aiops** — close 5 gaps surfaced by 2026-05-23 chaos test
</Update>

<Update label="1.121" description="2026-05-23">
  * **auth** — TokenProvider with proactive OAuth refresh and retry-on-401
</Update>

<Update label="1.120" description="2026-05-21">
  * **mcp** — complete channel push delivery, reactive triggers and persistence
</Update>

<Update label="1.119" description="2026-05-20">
  * **ui** — cross-mode UI polish — i18n, red errors, lipgloss cards, unified banners
</Update>

<Update label="1.118" description="2026-05-17">
  * Claude Code parity tool layer (atomic tools, @todo, multipatch, schema validation, per-tool policies)
  * tool layer enterprise refactor (security UX + parallel orchestration + provider-agnostic tool\_result)
</Update>

<Update label="1.117" description="2026-05-15">
  * **mcp** — add Streamable HTTP transport (MCP 2025-03-26)
</Update>

<Update label="1.116" description="2026-05-15">
  * **moonshot** — add Moonshot (Kimi) provider with thinking-mode support
  * **qg** — 15-floor Quality Gate overhaul — fix Floor 3, add 6 floors, redesign table
</Update>

<Update label="1.115" description="2026-05-12">
  * **mcp** — tier 1-3 server config extensions + autoApprove audit
</Update>

<Update label="1.114" description="2026-05-11">
  * **skills** — session-scoped pin for multi-turn auto-injection
</Update>

<Update label="1.113" description="2026-05-08">
  * **mcp** — per-server commands + logs ring + manual reload
  * **coder** — use go-prompt for iteration input (paste + full width)
  * **mcp** — inherit parent env, expand \${VAR}, and hot-reload from empty state
</Update>

<Update label="1.112" description="2026-05-05">
  * **Agent Park & Resume** — tool `@park` que suspende o agent loop, libera o terminal e auto-retoma sozinho quando timer/probe completa. Quatro modos: `delay`, `until`, `for_url`, `for_cmd`. Ver [Agent Park & Resume](/pt/features/agent-park).
  * **Auto-resume foreground** — TIOCSTI no Unix e `WriteConsoleInputW` no Windows injetam `/resume <token>` na TTY automaticamente; fallback transparente quando o kernel restringe (Linux 6.x+, macOS Ventura+).
  * **Slash commands de gerenciamento** — `/parked` (lista), `/resume <token>`, `/cancel-park <token>` com prefix-match e idempotência contra race do auto-resume.
  * **Operator SchemeBuilder migration** — controller-runtime 0.24 depreciou `sigs.k8s.io/controller-runtime/pkg/scheme.Builder`; migrado para `runtime.NewSchemeBuilder` do apimachinery (–43 linhas líquidas).
</Update>

<Update label="1.111" description="2026-04-30">
  * **Scheduler (Chronos)** — cron, wait-until, DAG e daemon mode com WAL durável
  * **Bedrock provider** — Claude/Llama/Nova via AWS Bedrock com IAM/profile/credentials chain
  * **Token waste audit** — cache em agent mode, tool defs cacheadas, early-exit/routing
  * **Anthropic cache coalescer** — planner local respeitando cap de 4 markers sem perder cache
  * **/config sections** — virou hierárquico (`/config <section>`) com mutação runtime
</Update>

<Update label="1.110" description="2026-04-15">
  * **MCP client + hooks + web tools** — paridade com Claude Code
  * **Cost tracking** com tabelas de preço por provedor
  * **Plan mode** + **worktrees** integrados
</Update>

<Update label="1.109" description="2026-03-29">
  * **Harness/Pipeline de Qualidade (7 padrões)** — ReAct + Plan-and-Solve + Reflexion + RAG+HyDE + Self-Refine + CoVe + Reasoning Backbone
  * **Context injection** via system prompt com cache Anthropic
  * **TUI Bubble Tea** padrão (go-prompt removido)
</Update>

<Note>
  Acompanhe todas as releases em [GitHub Releases](https://github.com/diillson/chatcli/releases) ou no [ArtifactHub](https://artifacthub.io/packages/search?ts_query_web=chatcli).
</Note>