> ## 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

> The CLI that brings the power of LLMs to your terminal. Multi-provider, agent mode, coder mode, K8s watcher, and much more.

**Your terminal becomes an AI engineer.** **ChatCLI** brings the leading large language models (LLMs) straight into your shell — it understands your project's context, edits code, runs commands and automates complex tasks, without you ever leaving the command line. A single **Go** binary: fast, portable and self-contained.

<Frame caption="ChatCLI in action — interactive mode with context and agent mode">
  <img src="https://mintcdn.com/encom/jXe34OctYqDbxuDm/images/chatcli-demo.gif?s=9e1e37199807ada6c61d9fd78bda0cf8" alt="ChatCLI Demo" width="852" height="480" data-path="images/chatcli-demo.gif" />
</Frame>

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

<CardGroup cols={4}>
  <Card title="15 providers" icon="shuffle">
    OpenAI, Claude, Gemini, Grok, Ollama and more — in a single interface.
  </Card>

  <Card title="350+ models" icon="layer-group">
    One unified catalog. Switch model at any time.
  </Card>

  <Card title="37+ native tools" icon="wand-magic-sparkles">
    `@coder`, `@lsp`, `@proc`, `@http`, `@api-explorer`, `@knowledge`, `@memory` and many more.
  </Card>

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

In practice, your everyday terminal turns into this:

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

› @git  write the commit message from the staged diff
  ⮑  feat(api): add pagination to the /users endpoint

› /agent  fix the failing test in ./cli/plugins
  ⮑  plan: run tests → locate the failure → edit → re-verify ✓

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

<Tip>
  The **CLI is the main product** — it works 100% locally, no server required. The server and operator are optional for team and Kubernetes scenarios. All versions are published automatically on every release via GitHub Actions. Check the full history on [Releases](https://github.com/diillson/chatcli/releases) or [ArtifactHub](https://artifacthub.io/packages/search?repo=chatcli).
</Tip>

***

## Architecture

ChatCLI ships as three artifacts that **work standalone or together**: the local CLI, the gRPC server, and the Kubernetes operator. Use just the CLI on your terminal, or set up a full topology with server + operator for teams and production environments.

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

***

## Current versions

<CardGroup cols={2}>
  <Card title="ChatCLI (Client)" icon="terminal" href="/getting-started/installation">
    **1.172.0** — The binary you install and use in your terminal. Interactive mode, agent, coder, smart context, and remote server connection. <br />
    `brew install chatcli` · `go install` · [binary](https://github.com/diillson/chatcli/releases)
  </Card>

  <Card title="gRPC Server" icon="server" href="/features/server-mode">
    **1.172.0** — Centralized deployment for teams. Clients connect via `chatcli connect` and share LLM providers, sessions, and plugins. <br />
    `ghcr.io/diillson/chatcli:1.172.0`
  </Card>

  <Card title="AIOps Operator" icon="dharmachakra" href="/features/k8s-operator">
    **1.172.0** — Autonomous incident detection, AI-powered analysis, and automated remediation for Kubernetes clusters. 17 CRDs, 54+ actions. <br />
    `ghcr.io/diillson/chatcli-operator:1.172.0`
  </Card>

  <Card title="Helm Charts" icon="cube" href="/features/artifacthub">
    **1.172.0** — Distributed via ArtifactHub and OCI registry on GHCR. <br />
    `oci://ghcr.io/diillson/charts/chatcli` <br />
    `oci://ghcr.io/diillson/charts/chatcli-operator`
  </Card>
</CardGroup>

***

## Quick start

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

  <Step title="Configure a provider" icon="key">
    <Snippet file="en/configure-provider.mdx" />
  </Step>

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

    Done — you're chatting with an LLM in your terminal, with full access to your project context.
  </Step>
</Steps>

***

## Highlights

Four pillars that define ChatCLI:

<CardGroup cols={2}>
  <Card title="Agent Mode" icon="robot" href="/core-concepts/agent-mode" horizontal>
    Delegate tasks with {'/agent'}: the AI plans, executes with your approval and self-corrects — with built-in safety against dangerous actions.
  </Card>

  <Card title="Coder Mode" icon="code" href="/core-concepts/coder-mode" horizontal>
    Software engineering with {'/coder'}: reads, edits, applies patches and runs tests in a loop with automatic rollback.
  </Card>

  <Card title="Multi-provider" icon="shuffle" href="/reference/supported-models" horizontal>
    15 providers and 350+ models — OpenAI, Claude, Gemini, Grok, Ollama… switch at any time, from a single interface.
  </Card>

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

And, in the same binary:

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

  <Card title="Smart Context" icon="eye" href="/core-concepts/context-commands">
    Inject context with {'@file'}, {'@git'}, {'@command'}, {'@env'}, and {'@history'}. Your environment straight into the AI prompt.
  </Card>

  <Card title="Multi-Agent" icon="network-wired" href="/features/multi-agent-orchestration">
    14 built-in specialist agents (File, Coder, Shell, Git, Search, Planner, Reviewer, Tester...) in parallel.
  </Card>

  <Card title="Customizable Agents" icon="user-gear" href="/features/customizable-agents">
    Create personas with reusable skills in Markdown. Version-controlled with Git, shareable across teams.
  </Card>

  <Card title="K8s Watcher and AIOps" icon="dharmachakra" href="/features/k8s-watcher">
    Monitor K8s workloads in real time. Operator with 17 CRDs, 54+ remediation actions, log analysis, and metrics.
  </Card>

  <Card title="Durable Scheduler" icon="calendar" href="/features/scheduler">
    Cron, wait-until, DAG, and daemon mode. Jobs survive CLI restarts. Agents schedule their own follow-ups.
  </Card>

  <Card title="ArtifactHub" icon="cube" href="/features/artifacthub">
    Helm charts published to ArtifactHub with automated CI/CD, 17 documented CRDs, and OCI registry.
  </Card>

  <Card title="Conversation Control" icon="clock-rotate-left" href="/features/conversation-control">
    {'/compact'} compacts history preserving what matters. {'/rewind'} and Esc+Esc go back to any point.
  </Card>

  <Card title="Hooks and Web Tools" icon="webhook" href="/features/hooks-system">
    Lifecycle hooks (pre/post tool, session start/end), native WebFetch and WebSearch to enrich context.
  </Card>
</CardGroup>

***

## Problems ChatCLI solves

<CardGroup cols={2}>
  <Card title="Endless copy and paste" icon="copy">
    No more `cat file.js`, selecting text, Ctrl+C, opening the browser, pasting, and typing your question. Use `@file` directly in the terminal.
  </Card>

  <Card title="Generic commits" icon="code-commit">
    `@git` + a question = perfect commit message based on the actual diff of your code.
  </Card>

  <Card title="Intimidating log analysis" icon="scroll">
    Pipe directly to the AI: `cat error.log | chatcli -p "root cause?"` — instant diagnosis.
  </Card>

  <Card title="Learning curve" icon="graduation-cap">
    `@file ./src --mode smart` and ask: "how does auth work?" — onboarding in minutes.
  </Card>
</CardGroup>

***

## Who is ChatCLI for?

<CardGroup cols={2}>
  <Card title="Developers" icon="laptop-code">
    Debug code, understand codebases, generate tests, refactor, and document — all without leaving the terminal.
  </Card>

  <Card title="DevOps / SREs" icon="gears">
    Analyze K8s logs, automate deploys, diagnose incidents with AI, and monitor clusters.
  </Card>

  <Card title="CLI Enthusiasts" icon="terminal">
    Supercharge your terminal, create powerful aliases, and explore new ways to interact with AI.
  </Card>

  <Card title="DBAs / Data Engineers" icon="database">
    Automate repetitive tasks, analyze queries, manage databases, and data pipelines.
  </Card>
</CardGroup>

***

## Next steps

<CardGroup cols={2}>
  <Card title="Full installation guide" icon="download" href="/getting-started/installation">
    Homebrew, binary, go install, from source, Docker, and OAuth.
  </Card>

  <Card title="Basic usage" icon="terminal" href="/core-concepts/basic-usage">
    Essential commands, modes, and navigation in the interactive prompt.
  </Card>

  <Card title="Cookbook" icon="kitchen-set" href="/cookbook/agent-refactoring">
    Practical recipes: agent refactoring, log debugging, K8s monitoring, AIOps in production.
  </Card>

  <Card title="API Reference" icon="code" href="/reference/api/overview">
    REST endpoints for the server and operator: incidents, SLOs, runbooks, analytics, federation.
  </Card>
</CardGroup>

***

## Recent updates

<Info>
  We only highlight **major** and **minor** versions here. Patches and hotfixes ship to [GitHub Releases](https://github.com/diillson/chatcli/releases) — the source of truth for the full changelog.
</Info>

<Update label="1.172" description="2026-07-28">
  * **update** — announce new releases in-session and revamp version UX
</Update>

<Update label="1.171" description="2026-07-27">
  * **providers** — list all gateway models when endpoint URL is customized
</Update>

<Update label="1.170" description="2026-07-24">
  * **models** — add Claude Opus 5 to the Anthropic, Bedrock and OpenRouter catalogs
  * **update** — channel-aware auto-update with /update command and staged background mode
</Update>

<Update label="1.169" description="2026-07-21">
  * **bedrock** — BEDROCK\_MODEL selects the default model
</Update>

<Update label="1.168" description="2026-07-21">
  * **bedrock** — custom endpoint overrides for corporate DNS and VPC
</Update>

<Update label="1.167" description="2026-07-20">
  * **session** — proactive cross-session recall with tolerant search and titles
</Update>

<Update label="1.166" description="2026-07-19">
  * **park** — capture user messages typed while parked as resume directives
</Update>

<Update label="1.165" description="2026-07-17">
  * **session** — MCP session autosave by default and bounded machine-session lifecycle
</Update>

<Update label="1.164" description="2026-07-17">
  * **memory** — derive rollups from the episodic record
  * **memory** — episodic timeline with temporal recall
  * **memory** — proactive auto-recall in index mode
  * **session** — sessions become retrievable memory
  * **devin** — drop identity coercion and accept tool tag alias
</Update>

<Update label="1.163" description="2026-07-16">
  * **mcp-server** — full ChatCLI experience parity over MCP
</Update>

<Update label="1.162" description="2026-07-14">
  * **agent** — @model tool — AI-driven model/provider routing with tiered catalog and delegate
</Update>

<Update label="1.161" description="2026-07-13">
  * **mcp** — re-export connected MCP servers' tools on the mcp-server surface
</Update>

<Update label="1.160" description="2026-07-12">
  * **ui** — add ui/kit presentation components and fix help header styling
  * **ui** — adopt the sóbrio borderless treatment across chat, agent and coder
  * **ui** — align command surfaces on kit padding, rules and notices
  * **ui** — make the welcome screen responsive and theme-aware
  * **ui** — sweep agent timeline glyphs and rules onto the kit vocabulary
  * **cli** — restore spinner, type-ahead queue and AltGr input in the Windows chat REPL
  * **i18n** — honor CHATCLI\_LANG from .env and detect the Windows locale
  * **i18n** — sentence-case display titles and notice-based session status
  * **i18n** — strip variation selectors and embedded rules from the catalogs
  * **ui** — give warnings their own theme role
</Update>

<Update label="1.159" description="2026-07-11">
  * **mcp** — OAuth 2.1 authorization for remote MCP servers
</Update>

<Update label="1.158" description="2026-07-10">
  * DEVIN provider — local Devin CLI as LLM transport
  * full MCP + ACP server surface — every tool, harness routing, skills as prompts
  * **embedding** — circuit-break Bedrock credential failures instead of hammering AWS
</Update>

<Update label="1.157" description="2026-07-10">
  * GPT-5.6 family (Sol/Terra/Luna) + Codex client headers fix
</Update>

<Update label="1.156" description="2026-07-10">
  * **mcp** — dynamic tool discovery on tools/list\_changed notifications
</Update>

<Update label="1.155" description="2026-07-09">
  * **agent** — adaptive payload-cap recovery, bounded prompt floor and zero-loss compaction ([48f3c0c](https://github.com/diillson/chatcli/commit/48f3c0c54a401dc8d292d72883a6c7fe024921d9))
  * **plugins** — tolerate the CCR key syntax variants models actually produce ([8ebe661](https://github.com/diillson/chatcli/commit/8ebe661e923552ca2d63a06da526ff7cbb21b437))
</Update>

<Update label="1.154" description="2026-07-08">
  * add @api-explorer builtin for end-to-end API reconnaissance ([cc99eab](https://github.com/diillson/chatcli/commit/cc99eabc6ad72094fca0737d248c4a7fafed9ae5))
</Update>

<Update label="1.153" description="2026-07-07">
  * **skills** — match multi-word triggers in any word order
  * **skills** — re-activate skills mid-loop in agent and coder modes
</Update>

<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](/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** — `@park` tool that suspends the agent loop, frees the terminal, and auto-resumes itself when the timer/probe completes. Four modes: `delay`, `until`, `for_url`, `for_cmd` — plus `/park-note` and `@park list`/`note` to send directives to a parked agent, delivered at resume. See [Agent Park & Resume](/features/agent-park).
  * **Foreground auto-resume** — TIOCSTI on Unix and `WriteConsoleInputW` on Windows automatically inject `/resume <token>` into the TTY; transparent fallback when the kernel restricts it (Linux 6.x+, macOS Ventura+).
  * **Management slash commands** — `/parked` (list), `/resume <token>`, `/cancel-park <token>` with prefix-match and idempotency against the auto-resume race.
  * **Operator SchemeBuilder migration** — controller-runtime 0.24 deprecated `sigs.k8s.io/controller-runtime/pkg/scheme.Builder`; migrated to apimachinery's `runtime.NewSchemeBuilder` (–43 net lines).
</Update>

<Update label="1.111" description="2026-04-30">
  * **Scheduler (Chronos)** — cron, wait-until, DAG, and daemon mode with durable WAL
  * **Bedrock provider** — Claude/Llama/Nova via AWS Bedrock with IAM/profile/credentials chain
  * **Token waste audit** — cache in agent mode, cached tool defs, early-exit/routing
  * **Anthropic cache coalescer** — local planner respecting the 4-marker cap without losing cache
  * **/config sections** — became hierarchical (`/config <section>`) with runtime mutation
</Update>

<Update label="1.110" description="2026-04-15">
  * **MCP client + hooks + web tools** — parity with Claude Code
  * **Cost tracking** with per-provider price tables
  * **Plan mode** + **worktrees** integrated
</Update>

<Update label="1.109" description="2026-03-29">
  * **Harness/Quality Pipeline (7 patterns)** — ReAct + Plan-and-Solve + Reflexion + RAG+HyDE + Self-Refine + CoVe + Reasoning Backbone
  * **Context injection** via system prompt with Anthropic caching
  * **Bubble Tea TUI** as default (go-prompt removed)
</Update>

<Note>
  Track all releases on [GitHub Releases](https://github.com/diillson/chatcli/releases) or [ArtifactHub](https://artifacthub.io/packages/search?ts_query_web=chatcli).
</Note>