> ## 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.

ChatCLI

**Your terminal becomes an AI engineer.**\
Fourteen providers, coder mode, agents, a gRPC server and a Kubernetes operator: one Go binary.

[New releasev1.226.0read one sealed file in plaintext with /config security revealRead release notes →](https://chatcli.edilsonfreitas.com/releases/1.226.0.md)

> **[Quickstart](https://chatcli.edilsonfreitas.com/start/quickstart.md)**
>
> Install ChatCLI, connect a provider and chat in under five minutes.

> **[Coder mode](https://chatcli.edilsonfreitas.com/usage/coder-mode.md)**
>
> /coder reads, edits, runs tests and rolls back, in a loop you approve.

> **[Agents and harness](https://chatcli.edilsonfreitas.com/agents/harness/overview.md)**
>
> Multi-agent squads, task graphs and seven reliability patterns.

> **[Server and Kubernetes](https://chatcli.edilsonfreitas.com/server/server-mode.md)**
>
> Share providers with a team over gRPC and run AIOps in your clusters.

## Quick start

**1. Install ChatCLI**

**Homebrew**

```bash theme={"system"}
brew tap diillson/chatcli && brew install chatcli
```

**go install**

```bash theme={"system"}
go install github.com/diillson/chatcli@latest
```

**Docker**

```bash theme={"system"}
docker pull ghcr.io/diillson/chatcli:latest
```

**Binary**

Download the binary for your platform from [Releases](https://github.com/diillson/chatcli/releases), then:

```bash theme={"system"}
chmod +x chatcli && sudo mv chatcli /usr/local/bin/
```

Every install path, including Helm, building from source and OAuth logins, is on the [Installation](https://chatcli.edilsonfreitas.com/start/installation.md) page.

**2. Configure a provider**

```bash OpenAI theme={"system"}
echo 'LLM_PROVIDER=OPENAI' > .env
echo 'OPENAI_API_KEY=sk-xxx' >> .env
```

```bash Claude theme={"system"}
echo 'LLM_PROVIDER=CLAUDEAI' > .env
echo 'ANTHROPIC_API_KEY=sk-ant-xxx' >> .env
```

```bash Gemini theme={"system"}
echo 'LLM_PROVIDER=GOOGLEAI' > .env
echo 'GOOGLEAI_API_KEY=AIza...' >> .env
```

```bash Ollama (local) theme={"system"}
echo 'LLM_PROVIDER=OLLAMA' > .env
echo 'OLLAMA_BASE_URL=http://localhost:11434' >> .env
echo 'OLLAMA_MODEL=llama3.1' >> .env
```

```bash OpenRouter theme={"system"}
echo 'LLM_PROVIDER=OPENROUTER' > .env
echo 'OPENROUTER_API_KEY=sk-or-xxx' >> .env
```

Each provider has a default model; set `<PROVIDER>_MODEL` to pick another, or use `/switch` at runtime. Have a ChatGPT, Claude or Copilot plan? Skip the key and run `/auth login <provider>` inside ChatCLI. All fourteen providers are in [Supported models](https://chatcli.edilsonfreitas.com/providers/supported-models.md).

**3. Start chatting**

```bash theme={"system"}
chatcli
```

You are talking to an LLM in your terminal, with your project's context one `@` away. Next, try [coder mode](https://chatcli.edilsonfreitas.com/usage/coder-mode.md).

## Connect a channel

Use ChatCLI from your chat app. Every message runs the full agent, with its tools and your memory.

[Telegram](https://chatcli.edilsonfreitas.com/gateway/telegram.md)
[Slack](https://chatcli.edilsonfreitas.com/gateway/slack.md)
[Discord](https://chatcli.edilsonfreitas.com/gateway/discord.md)
[WhatsApp](https://chatcli.edilsonfreitas.com/gateway/whatsapp.md)
[Webhook](https://chatcli.edilsonfreitas.com/gateway/webhook.md)
[How the gateway works](https://chatcli.edilsonfreitas.com/gateway/chat-gateway.md)

## See it in action

<video autoPlay muted loop playsInline poster="/images/chatcli-demo-poster.png" src="https://mintcdn.com/encom/SkUk0bLygre3bS6k/images/chatcli-demo.mp4?fit=max&auto=format&n=SkUk0bLygre3bS6k&q=85&s=a1aa3ffb17e8894d1771bf637c60e2f4" aria-label="ChatCLI coder mode fixing a failing Go test end to end" />

One prompt, real work: /coder runs the failing tests, reads the code, patches the bug and re-runs go test uncached to prove the fix — live, on Claude Sonnet 5.5

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)
```

## Memory, measured

On **LongMemEval-S** — 500 questions, each over about 115k tokens of past conversations — chatcli answered **95.0%** of the 260 questions never read while tuning it, and **95.8%** of all 500, by searching its own saved sessions. Its search surfaced the evidence in 470 of 470 answerable questions.

> **[See the full LongMemEval results](https://chatcli.edilsonfreitas.com/context/longmemeval.md)**
>
> The method, every number, where it fails, what it changed in chatcli, and the data to rerun it.

## Browse the docs

> **[Get started](https://chatcli.edilsonfreitas.com/start/quickstart.md)**
>
> Quickstart, installation, Docker and Kubernetes, updates.

> **[Using ChatCLI](https://chatcli.edilsonfreitas.com/usage/basic-usage.md)**
>
> The prompt, `@` context, agent and coder modes, one-shot runs.

> **[Coder](https://chatcli.edilsonfreitas.com/coder/coder-plugin.md)**
>
> The `@coder` tool, atomic tools, permissions, worktrees, LSP.

> **[Agents](https://chatcli.edilsonfreitas.com/agents/multi-agent-orchestration.md)**
>
> Multi-agent, squads, task graphs, personas and the quality harness.

> **[Context & memory](https://chatcli.edilsonfreitas.com/context/persistent-context.md)**
>
> Persistent context, knowledge bases, memory as a linked graph of notes with an Obsidian vault, sessions, token efficiency.

> **[Models & providers](https://chatcli.edilsonfreitas.com/providers/supported-models.md)**
>
> Fourteen providers, OAuth, Bedrock, fallback, rate limits and cost.

> **[Tools](https://chatcli.edilsonfreitas.com/tools/web-tools.md)**
>
> Web search, browser, API explorer, Git forges, images, diagrams, scheduler.

> **[Extensions](https://chatcli.edilsonfreitas.com/extensions/plugin-system.md)**
>
> Plugins, MCP servers, skills, slash commands and hooks.

> **[Channels & gateway](https://chatcli.edilsonfreitas.com/gateway/chat-gateway.md)**
>
> ChatCLI on Telegram, Slack, Discord and WhatsApp, with voice replies.

> **[Server & IDE](https://chatcli.edilsonfreitas.com/server/server-mode.md)**
>
> The gRPC server, remote connections, MCP server and ACP for editors.

> **[Kubernetes & AIOps](https://chatcli.edilsonfreitas.com/kubernetes/k8s-operator.md)**
>
> K8s watcher, the AIOps operator, incidents, SLOs and remediation.

> **[Security](https://chatcli.edilsonfreitas.com/security/overview.md)**
>
> Enterprise security controls and dependency vulnerability scans.

> **[Cookbook](https://chatcli.edilsonfreitas.com/cookbook/agent-refactoring.md)**
>
> Step-by-step recipes for refactoring, debugging, pipelines and AIOps.

> **[Reference](https://chatcli.edilsonfreitas.com/reference/command-reference.md)**
>
> Commands, environment variables, configuration and the REST API.

> **[Releases](https://chatcli.edilsonfreitas.com/releases.md)**
>
> Release notes for every version, with links to the changes.

## What is ChatCLI?

**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.

> **14 providers**
>
> OpenAI, Claude, Gemini, Grok, Ollama and more — in a single interface.

> **350+ models**
>
> One unified catalog. Switch model at any time.

> **37+ native tools**
>
> `@coder`, `@lsp`, `@proc`, `@http`, `@api-explorer`, `@knowledge`, `@memory` and many more.

> **7 quality patterns**
>
> ReAct · Reflexion · CoVe · RAG+HyDE · Self-Refine…

> [!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://chatcli.edilsonfreitas.com/releases.md) or [ArtifactHub](https://artifacthub.io/packages/search?repo=chatcli).

**Who is it for?**

* **Developers**: debug code, understand codebases, generate tests, refactor and document, all without leaving the terminal.
* **DevOps and SREs**: analyze K8s logs, automate deploys, diagnose incidents with AI and monitor clusters.
* **CLI enthusiasts**: supercharge your terminal, create powerful aliases and explore new ways to work with AI.
* **DBAs and data engineers**: automate repetitive tasks, analyze queries, manage databases and data pipelines.

**What does it replace?**

* **Endless copy and paste**: no more `cat file.js`, selecting, copying, opening the browser and pasting. Use `@file` right in the terminal.
* **Generic commits**: `@git` plus a question gives a commit message based on the actual diff.
* **Intimidating log analysis**: pipe straight to the AI with `cat error.log | chatcli -p "root cause?"`.
* **A steep learning curve**: `@file ./src --mode smart` and ask "how does auth work?", and onboarding takes minutes.

## How it works

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.

```mermaid theme={"system"}
flowchart LR
  subgraph Local["💻 Local"]
    CLI["ChatCLI<br/>(binary)"]
  end
  subgraph Cloud["☁️ Server / Operator"]
    SRV["ChatCLI Server<br/>(gRPC)"]
    OP["ChatCLI Operator<br/>(K8s + 17 CRDs)"]
  end
  subgraph Providers["🤖 LLM providers"]
    OAI["OpenAI"]
    ANT["Claude"]
    GEM["Gemini"]
    OLL["Ollama"]
    OTH["+ 10 providers"]
  end
  subgraph K8s["🚢 Kubernetes"]
    APP["Workloads"]
    PROM["Prometheus"]
  end

  CLI -->|chatcli connect| SRV
  CLI -.->|direct| Providers
  SRV --> Providers
  OP -->|watch| APP
  OP -->|metrics| PROM
  OP -->|AI analysis| Providers
  OP -.->|alert + remediation| APP
```

## Key capabilities

> **[Agent mode](https://chatcli.edilsonfreitas.com/usage/agent-mode.md)**
>
> Delegate tasks with /agent: the AI plans, executes with your approval and self-corrects, with built-in safety against dangerous actions.

> **[Coder mode](https://chatcli.edilsonfreitas.com/usage/coder-mode.md)**
>
> Software engineering with /coder: reads, edits, applies patches and runs tests in a loop with automatic rollback.

> **[Quality harness](https://chatcli.edilsonfreitas.com/agents/harness/overview.md)**
>
> 7 reliability patterns (ReAct, Reflexion, CoVe, RAG+HyDE, Self-Refine…) opt-in via `/config quality`.

> **[Atomic tools](https://chatcli.edilsonfreitas.com/coder/atomic-tools.md)**
>
> @read, @search, @tree narrow read-only + @todo (TodoWrite parity) + @coder multipatch transactional. Architectural parity with Claude Code.

> **[Smart context](https://chatcli.edilsonfreitas.com/usage/context-commands.md)**
>
> Inject context with @file, @git, @command, @env, and @history. Your environment straight into the AI prompt.

> **[Multiagente](https://chatcli.edilsonfreitas.com/agents/multi-agent-orchestration.md)**
>
> 14 built-in specialist agents (File, Coder, Shell, Git, Search, Planner, Reviewer, Tester...) in parallel.

> **[Agent squad](https://chatcli.edilsonfreitas.com/agents/agent-squad.md)**
>
> Live run observability, shared kanban board, agent-to-agent mail, and an autonomous plan → develop → review → deliver playbook.

> **[Customizable agents](https://chatcli.edilsonfreitas.com/agents/customizable-agents.md)**
>
> Create personas with reusable skills in Markdown. Version-controlled with Git, shareable across teams.

> **[K8s watcher and AIOps](https://chatcli.edilsonfreitas.com/kubernetes/k8s-watcher.md)**
>
> Monitor K8s workloads in real time. Operator with 17 CRDs, 54+ remediation actions, log analysis, and metrics.

> **[Durable scheduler](https://chatcli.edilsonfreitas.com/tools/scheduler.md)**
>
> Cron, wait-until, DAG, and daemon mode. Jobs survive CLI restarts. Agents schedule their own follow-ups.

> **[Conversation control](https://chatcli.edilsonfreitas.com/usage/conversation-control.md)**
>
> /compact compacts history preserving what matters. /rewind and Esc+Esc go back to any point.

> **[Hooks and web tools](https://chatcli.edilsonfreitas.com/extensions/hooks-system.md)**
>
> Lifecycle hooks (pre/post tool, session start/end), native WebFetch and WebSearch to enrich context.

## Current versions

> **[ChatCLI (client)](https://chatcli.edilsonfreitas.com/start/installation.md)**
>
> **1.226.0** — The binary you install and use in your terminal. Interactive mode, agent, coder, smart context, and remote server connection. \\
>
> `brew install chatcli` · `go install` · [binary](https://github.com/diillson/chatcli/releases)

> **[gRPC server](https://chatcli.edilsonfreitas.com/server/server-mode.md)**
>
> **1.226.0** — Centralized deployment for teams. Clients connect via `chatcli connect` and share LLM providers, sessions, and plugins. \\
>
> `ghcr.io/diillson/chatcli:1.226.0`

> **[AIOps operator](https://chatcli.edilsonfreitas.com/kubernetes/k8s-operator.md)**
>
> **1.226.0** — Autonomous incident detection, AI-powered analysis, and automated remediation for Kubernetes clusters. 17 CRDs, 54+ actions. \\
>
> `ghcr.io/diillson/chatcli-operator:1.226.0`

> **[Helm charts](https://chatcli.edilsonfreitas.com/kubernetes/artifacthub.md)**
>
> **1.226.0** — Distributed via ArtifactHub and OCI registry on GHCR. \\
>
> `oci://ghcr.io/diillson/charts/chatcli` \\
>
> `oci://ghcr.io/diillson/charts/chatcli-operator`


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.