Skip to main content
ChatCLI is a command-line interface that integrates the leading large language models (LLMs) directly into your terminal. Built in Go, it is fast, portable, and transforms your shell into an intelligent development assistant β€” capable of understanding context, executing commands, editing code, and automating complex tasks.
ChatCLI Demo
The CLI is the main product β€” 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 or ArtifactHub.

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.

Current versions

ChatCLI (Client)

1.139.0 β€” The binary you install and use in your terminal. Interactive mode, agent, coder, smart context, and remote server connection.
brew install chatcli Β· go install Β· binary

gRPC Server

1.139.0 β€” Centralized deployment for teams. Clients connect via chatcli connect and share LLM providers, sessions, and plugins.
ghcr.io/diillson/chatcli:1.139.0

AIOps Operator

1.139.0 β€” Autonomous incident detection, AI-powered analysis, and automated remediation for Kubernetes clusters. 17 CRDs, 54+ actions.
ghcr.io/diillson/chatcli-operator:1.139.0

Helm Charts

1.139.0 β€” Distributed via ArtifactHub and OCI registry on GHCR.
oci://ghcr.io/diillson/charts/chatcli
oci://ghcr.io/diillson/charts/chatcli-operator

Quick start

Install

Configure a provider

Start using it!

chatcli
Done β€” you’re chatting with an LLM in your terminal, with full access to your project context.

Highlights

Harness/Quality Pipeline (7 patterns)

Full suite: ReAct, Plan-and-Solve/ReWOO, Reflexion, RAG+HyDE, Self-Refine, CoVe, and cross-provider reasoning backbone. Each pattern opt-in via /config quality or the slashes /thinking, /plan, /refine, /verify, /reflect.

Multi-provider

Switch between OpenAI, Claude, Gemini, Grok, ZAI (Zhipu AI), MiniMax, Moonshot (Kimi), OpenRouter (200+ models), GitHub Copilot, StackSpot, and local models via Ollama β€” all from a single interface.

Agent Mode

Delegate tasks with . The AI plans, suggests commands, and executes with your approval. Built-in safety against dangerous actions.

Coder Mode

Software engineering with . The AI reads, edits, applies patches, and runs tests in a loop with automatic rollback.

Atomic Tools

, , narrow read-only + (TodoWrite parity) + transactional. Architectural parity with Claude Code.

Smart Context

Inject context with , , , , and . Your environment straight into the AI prompt.

Multi-Agent

12 built-in specialist agents (File, Coder, Shell, Git, Search, Planner, Reviewer, Tester…) in parallel.

Customizable Agents

Create personas with reusable skills in Markdown. Version-controlled with Git, shareable across teams.

K8s Watcher and AIOps

Monitor K8s workloads in real time. Operator with 17 CRDs, 54+ remediation actions, log analysis, and metrics.

Durable Scheduler

Cron, wait-until, DAG, and daemon mode. Jobs survive CLI restarts. Agents schedule their own follow-ups.

ArtifactHub

Helm charts published to ArtifactHub with automated CI/CD, 17 documented CRDs, and OCI registry.

Conversation Control

compacts history preserving what matters. and Esc+Esc go back to any point.

Hooks and Web Tools

Lifecycle hooks (pre/post tool, session start/end), native WebFetch and WebSearch to enrich context.

Problems ChatCLI solves

Endless copy and paste

No more cat file.js, selecting text, Ctrl+C, opening the browser, pasting, and typing your question. Use @file directly in the terminal.

Generic commits

@git + a question = perfect commit message based on the actual diff of your code.

Intimidating log analysis

Pipe directly to the AI: cat error.log | chatcli -p "root cause?" β€” instant diagnosis.

Learning curve

@file ./src --mode smart and ask: β€œhow does auth work?” β€” onboarding in minutes.

Who is ChatCLI for?

Developers

Debug code, understand codebases, generate tests, refactor, and document β€” all without leaving the terminal.

DevOps / 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 interact with AI.

DBAs / Data Engineers

Automate repetitive tasks, analyze queries, manage databases, and data pipelines.

Next steps

Full installation guide

Homebrew, binary, go install, from source, Docker, and OAuth.

Basic usage

Essential commands, modes, and navigation in the interactive prompt.

Cookbook

Practical recipes: agent refactoring, log debugging, K8s monitoring, AIOps in production.

API Reference

REST endpoints for the server and operator: incidents, SLOs, runbooks, analytics, federation.

Recent updates

We only highlight major and minor versions here. Patches and hotfixes ship to GitHub Releases β€” the source of truth for the full changelog.
1.139
2026-06-13
  • transcription β€” pure-Go OGG/Opus decoding and actionable ffmpeg guidance
1.138
2026-06-12
  • plugins β€” bring @docs-flatten in as a builtin tool
1.137
2026-06-11
  • tls β€” global corporate TLS trust overrides for all outbound clients
1.136
2026-06-10
  • context β€” knowledge mode: index-card attach + keyless hybrid retrieval (BM25 + embeddings) + @knowledge pull tool (agent/coder/chat)
  • i18n β€” stop x/text from stamping MISSING into argless lookups
1.135
2026-06-10
  • transcription β€” embedded offline Whisper STT via sherpa-onnx
1.134
2026-06-09
  • webfetch β€” render JS pages via headless browser escalation
  • websearch β€” keyless fallback providers + Claude Fable 5 in catalog
  • embedding β€” rebuild embedding provider on /reload
  • operator β€” resolve all 82 open gosec findings
1.133
2026-06-09
  • context β€” semantic passage retrieval for /context attach
  • memory β€” blend cosine, lexical and temporal signals in retrieval ranking
1.132
2026-06-06
  • gateway β€” voice replies, embedded TTS and memory resilience
1.131
2026-06-06
  • imagegen β€” Z.AI + MiniMax image backends, model-aware auto, and /model-image
1.130
2026-06-04
  • proactive messaging, productivity skills pack, and multimodal agent tools
1.129
2026-06-03
  • gateway β€” voice messages (transcription) + conversational replies
1.128
2026-06-01
  • add interactive ask_user tool for agent, coder and chat
1.127
2026-05-31
  • cli β€” interactive command palette overlay
1.126
2026-05-30
  • cli β€” gateway runtime model, /model + /max-tokens, 9 new themes
  • gateway β€” list stop in the /gateway usage hint
1.125
2026-05-29
  • ui β€” unified color theme system + indentation-safe rendering
1.124
2026-05-29
  • catalog β€” add Claude Opus 4.8 with adaptive thinking and fast mode
1.123
2026-05-27
  • gateway β€” messaging gateway β€” Telegram, Slack, Discord, WhatsApp, Webhook
  • hub β€” cross-channel conversation continuity via shared hub
  • lsp β€” language server diagnostics via /lsp
  • memory hybrid capture, security & multi-provider robustness (Tiers A+B+partial C)
  • rpcserve β€” MCP server + ACP agent over stdio
1.122
2026-05-23
  • aiops β€” close 5 gaps surfaced by 2026-05-23 chaos test
1.121
2026-05-23
  • auth β€” TokenProvider with proactive OAuth refresh and retry-on-401
1.120
2026-05-21
  • mcp β€” complete channel push delivery, reactive triggers and persistence
1.119
2026-05-20
  • ui β€” cross-mode UI polish β€” i18n, red errors, lipgloss cards, unified banners
1.118
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)
1.117
2026-05-15
  • mcp β€” add Streamable HTTP transport (MCP 2025-03-26)
1.116
2026-05-15
  • moonshot β€” add Moonshot (Kimi) provider with thinking-mode support
  • qg β€” 15-floor Quality Gate overhaul β€” fix Floor 3, add 6 floors, redesign table
1.115
2026-05-12
  • mcp β€” tier 1-3 server config extensions + autoApprove audit
1.114
2026-05-11
  • skills β€” session-scoped pin for multi-turn auto-injection
1.113
2026-05-08
  • mcp β€” per-server commands + logs ring + manual reload
  • coder β€” use go-prompt for iteration input (paste + full width)
  • mcp β€” inherit parent env, expand $, and hot-reload from empty state
1.112
2026-05-05
  • Agent Park & Resume β€” @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. See Agent Park & Resume.
  • Foreground auto-resume β€” 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 β€” /parked (list), /resume <token>, /cancel-park <token> with prefix-match and idempotency against the auto-resume race.
  • Operator SchemeBuilder migration β€” controller-runtime 0.24 deprecated sigs.k8s.io/controller-runtime/pkg/scheme.Builder; migrated to apimachinery’s runtime.NewSchemeBuilder (–43 net lines).
1.111
2026-04-30
  • Scheduler (Chronos) β€” cron, wait-until, DAG, and daemon mode with durable WAL
  • Bedrock provider β€” Claude/Llama/Nova via AWS Bedrock with IAM/profile/credentials chain
  • Token waste audit β€” cache in agent mode, cached tool defs, early-exit/routing
  • Anthropic cache coalescer β€” local planner respecting the 4-marker cap without losing cache
  • /config sections β€” became hierarchical (/config <section>) with runtime mutation
1.110
2026-04-15
  • MCP client + hooks + web tools β€” parity with Claude Code
  • Cost tracking with per-provider price tables
  • Plan mode + worktrees integrated
1.109
2026-03-29
  • Harness/Quality Pipeline (7 patterns) β€” 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)
Track all releases on GitHub Releases or ArtifactHub.