Skip to main content
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.
ChatCLI Demo

ChatCLI in action — interactive mode with context and agent mode

15 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…
In practice, your everyday terminal turns into this:
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 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)

1.172.0 — 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

gRPC Server

1.172.0 — Centralized deployment for teams. Clients connect via chatcli connect and share LLM providers, sessions, and plugins.
ghcr.io/diillson/chatcli:1.172.0

AIOps Operator

1.172.0 — Autonomous incident detection, AI-powered analysis, and automated remediation for Kubernetes clusters. 17 CRDs, 54+ actions.
ghcr.io/diillson/chatcli-operator:1.172.0

Helm Charts

1.172.0 — 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!

Done — you’re chatting with an LLM in your terminal, with full access to your project context.

​
Highlights

Four pillars that define ChatCLI:

Agent Mode

Delegate tasks with : the AI plans, executes with your approval and self-corrects — with built-in safety against dangerous actions.

Coder Mode

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

Multi-provider

15 providers and 350+ models — OpenAI, Claude, Gemini, Grok, Ollama… switch at any time, from a single interface.

Quality Harness

7 reliability patterns (ReAct, Reflexion, CoVe, RAG+HyDE, Self-Refine…) opt-in via /config quality.
And, in the same binary:

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

14 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?" — instant diagnosis.

Learning curve

@file ./src --mode smart and ask: “how does auth work?” — onboarding in minutes.

​
Who is ChatCLI for?

Developers

Debug code, understand codebases, generate tests, refactor, and document — 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 — the source of truth for the full changelog.
​
2026-07-28
  • update — announce new releases in-session and revamp version UX
​
2026-07-27
  • providers — list all gateway models when endpoint URL is customized
​
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
​
2026-07-21
  • bedrock — BEDROCK_MODEL selects the default model
​
2026-07-21
  • bedrock — custom endpoint overrides for corporate DNS and VPC
​
2026-07-20
  • session — proactive cross-session recall with tolerant search and titles
​
2026-07-19
  • park — capture user messages typed while parked as resume directives
​
2026-07-17
  • session — MCP session autosave by default and bounded machine-session lifecycle
​
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
​
2026-07-16
  • mcp-server — full ChatCLI experience parity over MCP
​
2026-07-14
  • agent — @model tool — AI-driven model/provider routing with tiered catalog and delegate
​
2026-07-13
  • mcp — re-export connected MCP servers’ tools on the mcp-server surface
​
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
​
2026-07-11
  • mcp — OAuth 2.1 authorization for remote MCP servers
​
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
​
2026-07-10
  • GPT-5.6 family (Sol/Terra/Luna) + Codex client headers fix
​
2026-07-10
  • mcp — dynamic tool discovery on tools/list_changed notifications
​
2026-07-09
  • agent — adaptive payload-cap recovery, bounded prompt floor and zero-loss compaction (48f3c0c)
  • plugins — tolerate the CCR key syntax variants models actually produce (8ebe661)
​
2026-07-08
  • add @api-explorer builtin for end-to-end API reconnaissance (cc99eab)
​
2026-07-07
  • skills — match multi-word triggers in any word order
  • skills — re-activate skills mid-loop in agent and coder modes
​
2026-07-03
  • tools — expose MCP tools through the @tools catalog
​
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
​
2026-07-01
  • models — Claude Sonnet 5 + GLM-5.2 + Bedrock Fable 5/Sonnet 5 support
​
2026-06-28
  • graphview — interactive grap-style, graph in agent, coder and chat
​
2026-06-26
  • live telemetry in agent/coder + on-demand CCR curation
​
2026-06-25
  • self-evolution engine, in-core knowledge graph and memory quality
​
2026-06-22
  • native context compression, image compression and output-token reduction
​
2026-06-21
  • plugins — add @diagram builtin for embedded Graphviz rendering
  • plugins — add selectable system/embedded Graphviz backend to @diagram (3ea68b5)
​
2026-06-18
  • multimodal vision input + multi-provider image editing
​
2026-06-17
  • docs-flatten — ingest code and infra repos into knowledge bases
  • coder — recover stdin after Ctrl+C at a security confirmation
​
2026-06-15
  • full @context parity + @registry-tags sort/last
​
2026-06-14
  • context — autonomous knowledge-base management via @context
  • plugins — add @registry-tags and @wikipedia builtins
​
2026-06-13
  • transcription — pure-Go OGG/Opus decoding and actionable ffmpeg guidance
​
2026-06-12
  • plugins — bring @docs-flatten in as a builtin tool
​
2026-06-11
  • tls — global corporate TLS trust overrides for all outbound clients
​
2026-06-10
  • context — knowledge mode: index-card attach + keyless hybrid retrieval (BM25 + embeddings) + @knowledge pull tool (agent/coder/chat)
  • i18n — stop x/text from stamping MISSING into argless lookups
​
2026-06-10
  • transcription — embedded offline Whisper STT via sherpa-onnx
​
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
​
2026-06-09
  • context — semantic passage retrieval for /context attach
  • memory — blend cosine, lexical and temporal signals in retrieval ranking
​
2026-06-06
  • gateway — voice replies, embedded TTS and memory resilience
​
2026-06-06
  • imagegen — Z.AI + MiniMax image backends, model-aware auto, and /model-image
​
2026-06-04
  • proactive messaging, productivity skills pack, and multimodal agent tools
​
2026-06-03
  • gateway — voice messages (transcription) + conversational replies
​
2026-06-01
  • add interactive ask_user tool for agent, coder and chat
​
2026-05-31
  • cli — interactive command palette overlay
​
2026-05-30
  • cli — gateway runtime model, /model + /max-tokens, 9 new themes
  • gateway — list stop in the /gateway usage hint
​
2026-05-29
  • ui — unified color theme system + indentation-safe rendering
​
2026-05-29
  • catalog — add Claude Opus 4.8 with adaptive thinking and fast mode
​
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
​
2026-05-23
  • aiops — close 5 gaps surfaced by 2026-05-23 chaos test
​
2026-05-23
  • auth — TokenProvider with proactive OAuth refresh and retry-on-401
​
2026-05-21
  • mcp — complete channel push delivery, reactive triggers and persistence
​
2026-05-20
  • ui — cross-mode UI polish — i18n, red errors, lipgloss cards, unified banners
​
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)
​
2026-05-15
  • mcp — add Streamable HTTP transport (MCP 2025-03-26)
​
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
​
2026-05-12
  • mcp — tier 1-3 server config extensions + autoApprove audit
​
2026-05-11
  • skills — session-scoped pin for multi-turn auto-injection
​
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 $, and hot-reload from empty state
​
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.
  • 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).
​
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
​
2026-04-15
  • MCP client + hooks + web tools — parity with Claude Code
  • Cost tracking with per-provider price tables
  • Plan mode + worktrees integrated
​
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)
Track all releases on GitHub Releases or ArtifactHub.