CLAT logo

CLAT

v2.2.10 — Latest release

A rock-solid agent foundation · The TUI client for DSH · A single Rust file

❯clat
# start the background host and attach the TUI as its client
❯clat dsh
# turn the same TUI into a client for a local DSH host
❯clat plugin
# browse the signed plugin market, install in one command
❯clat web
# configure the native web search and fetch tools
CLAT desktop app screenshot
15.2 MB
Download size: one binary, no Node / Python required
5
Clients: TUI / Desktop / Web / WeChat / DSH
5
Interface languages: English & Chinese, following the system

Why CLAT

Command line + tools + models

CLAT brings the model into your terminal: reading code, editing files, and running commands all happen locally — edits land atomically (batch changes to one file validate and commit in a single snapshot, all-or-nothing), workspace changes export as a hash-manifested Git delivery patch, and every step stays visible, controllable, and auditable.

Local first

Sessions persist as append-only logs; settings, credentials, and trust decisions live in local JSON files under ~/.clat. No cloud dependency — your data never leaves your machine.

One binary

A single Rust executable with no runtime and nothing to install — it runs out of the box on six platforms across macOS, Linux, and Windows, no Node or Python required.

Safe by default

A trust gate guards every new directory; permissions switch between read-only, project-write, and full-access — every write and command asks first, and file changes stay traceable and recoverable.

Positioning

One container lineage, three routes

Spring, DeepSeek Harness, and CLAT share the same "composable container" organ — systems assembled declaratively from swappable parts, an idea reaching back to IoC and OSGi — yet they serve different users and head in different directions. This table orients first-time visitors.

SpringDSHCLAT
PositioningEnterprise Java application frameworkAn "everything is a plugin" agent runtimeA rock-solid agent foundation
UsersProgrammers building applicationsDevelopers driving agents, and the models themselvesUsers who want local-first, single-binary, auditable tooling
Container philosophyLet programmers forget the containerLet the runtime be rewritten at any timeLet the user audit the container
Composition timeCompile time / deploy timeRun timeCompile time (static manifest); extensions move out via MCP
Extensionjar + interfacesIn-process TypeScript pluginsMCP protocol + gated WASM

Spring lets programmers forget the container, DeepSeek Harness lets the model rewrite it, and CLAT lets the user audit it. If what you want is a stable, small, see-through agent foundation — this is it.

Features

Built for real programming workflows

01 — Models

Vendors out of the box

DeepSeek, GLM, Qwen, Kimi, and Tencent Hy presets are built in, and any OpenAI-compatible endpoint works too. /model opens a two-level picker — vendor first, then model — with keys in per-vendor slots, thinking levels, and live quota telemetry.

02 — Multimodal

Multimodal image interaction

Press Ctrl+V to paste a screenshot, drag a path in, or /paste-image from the clipboard — images ride along as structured attachments in both the TUI and the workbench. view_image lets the model inspect project images itself; a model that can't see fails loudly, never silently.

03 — Interaction

Questions, steering & thinking

The model stops to ask when a decision is yours; steer an active run any time, or press Ctrl+Q to queue a message for the next turn — dispatched automatically. Reasoning renders inline as a collapsible Think row (Ctrl+R), and next-step suggestions appear automatically after each turn — sent only when adopted.

04 — Runtime

Unlimited turns & auto-compaction

No turn limit — a run continues until the task is done; in Plan Mode the model plans read-only first and executes only after your approval. At 80% of the context window the conversation compacts automatically with the original history preserved; Esc cancels any time.

05 — Permissions

Three permission modes

Read-only, project-write (default), and full-access, switchable any time via /perm or right from a permission prompt, remembered per project. In the lower two modes file writes and commands still ask every time; commands running sandboxed are approved automatically.

06 — Integration

MCP native

MCP servers over stdio or Streamable HTTP; GLM Coding Plan mounts the four official GLM servers automatically, /mcp inspects every connection and tool. /web configures the native web search and fetch tools, and the official DSH web quartet installs from the market.

07 — Agent

Memory, goals & subagents

Memory is explicit and yours: /memory stores project or global knowledge, the model only reads it — conversations never become memory on their own. /jobs and /schedule run background work with time- or completion-based triggers, progress inspectable any time.

08 — Persistence

Crash-safe sessions

Every conversation is written to an append-only log, flushed before the model is called; after a crash it recovers to the last complete batch. Logs use the DSH-compatible format readable by other tools, /history full-text-searches committed sessions, and input history is shared across clients.

09 — Skills

Layered skills & LSP navigation

Skills layer across the project's .clat/skills/, the user directory, and built-ins; the model loads instructions by name (/skill invokes directly) — read-only, never executing code. Configure ~/.clat/lsp.json for read-only LSP: definition, references, implementation, hover.

10 — Plugins

Plugins & marketplace

The signed plugin marketplace pi.at.cn is live: clat plugin and the /plugin UI (identical in TUI and workbench) browse, install, configure, and roll back, with signature checks built in. Manifest v2 lets WASM plugins go online; the DSH ecosystem interoperates.

11 — Ecosystem

DSH host client

One clat dsh connects to a local DSH host and the CLAT interface becomes its terminal: DSH sessions, questions, and approvals all happen in the same TUI with automatic reconnection. It never writes to ~/.dsh — everything goes through the official API, and host feedback renders natively.

12 — Frontends

Clients & desktop app

clat starts a background host with the TUI, web workbench, and WeChat remote on the same sessions; the desktop app installs standalone and shares Host data. The workbench ships a terminal, a code editor, and full Git source control, in three languages.

Get started

Install

The one-line scripts are recommended: they detect your platform, download the release binary, verify the Minisign signature and SHA-256, and put it into ~/.local/bin (Windows: %LOCALAPPDATA%\Programs\clat). First-install verification needs minisign (macOS: brew install minisign); when no prebuilt binary exists the scripts fall back to building from source.

One-line scripts (recommended)

macOS / Linux

❯curl -fsSL https://raw.githubusercontent.com/artec/clat/main/install.sh | sh

The script offers to add ~/.local/bin to your PATH

Windows PowerShell

❯irm https://raw.githubusercontent.com/artec/clat/main/install.ps1 | iex

Installs into %LOCALAPPDATA%\Programs\clat

Manual download

You can also grab the binary for your platform from the Releases page and drop it into your PATH. Installed users self-update with clat upgrade.

PlatformAssetArchitecture
macOSclat-v*-aarch64-apple-darwin.tar.gzApple Silicon
macOSclat-v*-x86_64-apple-darwin.tar.gzIntel
Linuxclat-v*-x86_64-unknown-linux-gnu.tar.gzx64
Linuxclat-v*-aarch64-unknown-linux-gnu.tar.gzARM64
Windowsclat-v*-x86_64-pc-windows-msvc.zipx64
Windowsclat-v*-aarch64-pc-windows-msvc.zipARM64

Linux builds require glibc 2.39+ (Ubuntu 24.04 generation or newer); older distributions should build from source. After extracting, try clat --help, then run clat inside a project directory — the first run asks you to trust it. The scripts are the same: once installed, just run clat.