Open source · MIT

The native AI coding IDE that plans before it acts

Clew describes what it's about to do, then does it — one visible step at a time. 16 providers, TUI + GUI, ReAct agents, MCP support, zero telemetry. Your code never leaves your machine.

macOS · Windows · Linux
Cloud & local models
Built in the open
clew · agent
PLAN

Add a login form to the app

List project files to find the entry point
Read existing components for style and patterns
Create the form and wire up validation
Write a test for empty and invalid input
Run the tests and check for regressions

Cursor + LM Studio + Multi-API Gateway + TUI, in one app

No Python dependencies to install. No telemetry. Absolute privacy for local models, with the flexibility to plug in cloud APIs. Two frontends: Qt GUI and Textual TUI.

Privacy-First

Local models run 100% on-device. No telemetry, no tracking, no cloud unless you want it.

16 AI Providers

Anthropic, OpenAI, Gemini, DeepSeek, Groq, xAI, z.ai, Nvidia NIM, or run Llama/Mistral/Qwen locally via Ollama or LM Studio. Plus 200+ via OpenRouter.

Dual Frontend

Qt-powered desktop app with real-time streaming, plus Textual TUI for terminal workflows. Switch seamlessly.

Built around trust, not just speed

What matters when you're letting something else touch your code: what it plans, what it costs, and how it fits the way you work.

Plans before it acts

Before editing a file, Clew lays out its plan in plain language, then checks off each step. You always know what's about to change.

Any model, one interface

16 cloud providers or models on your own machine through Ollama, LM Studio, or Nvidia NIM. Switch the active model without leaving the project.

Budget guardrails

Token usage, cost per provider, and burn rate, tracked live. Set daily/monthly limits, enable predictable mode for deterministic token usage.

Smart context

Git-aware filtering, relevance ranking, token budgeting, and live indexing. Clew reads your real project structure before proposing changes.

MCP Protocol

Built-in MCP client and manager. Connect external tools and knowledge bases — MCP tools appear alongside built-in agent tools.

Auto-Router

Complexity-based provider and model selection with fallback chains. Automatically picks the best model for each task.

Plugins & Skills

Drop .py plugins for custom providers and API routes. SKILL.md packages guide agent behavior with YAML frontmatter activation.

Git & Memory

Built-in git tools: status, diff, stage, commit. Cross-chat memory with structured metadata so prior sessions inform new ones.

LSP Integration

Python language server for autocomplete, hover, go-to-definition, and diagnostics — all running in a background thread.

Guardian Safety

LLM-based safety reviewer for risky tool calls. Three levels: off, dangerous-only, all. Shows 3-button modal (Approve / Reject / Use Fix) with proposed alternatives.

Capability Catalog

20+ pre-built templates across 9 categories (code, refactor, test, debug, document, review, deploy, office, learn). Run via /capabilities with placeholder substitution.

Cross-Model Verification

Second Opinion (Pro): ask a different model family to review risky actions. Verify last response: cross-family verifier checks correctness, safety, completeness after agent answers.

Custom Providers

Add your own OpenAI-compatible endpoints via YAML config (~/.clew/providers.yaml) or drop Python plugins in ~/.clew/providers/. Hot-reload without restart.

What makes Clew different

A feature-by-feature look at how Clew stacks up against the alternatives.

Feature Clew Cursor / Cline Windsurf Claude Desktop
Native desktop Qt/PySide6 + Textual TUI, offline-capable Web/Electron Electron Electron
Local-first privacy Zero telemetry, 100% offline Partial Partial Cloud-only
Autonomous agents ReAct + JSON tool calling Yes Yes Limited
Provider count 16 native + 200+ via OpenRouter + custom 5–10 3–5 1 (Anthropic)
MCP Protocol Built-in client & manager Plugin No Yes
Smart context Git-aware, ranked, token-budgeted Yes Yes Limited
Auto-Router Complexity-based + fallbacks No No No
Plugin system Custom providers, routes, skills No No No
Live token tracking Real-time, per-provider quotas, budgets Basic No No
Guardian safety LLM reviewer, 3-level, fix suggestions No No No
Cross-model verification Second Opinion + Verify response No No No
Capability catalog 20+ templates, 9 categories No No No
TUI frontend Textual, full feature parity No No No
Open source MIT Proprietary Partial Proprietary

Bring the model you already trust

Add a key for the providers you use, or skip the cloud entirely and run everything on your own hardware. Custom providers supported via YAML or Python plugins.

Cloud
Anthropic
OpenAI
OpenRouter
Groq
DeepSeek
z.ai
Gemini
Mistral
Together
Fireworks
xAI
Cerebras
SambaNova
Nvidia NIM
Local
Ollama
LM Studio
Custom
OpenAI-compatible (YAML)
Python plugin

...and 200+ more models via OpenRouter gateway

Three steps, no ceremony

No account, no cloud dashboard to configure first.

01

Install Clew

Download the native app for macOS, Windows, or Linux from the latest GitHub release. Requires Python 3.11+. Or pip install -e . from source.

02

Connect a model

Paste an API key for any supported cloud provider, or point Clew at a local Ollama, LM Studio, or Nvidia NIM server. Auto-detection included. Add custom providers via YAML or Python plugins.

03

Describe the task

Open a project in the GUI (clew) or TUI (clew_tui) and tell Clew what you need in plain language. Review the plan, then let the agent read, write, and execute code.

Zero runtime dependencies for core features

No Docker, no Redis, no Node.js. Just Python + Qt. Native desktop with an embedded HTML5 frontend.

Python 3.11+
PySide6 / Qt 6.6+
Textual (TUI)
HTML5 / JS / CSS
SQLite
python-lsp-server
Pure subprocess Git
MCP Client
Plugin System

What's next

Done (v2.0.1)

  • Multi-provider support (16 + OpenRouter + custom)
  • ReAct agent with JSON tool calling
  • MCP protocol integration
  • Smart context & Git integration
  • Auto-Router, LSP, Plugins, Skills
  • Live token tracking & daily/monthly budgets
  • Guardian safety reviewer (3 levels)
  • Capability catalog (20 templates, 9 categories)
  • Cross-model Second Opinion & Verification
  • TUI frontend (Textual) with full feature parity
  • Nvidia NIM provider + custom provider system
  • Collaboration modes (Reviewer, Codegen, Pair, Observer)
  • SQLite persistence + request serialization queues

Planned

  • Agent identity + tool-call audit (G5)
  • Post-task bridge: CMS/editable handoff (G6)
  • Polished TUI/GUI, fast bug fixes (G8)
  • More agent tools (web_fetch, web_search, notebook_edit, image_generation, terminal_interact, database_query)
  • Shared session state for seamless TUI↔GUI switching
  • Smart cost-aware AutoRouter (free/paid modes)
  • Team spend dashboard
  • OAuth: SharePoint/Drive/OneDrive integration
  • Audit trail export (hash-chain + signature)
  • Web UI for remote access
  • Team collaboration & shared sessions

Contributions welcome

Clew is a solo project shaped with help from AI. It's rough in places and that's exactly why more hands would help — trying it and filing an issue is as valuable as a pull request.

Download Clew

Free and open source under the MIT License, for macOS, Windows, and Linux.