Skip to content
Kwabs AI Workspace Logo
Kwabs · Autonomous Local-First AI Workspace

An AI workspace that actually gets work done.

Kwabs plans, codes and runs commands in a real terminal, asking before anything risky. Run models locally with Ollama or llama.cpp, or bring your own OpenAI, Anthropic or Gemini key. Your memory stays on your machine.

Available for Windows and Linux

Features

Everything an assistant needs to do the work, not just talk about it.

Autonomous Agents

An orchestrator hands work to specialised planner, coder, researcher, terminal and verifier agents, then tracks the plan step by step. Pause or stop at any point.

On-Demand Skills

Teach agents specialized workflows from an open library of playbooks. Loaded dynamically when relevant to avoid prompt bloat, and stored globally in ~/.kwabs/skills.

Safety Gateway

Every terminal command is rated low, medium or high risk. Risky ones wait for your approval, sudo prompts are answered in-app, and file tools are sandboxed.

Local or Cloud Models

Run models fully offline with Ollama or llama.cpp, installed in one click. Or switch to OpenAI, Anthropic or Google Gemini whenever a task calls for it.

Semantic File Search

Search documents, PDFs, photos and recordings by meaning with /search. Local embeddings index your folders in the background with zero data leakage.

Model Cookbook

Kwabs scans your CPU, RAM and GPU, places your machine in a performance tier and recommends the models that will actually run well on it.

Live Canvas

Watch agent output render beside the chat: Markdown docs, live HTML previews, SVG artwork and Mermaid diagrams, ready to inspect and copy.

Private Long-term Memory

Local embeddings and on-device vector search let Kwabs recall past conversations. The index never leaves your machine, even when you chat with cloud models.

PC Doctor Diagnostics

Built-in cross-platform system diagnostics for real-time CPU/GPU load, memory usage, disk health, process triage, and automated OS troubleshooting.

Recording of the Kwabs AI desktop application researching the web and summarizing today's tech news, with its built-in terminal panel

Built for professionals. Designed for everyone.

Documentation

Everything you need to master Kwabs.

Getting Started

Download the installer for your platform and launch Kwabs. Open a project folder to give the agents a workspace, then describe what you want done in the chat.

Choosing a Model

Open Settings to add API keys for OpenAI, Anthropic or Gemini, or install Ollama or llama.cpp in one click. Not sure what your machine can run? The Model Cookbook recommends models for your hardware.

Working with Agents

Kwabs breaks bigger requests into a plan and works through it in a built-in terminal. You can queue follow-up messages, pause between steps, or press Esc to stop the agent.

Agent Skills & Playbooks

Equip agents with expert playbooks for coding, data analysis, finance, and system operations. Built-in and community skills from skills.sh load dynamically on demand.

Local File Search

Search files, PDFs, images, and audio by meaning with /search and jump straight to matches with /goto. All processed locally with background folder watching.

Privacy & Security

With local models nothing leaves your machine. Conversation memory is always indexed locally, API keys are stored only on your device, and saved terminal passwords are encrypted with OS secure storage.

Keyboard Shortcuts

Ctrl + N
New conversation
Ctrl + K
Focus message box
Ctrl + H
Conversation history
Ctrl + `
Toggle terminal
Ctrl + ,
Open settings
Esc
Close panel / stop agent
Got Questions?

Frequently Asked Questions.

Everything you need to know about Kwabs, local models, privacy, and system requirements.

Skills are domain playbooks that teach Kwabs agents specialized workflows (like financial modeling, contract review, or PC diagnostics). All skills are available on demand with zero prompt bloat—agents automatically load relevant instructions only when needed. Skills are installed globally in ~/.kwabs/skills, and agents can discover and install community skills from skills.sh.
Yes. With the /search command, Kwabs performs semantic search across your documents, PDFs, presentations, photos, and recordings using local embeddings. Everything is indexed and searched strictly on your machine without external cloud transfers.
Kwabs is an autonomous, local-first AI workspace for coding and operations. It features multi-agent planning and execution in a real terminal, a safety approval gateway, local LLM execution via Ollama and llama.cpp, a live preview canvas, and encrypted, private vector memory.
Yes. Kwabs provides one-click setup and management for Ollama and llama.cpp. Models run directly on your hardware without internet access, and your conversation index stays on your machine using local embeddings.
Yes. You can bring your own API keys for Anthropic Claude, OpenAI, or Google Gemini. You can seamlessly switch between cloud models and local offline models based on task sensitivity and performance needs.
Every terminal command evaluated by Kwabs's agents is scored as low, medium, or high risk. Medium and high-risk operations pause for explicit user approval before execution. In addition, file operations are strictly sandboxed to your designated workspace and home directory.
The Model Cookbook benchmarks your machine's CPU architecture, system RAM, and GPU VRAM to assign your system a performance tier. It automatically recommends model weights and quantizations tailored to run smoothly at optimal token generation speeds.
Kwabs supports Windows 10 & 11 (64-bit installer) and Linux x86-64 (AppImage, Fedora/RHEL RPM, Debian/Ubuntu .deb). A minimum of 8 GB RAM is required, with an NVIDIA or AMD GPU recommended for larger local models.
Yes. Kwabs is free to download and use with your local models (Ollama and llama.cpp). If you choose to connect cloud providers, you only pay for your own API usage with your personal API keys.
Release History

Evolving day by day.

  1. v1.5.2

    Latest
    • Zero-friction on-demand agent skills: all built-in and installed domain playbooks are enabled by default and dynamically matched without prompt bloat.
    • Global skills storage: installed skills live universally in ~/.kwabs/skills across all workspaces and projects.
    • Open agent skills ecosystem integration: discover and install community playbooks directly from skills.sh via the built-in find-skills tool (npx -y skills add <package> -g -y).
    • PC Doctor diagnostic skill: real-time cross-platform hardware diagnostics, OS performance checks, resource monitoring, and automated troubleshooting.
    • Fine-grained token usage tracking across all model providers and customizable agent output conciseness styles.
  2. v1.5.0

    • Semantic local file search: search documents, PDFs, photos, and audio recordings by meaning using local embeddings without uploading anything.
    • Instant navigation with /goto: jump directly to files, folders, line numbers, or URLs with integrated side-panel preview.
    • Background folder indexing: automatic file watching with incremental updates and visual status tracking.
    • Voice control for Gemini Live sessions: hands-free voice commands to start, pause, and navigate active sessions.
  3. v1.4

    • Rewritten in Rust with Tauri: the Windows, .deb and .rpm installers are now 5–7 MB instead of 150–360 MB, and the app uses about a fifth less memory.
    • Native model clients for OpenAI, Anthropic, Gemini and Ollama, with streaming and tool calling.
    • llama.cpp runs as a managed llama-server, downloaded on demand instead of bundled.
    • Memory search runs on-device in Rust; existing conversations and memories carry over.
    • Faster built-in file search that respects .gitignore.
  4. v1.2

    • Multi-agent architecture: an orchestrator routing work to planner, coder, research, terminal and verifier agents.
    • Pause agent loops between steps, and queue messages while one is running.
    • Live voice sessions with Gemini Live and OpenAI Realtime, including screen sharing and a floating mini-dock.
    • Offline speech-to-text powered by whisper.cpp.
    • Encrypted credential storage with biometric unlock for terminal password prompts.
    • Long-term memory moved to sqlite-vec for faster local vector search.
    • Skill catalog and installer for extending what agents can do.
    • Light theme, file previews, Fedora RPM packages and cross-built Windows installers.
  5. v1.0

    • Initial public release of Kwabs.
    • Native support for OpenAI, Anthropic and Google Gemini.
    • Local model integration with Ollama.
    • Vector-based long-term memory.
Feedback

Report a bug or share an idea.

Messages go straight to the developer. Leave your email if you'd like a reply.

Download Kwabs

Latest release · v1.5.2