MushyBook
TrueDeck logo

TrueDeck

Free multi-agent coding workbench: Grok/Codex/Claude/Cursor panes + TrueMemory (per-repo + global)

Developer ToolsAI AgentsTypeScriptMIT 120 0Health 73
releasedocs GitHub Pages
GitHub

What is it?

What it is

A terminal-first studio for running multiple coding agents side by side in a multi-pane layout.

Why it exists

To eliminate the operational overhead of managing agentic workflows, such as manual memory management, MCP wiring, and project context configuration, allowing developers to use real CLI interfaces instead of webviews.

Who should use it

Developers working with AI coding agentsSoftware engineers managing multiple CLIsTech-savvy users preferring terminal environmentsTeams needing agentic programming workflows

Who should avoid it

Non-technical usersThose requiring GUI-only interfacesUsers without CLI proficiencyProjects needing minimal setup complexity

How it works

A quick walkthrough in plain English

How TrueDeck works

Step 1 of 3

You interact with it

Open TrueDeck, send a request, or connect it to your stack.

Features

Multi-CLI agent support (Grok, Codex, Cursor, Claude, Gemini)
Terminal-first studio layout with tabs and splits
Automated memory and context management
Integrated MCP (Model Context Protocol) wiring
Real TUI (Terminal User Interface) support
Project-based workspace management

Advantages

  • Eliminates manual configuration of memory dashboards and note apps
  • Reduces operational overhead by handling context sync under the hood
  • Allows simultaneous execution of multiple agents on a single codebase
  • Provides a dedicated workspace for agents rather than a standard IDE
  • Simplifies workflow by using real agent CLIs instead of webviews

Disadvantages

  • Terminal-centric interface may have a steeper learning curve for non-CLI users
  • Relies on the availability and stability of external agent CLIs

Installation

FAQ

How do I install TrueDeck?

Download installers or portable builds from the Releases tab on GitHub.

Which coding agents can I run with TrueDeck?

TrueDeck supports Grok, Codex, Cursor, Claude, Gemini, and other agents that can be launched in a terminal.

Do I need to set up Docker, memory apps, or MCP wiring manually?

No. TrueDeck handles memory and MCP synchronization automatically, so you don’t need Docker, note‑taking apps, or memory dashboards.

How can I organize multiple agents in the interface?

Use the studio layout features: tabs, splits, focus, and restore to arrange agents side‑by‑side as you like.

Where is the full documentation and troubleshooting guide?

All guides, shortcuts, configuration details, and troubleshooting are available at https://wutishummus.github.io/TrueDeck/.

Loading documentation…
View on GitHub

Featured in Videos

YouTube tutorials and walkthroughs for TrueDeck

Alternatives

Similar projects ranked by category, topics, and text overlap.

Compare
openwiki logo

openwiki

TypeScript

OpenWiki installs globally via npm and is initialized with `openwiki --init`. It configures an inference provider, API key, and LLM, optionally tracing runs to LangSmith. The CLI can run interactively, accept prompts, or perform single‑shot commands. It creates or refreshes documentation in an `openwiki/` folder, updates `AGENTS.md` or `CLAUDE.md` to point agents to the docs, and supports CI workflows for GitHub Actions and GitLab CI to auto‑merge documentation changes. Customization is supported for multiple providers (OpenRouter, Fireworks, Baseten, OpenAI, Anthropic) with model and base‑URL overrides.

12.4k·Health 95

Compare
agent-as-a-router logo

agent-as-a-router

TypeScript

ACRouter provides a system for routing coding tasks to various backend models, balancing accuracy and cost. The repository includes the CodeRouterBench dataset, reproducible implementations for in-distribution and out-of-distribution (OOD176) testing, and runtime integrations for tools like Claude Code and Codex. It supports both offline reproduction using cached results and live inference-time integration with verifiers.

881·Health 77

Compare
gemma-chat logo

gemma-chat

TypeScript

Gemma Chat combines Electron, Vite, React, and TypeScript with an auto‑provisioned Python venv running MLX‑LM to deliver a local-first coding agent. It offers Build Mode (live‑preview multi‑file code generation), Chat Mode with tool use, model switching, voice input via in‑browser Whisper, and zero‑config setup. After a one‑time ~3 GB model download, everything works offline, producing a distributable .dmg via npm run dist.

1.4k·Health 80

Compare
deepsec logo

deepsec

TypeScript

deepsec follows a multi‑stage pipeline: a fast regex‑based scan identifies candidate files, AI agents (via Vercel AI Gateway or local Claude/Codex) investigate those files to emit findings and recommendations, and optional revalidation checks git history for fixes. The tool supports distributed execution across Vercel Sandbox microVMs for large monorepos, provides a lightweight triage model, and includes plugins for enrichment. Security is mitigated by sandboxing, limiting API key exposure and network egress. Users bootstrap with `deepsec init`, run scans with `pnpm deepsec scan`, process results, and export findings in Markdown or JSON.

5.4k·Health 90

Compare
lottie logo

lottie

TypeScript

The repository provides a skill that agents can invoke to generate Lottie JSON from SVG or other assets, stores each animation as a scene in a project, and serves it through a local player that live‑updates as the agent edits the file. Generated animations can be used directly on web, React Native, iOS, Android, or Flutter.

4.9k·Health 90

Compare
TrueDeck | MushyBook