Pixel Agents

Pixel Agents

Pixel Agents is an open-source mission-control desktop app that runs Claude Code agent sessions in a pixel-art 'office' UI, letting you visualise, orchestrate, and interact with agents across projects while tracking exact costs.

Pixel Agents is ai agents software teams evaluate for ai agents. Use this page to review pricing, integration signals, and the best alternatives before you commit.

Pricing not listed API 70/100
One of 626 tools in AI Agents
Just launched
25 profile views ยท 13 vendor visits in 30 days

Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.

Review official source →

Quick Overview

Best for: AI Agents

What it does

AI Agents software for decision-makers comparing workflow fit and alternatives.

Best fit

AI Agents

Pricing snapshot

Pricing available from Free (MIT licensed)

Next step

Compare Pixel Agents with similar tools before you shortlist it.

Compare this tool before you shortlist it

Review alternatives, pricing posture, and workflow fit side by side.

Pixel Agents is an open-source desktop application that provides a mission-control interface for running Claude Code agent sessions in a pixel-art office metaphor. Each project folder is represented as an 'office' on a pannable campus map; agents appear as characters you can watch think, code, and interact with. The app syncs with Claude Code sessions (same login, same transcripts) so you can start in the app and resume in a terminal or vice versa. It is targeted at developers and people who use Claude agents as part of their workflow and is distributed free under the MIT license for macOS, Linux, and Windows.

Pixel Agents is an open-source mission-control desktop app for Claude Code. Every project is an office on a campus map; every agent is an animated pixel character.

Own this listing?

Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.

Claim this listing for $29

Key Features

Real Claude Code sessions

Runs actual Claude Code sessions with the same login, configuration, and transcripts so sessions are resumable across the app and terminal.

Campus view

Register project folders as offices on a pannable pixel map to see who is working, who is waiting, and per-project costs at a glance.

Rich chat agents

Agents powered by the Claude Agent SDK with streamed markdown, tool cards that show diffs, Allow/Deny permission buttons, image paste, and session resume.

Task orchestration

Shared task lists between you and agents; assign a task with one click and an agent spawns, works, logs discovered work, and checks it off when finished.

The Assistant (campus orchestrator)

A campus-wide rubber-duck assistant that reads project status, backlogs and spending, and dispatches agents to offices in plain language.

Spend tracking

Exact costs reported from the Claude Agent SDK (per turn, per day, per project) shown live on each office's label.

Achievements

Milestones for shipped tasks, parallel agents, and streaks (achievements explicitly exclude spend-based rewards).

Agent-drawn art pipeline

Sprites and office imagery were generated by Claude agents (drawn as pixel arrays in TypeScript, rendered to a contact sheet, screenshotted, and self-critiqued).

Pricing

Free Tier Available

The app is free and MIT licensed; however, agent usage may incur Claude/SDK costs (the UI shows exact spend derived from the SDK).

Open-source

Free (MIT licensed)
  • Desktop app for macOS, Linux, and Windows
  • Source available under the MIT License

Use Cases

Developer workflows with Claude agents

Run and resume Claude Code sessions across UI and terminal, keep transcripts and config in sync, and orchestrate agent tasks for coding and automation.

Multi-project agent management

Register multiple project folders as offices on the campus map to monitor which agents are active, queued, and how much each project is spending.

Task delegation and tracking

Create shared task lists, assign tasks to agents, and let agents log discovered work and mark tasks complete when finished.

Experimenting with agent-generated assets

Use Claude agents to generate pixel art sprites and iterate on visual assets via an automated pipeline described on the page.

Integrations

Claude Code / Claude Agent SDK

Runs real Claude Code sessions and uses the Claude Agent SDK for streamed markdown, tool cards, permissions, and exact cost reporting.

Terminal (resume sessions)

Sessions can be started in the app and resumed in a terminal or vice versa, indicating integration with CLI workflows.

Benefits

Persistent, resumable Claude Code sessions that sync between the desktop app and terminal.
Visual, at-a-glance management of agents across multiple projects via a campus map UI.
Built-in cost visibility with exact spend reporting from the SDK per turn/day/project.
Open-source (MIT) cross-platform desktop app available for macOS, Linux, and Windows.
Task orchestration and shared task lists streamline agent delegation and completion.

Limitations

macOS app isn't signed yet โ€” installer requires manually allowing the app in System Settings โ†’ Privacy & Security โ†’ "Open Anyway".
Agent usage can produce monetary costs reported by the SDK; the app shows exact spend but agent calls may incur charges outside the app.

Frequently Asked Questions

No verified FAQs are available.

Getting Started

  1. 1 Download the app from the project page/GitHub for macOS, Linux, or Windows.
  2. 2 Install and run the desktop app (on macOS, allow the unsigned app in System Settings โ†’ Privacy & Security โ†’ "Open Anyway").
  3. 3 Log in with your Claude Code credentials, register project folders as offices, and begin assigning tasks to agents.

Support

GitHub

Project and issues on GitHub (page lists a GitHub link).

email

Email contact listed on the project page.

docs

Project page includes feature descriptions and example workflow; SDK documentation is referenced via the Claude Agent SDK mention.

API

Available: Yes

Compare Pixel Agents with similar tools

See how it stacks up against alternatives

Free
Offrun

Offrun

Offrun is a Mac workspace for running and monitoring coding agents such as Claude Code, Codex, AGY, and Grok Build side by side. It adds isolated worktrees, peer review, project memory, and on-device dictation while using your existing agent accounts.

AI Agents
Top source
Contact for pricing
Needle2

Needle2

Needle 2 is an open, production-ready 45M-parameter agentic LLM from Cactus designed for tool calling, device control, and structured extraction on extremely small devices; the shipped CQ2-bit binary is ~14 MB and runs in ~28 MB of RAM across Cortex-M, microcontrollers, phones, Raspberry Pi and WebAssembly.

AI Agents
Top source Enterprise-ready
Aclif

Aclif

aclif is an Agent CLI Framework that builds command-line tools for AI agents, providing a unified command grammar and canonical names across multiple SaaS providers to let agents discover, introspect, and run provider operations with consistent safety and auditing.

AI Agents
Top source
Freemium
The cheapest GPU cloud

The cheapest GPU cloud

Compute Cheap provides low-cost GPU compute for training and inference, offering H100 and H200 SXM GPUs as interruptible or reserved capacity with published per-GPU-hour pricing and a simple request/reserve/run workflow.

AI Agents
Top source
Freemium
Jotbus

Jotbus

Jotbus is an encrypted shared scratchpad for coding agents. Developers use it to pass notes and files, hand off work, and request reviews across agents and machines without copying context between terminals.

AI Agents
Top source
Free
Oodle.ai

Oodle.ai

Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.

AI Agents
Top source
Pod

Pod

Pod (Point of Decision) is an AI-native knowledge sharing platform where agents and humans record, search, and inspect firsthand observations about APIs, products, and services to inform future decisions.

AI Agents
Top source
Contact for pricing
Sentinel

Sentinel

Sentinel is an open-source (MIT) autonomous QA agent that reads a codebase to derive end-to-end business flows and tests them across frontend and backend, combining deterministic repo recon, model-driven planning, Playwright browser automation, and backend assertions.

AI Agents

Premium Alternatives

Paid
Ardent

Ardent

Ardent is a production-ready AI agent desktop app for Apple Silicon Mac that generates custom code to automate and scale business workflows, share reusable "abilities" across teams, and connect to company data sources while running in a secure sandbox.

AI Agents
Paid
Abliterated LLM provider for cyber tasks

Abliterated LLM provider for cyber tasks

Refuseless hosts GLM 5.3 Abliterated models through an OpenAI-compatible API for cybersecurity and coding work. The page states that prompts are not retained and shows integrations with OpenCode and Pi.

AI Agents
Enterprise-ready
Paid
PHNTM ONE

PHNTM ONE

PHNTM One is a private, local-first AI appliance: a hand-built desktop device (Raspberry Pi 5, 8 GB, 10.1โ€ณ touchscreen) that runs an on-device model (Gemma 3 4B) to provide a voice-capable assistant, memories, document reading, timers, Home Assistant integration and offline knowledge โ€” sold as a one-time $549 purchase with no subscription and zero telemetry by default.

AI Agents
Paid
AletheionAGI

AletheionAGI

AletheionAGI provides a grounded-memory layer for AI systems that enforces evidence-bound delivery, namespace isolation, and policy authorization so AI readers cannot produce unsupported claims. It's targeted at production-facing use cases like customer support, commerce agents and internal copilots.

AI Agents
Paid
Pact0

Pact0

Pact0 is a marketplace where AI agents perform small paid tasks and build a portable, signed work record; the site also offers reproducible audits of how well an agent can cold-start against a live product and public graded challenges (Pact Trials).

AI Agents
Enterprise-ready
Paid
ClaudeThings

ClaudeThings

ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code โ€” delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.

AI Agents
Paid
Fireworks AI

Fireworks AI

Fireworks AI is an enterprise-grade platform for training, fine-tuning, and serving open and closed AI models, offering a drop-in replacement for closed-model APIs, an optimized inference engine, and tooling to own specialized intelligence and reduce AI spend.

AI Agents
Enterprise-ready
Paid
Moontower

Moontower

Moontower is an AI-powered volatility intelligence platform that provides cross-sectional options-market analytics, dealer positioning signals, and an AI agent copilot for desks ranging from individual traders to enterprise trading teams.

AI Agents
Enterprise-ready

Explore Related Categories

Explore by Outcome