llms.txt
Compare with other sites' llms.txt files →# Traycer
Traycer is a free, open-source desktop app for Mac, Windows, and Linux. It runs coding agents in parallel: a worktree per agent, shared specs and tickets, and agents that message each other.
Traycer supports 22 coding agents and model providers. Coding agents: Claude Code, Codex, OpenCode, Cursor, Grok, Qwen Code, Kiro, Droid, Kimi, Copilot, Kilo Code, Amp, Devin, Pi, Hermes Agent, Oh My Pi, Reasonix, Antigravity, and Command Code. Model providers: Traycer Inference, OpenRouter, and Hugging Face.
The free tier is for individuals and includes cloud sync and device switching. Sync for teams is $16 per user per month billed yearly, or $20 per user per month billed monthly, and adds sharing a task with the whole team.
## Pages
- [Home](https://traycer.ai/index.md): Free, open-source desktop app for running Claude Code, Codex and Cursor in parallel. Worktree per agent, shared specs, agents that message each other.
- [Download](https://traycer.ai/download.md): Download Traycer for Mac, Windows, and Linux, and get the app on your phone.
- [Pricing](https://traycer.ai/pricing.md): Traycer pricing: free for individuals, including cloud sync and device switching. Sync for teams is $16 per user per month billed yearly, or $20 monthly, for sharing a task with the whole team.
- [Enterprise](https://traycer.ai/enterprise.md): Traycer helps teams move faster by turning shared specs into clear, executable development workflows.
- [Blog](https://traycer.ai/blog.md): Read the Traycer blog for insights on spec-first development, product thinking, workflows, and building better software.
- [Compare](https://traycer.ai/compare.md): Side-by-side comparisons of coding agents and agent workspaces.
- [About Us](https://traycer.ai/about-us)
- [About Traycer](https://traycer.ai/about.md): Traycer is an open source (MIT) desktop app where several coding agents, such as Claude Code, Codex and Cursor, share Tasks with specs, tickets and reviews.
- [Contact](https://traycer.ai/contact-us.md): Get in touch with the Traycer team for product questions, support, or help getting started.
- [Roadmap](https://traycer.ai/roadmap.md): What Traycer is building next, mirrored from GitHub Discussions: in progress, planned, under consideration and shipped. Vote and discuss on the thread itself.
- [Status](https://traycer.ai/status)
- [Privacy Policy](https://traycer.ai/legal/privacy-policy.md): Privacy Policy for Traycer. Last updated Aug 29, 2026.
- [Terms of Service](https://traycer.ai/legal/terms-of-service.md): Terms of Service for Traycer. Last updated Aug 14, 2024.
- [Data Processing Agreement](https://traycer.ai/legal/data-processing-agreement.md): Data Processing Agreement for Traycer. Last updated Jan 17, 2025.
## Posts
- [How to build a software factory from zero](https://traycer.ai/blog/how-to-build-a-software-factory.md): How to build a software factory from zero, step by step: what we learned when ours opened 332 of the 675 PRs we merged in 11 days.
- [Ralph Loops. Bart Orchestrates.](https://traycer.ai/blog/ralph-loops-bart-orchestrates.md): Simple loops keep an agent going until context rot breaks the repo. Larger projects need an orchestrator that can observe, steer, and keep the plan intact.
- [The Ultimate Spec-Driven Development Approach](https://traycer.ai/blog/the-ultimate-spec-driven-development-approach.md): Agents write code easily and lose the intent behind it. Spec-driven development keeps the why, the constraints, and the edge cases intact.
- [The Sum Is Greater Than the Parts: Inside Traycer’s Multi‑Model Architecture](https://traycer.ai/blog/inside-traycers-multi-model-architecture.md): No single model is best at planning, decomposition, and verification. Traycer runs an ensemble, with each model chosen for one job.
- [Build With Intent, Ship With Confidence](https://traycer.ai/blog/build-with-intent-ship-with-confidence.md): Plan what you are building and why before an agent writes code, so scope, constraints, and structure stay explicit.
## Comparisons
- [Conductor alternative for teams: shared Tasks, handoff, mobile](https://traycer.ai/compare/conductor-alternative-for-teams.md): Conductor's multiplayer ends with Conductor Cloud on Nov 20, 2026. Traycer lets teams share Tasks and agents on Windows, Linux and macOS. Free, MIT.
- [Conductor Cloud is shutting down: how to switch to Traycer](https://traycer.ai/compare/conductor-cloud-shutdown-alternative.md): Conductor Cloud shuts down Nov 20, 2026. Dates, what to export, and how to switch to Traycer: free, MIT open source, Windows, Linux, macOS, 22 agents.
- [T3 Code vs Orca (2026): features, agents and mobile](https://traycer.ai/compare/t3-code-vs-orca.md): T3 Code vs Orca: both free and open source (MIT). Agents, mobile apps, worktrees and remote access compared, plus when Traycer is the better fit.
- [Best Conductor alternatives (2026) after Conductor Cloud shutdown](https://traycer.ai/compare/conductor-alternatives.md): Conductor Cloud shuts down Nov 20, 2026. Compare Conductor alternatives for Windows, Linux and Mac. Top pick: Traycer, free and open source (MIT).
- [The best tools to run multiple coding agents in parallel (2026), checked and sourced](https://traycer.ai/compare/best-parallel-coding-agent-tools.md): Best tools to run Claude Code, Codex and other agents in parallel (2026). Top pick: Traycer, free and open source (MIT). Plus Conductor, Orca, T3 Code, Paradev.
- [How to review code your agents wrote: Claude Code Review vs Codex review vs a second-agent review (2026)](https://traycer.ai/compare/claude-code-review-vs-codex-review.md): Claude Code Review vs Codex review: pricing, setup, GitHub triggers and limits compared, plus how to add a second-agent review before you merge AI-written PRs.
- [Cursor vs Claude Code vs Codex (2026): pricing, limits, and when to use all three](https://traycer.ai/compare/cursor-vs-claude-code-vs-codex.md): Cursor vs Claude Code vs Codex (2026): pricing, models, usage limits, safety defaults and parallel agents compared, and when to use one, two or all three.
- [Traycer vs Conductor: Conductor alternative as Cloud shuts down](https://traycer.ai/compare/traycer-vs-conductor.md): Conductor Cloud shuts down Nov 20, 2026. Traycer is a free, MIT open source Conductor alternative for Windows, Linux and macOS with 22 coding agents.
- [T3 Code vs Traycer (2026): providers, apps and open source](https://traycer.ai/compare/traycer-vs-t3-code.md): T3 Code, by Theo Browne and team, vs Traycer: both free and MIT open source. Providers, mobile apps, shared plans, PR review and automation, compared.
- [Claude Code vs Codex: an honest comparison, and why many devs use both](https://traycer.ai/compare/codex-vs-claude-code.md): Codex vs Claude Code is mostly a choice of defaults, models and pricing.
- [Traycer vs Orca: which coding-agent workspace fits how you work?](https://traycer.ai/compare/traycer-vs-orca.md): Traycer and Orca are both free, open source (MIT) desktop apps for running Claude Code, Codex and other coding agents in parallel with your own subscriptions.
## Docs
- [Documentation](https://docs.traycer.ai/)
- [Docs for agents](https://docs.traycer.ai/llms.txt)
- [Source](https://github.com/traycerai/traycer)