| [ Web Proxy ] |
| Viewing: https://humanlayer.dev/code | [Back] [Original] |
HumanLayer is a multiplayer coding agent IDE and cloud that works seamlessly from your workstation to anywhere you want to run background agents.
It brings agent sessions, plan artifacts, and code diffs together in one place for your team to collaborate and ship.
HumanLayer ships composable pieces to meet software factory builders where they already are. Bring your own compute, development environment, and agent harness, or run the HumanLayer stack on your workstation or remote workers.
$brew trust humanlayer/humanlayer$brew install humanlayer/humanlayer/humanlayer
Bring agent sessions, plan artifacts, and code diffs together so your team can collaborate and ship.
A complete AI coding environment from tasks and artifacts to cloud-scale agent orchestration.
Tasks group agent sessions, artifacts, and worktrees in one workspace that you can collaborate on with your whole team.
The team that brought you context engineering brings frontier AI coding techniques and makes them shareable and collaborative. Battle-tested for solving large problems in million-LOC enterprise codebases.
Research, designs, plans, mockups. Versioned, shareable, and tied to the task.
Humans and Agents collaborating on design docs. Catch mistakes before 2,000 lines of code.
You cant do advanced context engineering without staying in touch with your context. HumanLayer optimizes for high-level orchestration, while letting you drill into every thinking message, every subagent tool call, and every code change.
A local daemon runs many Agent sessions in parallel on your laptop. Spin up cloud daemons for long-running work. Everything syncs through the HumanLayer API same UI on web, desktop, or phone, with your teammates one tab away. Agents keep working even if you close your laptop.
Jump between tasks, sessions, and artifacts with a keystroke. A command palette for every action.
Tasks group agent sessions, artifacts, and worktrees in one workspace that you can collaborate on with your whole team.
Ensure alignment at every step and put engineers in the driver's seat for code quality and architecture.
Structured workflows give the agent every opportunity to show you what it's wrong about before moving to implementation.
Six phases that turn fuzzy intent into shipped code, with checkpoints your team can verify.
Generate clarifying questions before any code is written.
Map the codebase, dependencies, and surrounding patterns.
Draft a design doc your team can comment on, in real-time.
Break the design into phased, verifiable implementation steps.
Detailed plan with file paths, test cases, and acceptance criteria.
Execute with continuous feedback. No 2,000-line surprises.
Do not outsource the thinking.
Every phase is a place to push back.
Gathering codebase context and research findings...
Inline comments on design documents. Your whole team humans and Agents collaborating in real-time. Catch mistakes before they become 2,000 lines of code.
Why not just use a Notion or Google Doc? Because there, your design doc is disconnected from the work. In HumanLayer, comments and decisions feed straight back to the agents the doc is the interface to the code, not a separate artifact you hope someone reads before shipping.
Your whole team humans and Agents commenting on the design before a single line is written.
This separation is causing the S/shift+S hotkey conflict. Can we share the same pure component?
Good catch updated the design to use a shared SidebarWidget with configurable tabs.
Can we move the sidebar to the left? Matches our other pages, puts navigation closer to the cursor.
We need to call the API for spline reticulation widget cant compute that locally.
Right adding a SplineAPI call between setActiveTab and persist.
+1, this matches the session detail pattern. LGTM to proceed!
Team opens the design document...
Describe the work, pick a workflow, and let HumanLayer provision worktrees and launch the first agent session.
Describe what you want to build inline, or pull it straight from a Linear or Jira ticket. HumanLayer drafts the task name and slug for you as you type.
Leading experts on getting the most out of AI coding agents.
Simple plans for individuals, teams, and enterprises.
HumanLayer is SOC 2 Type II compliant. We use Vanta to help monitor our security controls and maintain compliance.
ZDR and DPA agreements available on enterprise tiers.
Bring your own. Plug in your existing Claude, Codex, and other AI subscriptions or API keys (BYOK) there's no separate HumanLayer per-token bill to reason about.
Claude Code, Codex, Copilot, Fireworks, with new models/subscription providers added regularly.
You can, but those are part of a fragmented, manual, pre-AI world. In HumanLayer, comments and decisions feed directly back to the agents, so your design docs live in the IDE, directly integrated with the implementation.
Today, HumanLayer supports a variety of RPI and experimental workflows, and we're actively working on ways for you to bring your own skills and workflows into HumanLayer.
You can but you'll spend months in the exploration phase trying things and seeing what sticks. HumanLayer is an opinionated system of agents that you can stand up in 10 minutes. We build HumanLayer with HumanLayer, so we know it works, and we've spent hundreds of hours working in the trenches with customers making the prompts and workflows "squishy" - that is, flexible to a broad range of problems and inputs, so there's no holding it wrong.
Yes - the Starter plan is free for teams of three or less.
Not yet, but we'll be open-sourcing some of the building blocks in the coming weeks and months. Our Research, Plan, Implement (RPI) framework is already open source.
Let's make this the year of no more slop.
$brew trust humanlayer/humanlayer$brew install humanlayer/humanlayer/humanlayer
| Web Proxy Viewer | New URL | Original Page |