Bring your own agent backends
Run Claude Code, Codex, OpenCode, and other supported backends in one workspace while keeping your routing choices and subscriptions separate from the app itself.
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
hob is an independent workspace for coding agents. It is designed for developers who already use agent CLIs and want a separate place to run them without tying the workspace to a single model vendor or editor bundle.
The product centers on parallel agent work: users can keep agents, terminals, project context, previews, diffs, and follow-up issues in one tiled surface. It also keeps local history and routing choices under the user's control, and the pricing page says hob does not resell tokens or harvest conversations.
Run Claude Code, Codex, OpenCode, and other supported backends in one workspace while keeping your routing choices and subscriptions separate from the app itself.
Keep agents, terminals, specs, previews, and diffs visible together in a tiled workspace so parallel runs do not collapse into hidden tabs.
Preserve decisions, commands, outputs, and handoffs in searchable activity so workflows can be resumed without re-briefing from scratch.
Create and track follow-up work inside the same workspace that produced it, so discoveries can become issues without moving notes into another tool.
Continue the same workspace from phone, tablet, or browser with encrypted remote access in Pro+, while keeping the workspace outside a bundled provider cloud.
Keep several agent runs open at once while you compare outputs, inspect diffs, and work in terminals without losing sight of the surrounding context.
Resume an earlier workflow after time away by reviewing the local activity trail of decisions, commands, outputs, and handoffs instead of re-explaining the project to the model.
Capture a discovery from an agent run as a follow-up issue in the same workspace, so notes and next steps stay attached to the work that produced them.
Use Pro+ when you want to reach a live workspace from another device while keeping the session encrypted and outside a bundled provider cloud.
Adopt Business or Enterprise when a company needs seats, admin controls, policy configuration, or deployment terms beyond an individual subscription.
Yes. hob offers a 14-day free trial on all plans. Annual plans also include a 14-day refund window if you change your mind after the trial.
hob runs locally on your device and stores agent conversations in a local database. Regular service traffic is limited to read-only checks such as app updates and model-list updates, while agent work goes directly between you and the provider you already use.
No. hob is not a model provider and does not resell tokens. You bring the agent CLIs, model accounts, API keys, and routing choices you already use.
Personal licenses are intended for individuals buying hob for themselves, including professional work. If the product is used inside a business, bought by a company, reimbursed by an employer, or managed as part of a company engineering workflow, it requires a Business license.
Business is for company-managed engineering workflows and employee seats. Enterprise is for larger deployments that need custom procurement, security, deployment, source access or escrow, or self-hosting requirements.
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.
Ghost es un asistente de IA para terminal para chatear, generar código y ejecutar tareas en la línea de comandos. Incluye modelos gratuitos, es compatible con Linux, macOS y Windows, y es de código abierto.
Vi3ecode is a maintained development environment for working with AI coding agents. It keeps project context, terminal, Git, memory, flows, review, and communication connected around the agent you already use.