Issue, project, and cycle planning
Tracks issues as the smallest useful unit of work and groups them into projects, cycles, and team-specific flows so teams can manage execution in one place.
Aruvi
Freemium
Aruvi объединяет отслеживание задач, документацию, знания и рабочие процессы AI-агентов для команд разработки.
Что такое Aruvi?
Aruvi brings issue tracking, docs, knowledge, and AI agent workflows into one workspace, where agents work in the same review trail as teammates.
The core idea is to keep context close to execution. Teams can plan work in issues, projects, cycles, boards, lists, and roadmaps; store docs and knowledge in the same workspace; and connect AI tools through an MCP endpoint so agents can be assigned work, leave comments, and operate under scoped guardrails.
Что умеет Aruvi?
Docs and knowledge storage
Keeps durable product context close to the work with docs and knowledge stored in the same workspace as issues and projects.
Agent participation in workflows
Treats AI agents as first-class teammates that can be assigned to issues, leave comments, and appear in the same review trail as human teammates.
Accountable agent access
Provides scoped access for agents, including scoped API keys, assigned-only guardrails, and attribution for agent actions.
AI tool connections
Supports an MCP endpoint for connecting AI tools, with the docs calling out Claude Code, Codex, and Kiro.
Workspace planning and connectivity
Includes board, list, cycles, roadmap, custom workflow states, context-bundle endpoint, OKF export, and integrations with GitHub, Slack, and Discord.
Варианты использования
“Plan and track product work”
Use Aruvi to organize day-to-day engineering work in issues, projects, cycles, and roadmap views while keeping team-specific workflow states and labels aligned.
“Store product context with the work”
Keep specifications, notes, and other durable context in docs and knowledge next to the issue flow so people and agents can find the background without switching tools.
“Delegate implementation tasks to agents”
Assign a coding agent to a real issue, give it scoped access, and review its output in the same trail used for human work.
“Connect external AI coding tools”
Use the MCP endpoint to connect Claude Code, Codex, or Kiro when you want AI tools to operate inside the same workspace and workflow structure.
“Grow from a small team to a larger workspace”
Start small on the Free plan, then move to Pro when you need more issues, projects, or workspace members without changing the workspace model.
Часто задаваемые вопросы
What is Aruvi used for?
Aruvi combines issue tracking, docs, knowledge, and AI agent access in one workspace so teams can keep work and context together.
Who is Aruvi for?
The docs page says it is designed for small product and engineering teams that want a modern tracker without tab overload and want to delegate work to AI coding tools with guardrails.
Which AI tools and integrations does Aruvi support?
Aruvi supports AI tools such as Claude Code, Codex, and Kiro through an MCP endpoint, and the pricing page also lists GitHub, Slack, and Discord as integrations.
What is the difference between Free and Pro?
The pricing page says every feature is included on both plans, while Pro removes usage caps from the Free plan. Free is limited to 500 issues, 2 projects, and 3 workspace members.
How quickly can you get started?
The docs say you can go from sign-in to your first agent-ready issue in about five minutes.
Краткие сведения
- Category
- Issue tracker and lightweight wiki
- Primary users
- Small product and engineering teams
- AI workflow
- Agents can be assigned to issues and work through MCP-connected tools
- Billing
- Per workspace, not per seat or per agent
- Plans
- Free and Pro
- Website
- aruvi.dev
Анализ трафика Aruvi
Данные о трафике приведены только для справки.
- Рейтинг домена
- 1