Repository-based task board
Create notes with descriptions, statuses, files, links, and screenshots; drag them on the board, connect related notes with arrows, and edit multiple notes at once.
Bruto
Bruto is a local-first task board for software projects that stores notes and AI context in the project folder. It helps developers prepare scoped Markdown handoffs for AI tools or agents, then review responses and request changes inside the original note.
A local task board for repository-based AI work
Bruto is a local-first task board for software projects. It keeps notes in a `.bruto/workspace.json` file inside the selected project folder, so tasks, their statuses, and their supporting context remain alongside the repository rather than in a separate hosted workspace. The board supports descriptions, files, links, screenshots, connections between notes, and bulk editing.
Its main workflow is to prepare precise context for an AI, then review the response in the same note. Users can copy one note, the notes it points to, or the whole project as Markdown, with a preview and token count before sending it to an AI. Agents with file access can answer notes directly, and MCP support lets compatible agents list, read, and answer notes without manually editing the workspace JSON.
Core features
Controlled AI context
Copy a selected note, its linked context, or the whole project as clean Markdown. A preview shows the material being copied and its token count, while global context carries project-wide stack and decision notes.
Review loop inside notes
When an AI that can edit project files works on a task, it can answer inside the note and mark it for review. You can add feedback and mark the note “Changes requested” to send it back with its existing context.
Project structure view
A structure view maps project folders and notes to recognized application elements, including screens and components, API resources and endpoints, and database tables, keys, and policies.
Rules and cross-project dependencies
Rules can be stored as notes and included in every AI context copy. Cross-project notes can block or wait on one another, with links between the related boards.
Agent workflows
Agents can list, read, update task status, and answer notes through the MCP server. Bruto also documents a one-line AGENTS.md or CLAUDE.md instruction for agents that can access project files.
Practical use cases
Planning repository changes
Break a feature into connected notes, attach the relevant paths and screenshots, and send an individual task or its linked context to an AI without manually assembling a prompt.
Delegating implementation to coding agents
Give an agent a task through an AGENTS.md or CLAUDE.md instruction, or connect it through MCP. The agent can find notes, identify the task it is working on, and return its answer to the board.
Applying shared project rules
Keep stack choices and project decisions in a standing rule or global context so they accompany each AI handoff. This is useful when repeated tasks need the same constraints.
Coordinating related projects
Represent dependencies between a front end, API, and database across separate project boards. A blocking or waiting note links the work and provides a route to the related project.
Reviewing and navigating active work
Use the structure view and filters to locate work by folder, path, status, images, links, or AI responses, then review the returned answer and request changes from the same note.
Pros and Cons
Pros
- Tasks and project context are stored in the project folder rather than a hosted account.
- Context can be scoped from one note to the whole project and reviewed with a token-count preview before copying.
- AI responses and change requests stay attached to the task, creating a visible review loop.
- The board supports files, links, screenshots, rules, dependencies, structure visualization, keyboard shortcuts, and accessibility-oriented labels.
- It works offline, can be installed as an app, and is described as free and open source.
Cons
- The documented browser requirement is a computer running Chrome, Edge, Brave, or Opera; support for other browsers and mobile devices is not stated.
- The source does not document team collaboration features, paid-plan limits, or integrations beyond the listed AI and MCP workflows.
- Its agent workflow depends on configuring file access, an AGENTS.md or CLAUDE.md instruction, or the Bruto MCP server.
FAQ
Where does Bruto store project notes?
Bruto stores its workspace in a `.bruto/workspace.json` file inside the selected project folder. The site says notes stay in the folder and nothing leaves the computer, aside from anonymous usage statistics; it does not require an account or cookies.
What is required to open a project?
On a computer, open the project folder in Chrome, Edge, Brave, or Opera. Bruto can also be installed as an app and works offline.
What can a Bruto note contain?
A note can include a task description, files, links, screenshots, and status. Notes can be connected, moved on a board, and edited in batches.
How do I give an AI context from Bruto?
You can copy the selected note, the selection together with everything it points to, or the whole project as Markdown. Bruto previews the copied content and token count, and supports a global context for stack and project decisions.
Which AI tools can work with Bruto?
Bruto supports pasting copied context into Claude, ChatGPT, Gemini, or DeepSeek. Agents can also work with notes through an AGENTS.md or CLAUDE.md instruction, or through the Bruto MCP server. The source does not document team collaboration features or paid-plan limits.
Quick Facts
- Category
- Developer Tool
- Storage model
- Local project folder; `.bruto/workspace.json`
- Supported browser setup
- Chrome, Edge, Brave, or Opera on a computer
- AI workflow
- Markdown context copying, direct file-access agents, and MCP
- AI tools named by the product
- Claude, ChatGPT, Gemini, and DeepSeek
- Availability
- Free and open source; no account required
Альтернативы Bruto
SonOf
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.
ByteAsk
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
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.
Biji
Biji - это универсальная платформа, разработанная для повышения продуктивности с помощью инновационных инструментов и функций.
GitBot
GitBot is a local browser-based workspace for creating reusable coding bots powered by Claude Code, Codex, or OpenCode. It helps developers run those agents across repository folders with persistent threads and configurable permissions.
hob
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.