Live codebase graph
The main workspace shows your codebase as a live graph, with files as nodes and imports as edges, so the shape of the repository stays visible while you work.
Flare
Flare is a graph-first IDE for agentic coding that shows a live dependency graph of a codebase while you run coding agents in its terminal. It helps developers monitor edits, review impact, and keep tasks, questions, and decisions in the same workspace.
Overview
Flare is a graph-first IDE for agentic coding. The repository README describes it as a desktop app, or as something that can be served to a browser from the machine where the agent runs. Its main surface is a live graph of the codebase, where each file is a node and imports are edges.
The product is built around a workflow where you run an agent in Flare's terminal and Flare watches the repository as it changes. It updates the graph in real time, snapshots change bursts into local shadow history, and uses a board to surface tasks, design decisions, and questions so the human and agent can work from the same map rather than a chat log.
Features
Built-in agent terminal
A terminal sits underneath the graph, and the README says you run agents such as claude, codex, or opencode there while Flare watches what they change.
Local change history and reverts
Every change burst is snapshotted into local shadow history, letting you diff and revert edits per file or across the whole tree.
Three graph views
The interface offers Canvas, Wheel, and Districts views for different questions: dependency flow, whole-repo connectivity, and repository size or mass.
Board-based collaboration workflow
The control panel separates tasks, design decisions, and questions, and exposes them as queryable workflow objects over MCP.
Multiple analysis lenses
Lenses let you recolor the same graph by activity, hotspots, risk, tests, coverage, instability, reuse, unread files, cycles, and related views.
Use Cases
Map repository structure
Use Flare when you want to inspect a codebase as a dependency graph and see how files connect, rather than jumping between tabs or searches.
Supervise agent-driven coding
Use the terminal and graph together when an agent is making edits, so you can watch changes appear in context and review the resulting impact immediately.
Review architecture from multiple angles
Use the Canvas, Wheel, or Districts views to answer different architecture questions: what depends on what, what spans the whole repo, and where the largest areas of code live.
Organize agent tasks
Use the task board when work needs to be handed to or resumed by an agent, especially when the brief should carry file context and graph-derived status.
Track open decisions and blockers
Use the questions and design-decision lanes when an agent needs input or has made a proposal that should be recorded before further work continues.
Pros and Cons
Pros
- Makes repository structure visible as a live graph instead of a list of files or a chat transcript.
- Connects agent work to the same visual surface the human uses, which helps keep code changes, tasks, and questions in context.
- Provides multiple views and lenses for different questions, from dependency tracing to whole-repo scale and churn.
- Includes local shadow history, giving users a way to inspect or revert change bursts without leaving the workspace.
- Treats tasks, design decisions, and questions as first-class workflow items, including MCP-accessible actions.
Cons
- The public sources are documentation-heavy and do not provide full setup, supported-platform, or release-stability details.
- Pricing for Flare itself is not clearly documented in the repository sources provided, so the product page cannot confirm a standalone plan or license terms from these materials alone.
FAQ
What is Flare?
Flare is presented as a graph-first IDE for agentic coding. The README describes it as a desktop app, or something that can be served to a browser from the machine the agent runs on.
How does Flare fit into an agentic coding workflow?
The README says you run the agent in Flare's terminal, while Flare watches the repository, updates the graph in real time, and records changes in local shadow history that you can diff against and revert.
What views does Flare provide for exploring a codebase?
The source text describes three views: Canvas, Wheel, and Districts. Each view can be switched from the toolbar or command palette and respects the active lens, selection, collapsed directories, and search filter.
Is Flare free to use?
The repository is public on GitHub. GitHub's pricing page shows a free tier for individuals and organizations, but the repository sources do not provide a separate product pricing page or a paid plan for Flare itself.
Does Flare support team collaboration or shared workflow management?
The README mentions task management, design decisions, and questions as collaborative board areas, plus MCP-accessible actions such as tasks_list, task_get, task_update, task_create, decision_record, question_ask, and working_agreement.
Quick Facts
- Category
- Developer Tool
- Product type
- Graph-based agentic IDE
- Platform
- Desktop app or browser-served from the agent machine
- Primary users
- Developers using coding agents
- Repository host
- GitHub
- Pricing signal
- Public GitHub repository; GitHub offers a free tier, but Flare pricing is not specified in the provided sources
Alternativas a Flare
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.
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.
Ghost
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
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.
Lucid Train
Lucid Train is a local-first AI coding harness that turns repository code into architecture diagrams and uses those diagrams as specifications for coding agents. It is available as a desktop app and a lightweight Rust CLI, and it can run with local models or your own API keys.
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.