Local-first context infrastructure

VContext is a versioned context layer that keeps project knowledge in sync across AI coding sessions and machines.

Git for AIcontext.

Context vanishes between sessions, tools, and machines. Snapshots, branches, and MCP keep every agent on the same page.

One line. That's it.
curl -fsSL https://vcontext.dev/install.sh | bash

Live context graph Ready
01CodexMCP connected
02ClaudeMCP connected
03OpenCodeMCP connected
v
shared/contextbranch: main
  • docs12
  • tasks08
  • changes31
  • file context46
snapshot8ef92a1

Problem

Agents forget. Documentation rots. Context stays trapped.

Every time you switch between Codex, Claude Code, OpenCode, or any other coding agent, the new model starts cold. Decisions from the previous session, project-specific conventions, and recent changes are gone — unless you manually reconstruct them in a prompt.

Static AGENTS.md files and docs drift out of date. Agent memory is isolated to one tool. VContext makes project context persistent, versioned, and accessible across any compatible agent.

Capabilities

Everything your models need. Nothing they need to relearn.

VContext turns scattered agent memory into explicit, inspectable project knowledge.

01

Context that survives the session

Store architecture notes, prompts, tasks, decisions, and codebase knowledge once. Pick them up from any compatible agent later.

Durable by design
02

CLI and MCP, one source of truth

Work directly from your terminal or let models read and write context through MCP. Both surfaces resolve to the same project history.

Agent-native access
03

Version everything that matters

Branches, immutable snapshots, history, diffs, and merges bring Git-like control to the knowledge your agents depend on.

Branch-aware
04

Local first. Always useful.

A lightweight daemon and project-scoped SQLite storage keep your context fast and available without requiring a cloud account.

Works offline
05

Built around your repository

Attach descriptions to files and directories, track change notes, and let each agent understand where work belongs before editing.

Git-aware context
06

Share when the project grows

Connect VContext Cloud to sync branches, collaborate through shared projects, and move the same context between machines and teammates.

Optional Cloud sync

Comparison

How VContext fits alongside your existing tools.

Git

Versions source code and files. Tracks changes, supports branches and merges. Does not manage project knowledge, decisions, or agent context.

AGENTS.md / Markdown

Static documentation you write by hand. Useful as a reference, but does not version history, does not branch, and requires manual updates.

Agent memory

Built into each coding agent. Ephemeral or isolated per tool. Does not transfer between Codex, Claude, OpenCode, or other agents.

VContext

Versioned, branchable, shareable context layer. Complements Git by tracking the knowledge that lives around your code. Works across agents via MCP.

How it works

Install. Connect. Keep moving.

No context archaeology. No hand-written catch-up prompt every time you switch tools.

I

Install

One command installs the native CLI. The daemon starts automatically when VContext needs it.

II

Create your context layer

Initialize a project, record the knowledge that matters, and connect any MCP-compatible agent.

III

Keep every model in sync

Agents read the same branch-aware context locally. Add Cloud only when you want remote sync or collaboration.

vcontext — status01

$ vcontext status

vcontext / status

project
api-platform
slug
api-platform
branch
main
documents
1
tasks
0
changes
0
file context
0

Last change

Create document "Architecture"

$

Compatible by default

Use the model you want.

VContext stays underneath your tools, not in the way of them.

01CodexMCP

AI coding agent by OpenAI

02Claude DesktopMCP

AI assistant by Anthropic

03OpenCodeMCP

Open-source coding agent

04TerminalCLI

Direct CLI for human workflows

05Git repositoriesNative

Automatic hook integration

06Any MCP clientProtocol

Standard protocol, compatible tools

VContext Cloud

Local by default. Shared when you need it.

Keep the local workflow you already trust, then add a remote when context needs to travel across people, machines, or agents.

01

Sync the same history

Push and pull versioned context without flattening it into another document or losing branch history.

02

Organize shared projects

Create personal or organization workspaces and keep team context attached to the project it describes.

03

Move between machines

Clone a context repository and continue from its current branch and snapshot wherever the work moves next.

Open VContext Cloud
VContext Cloud showing the vcontext project context browser

Pricing

Free today. Built to grow.

Start using the complete local context workflow now. Paid options may arrive as collaboration and hosted capabilities expand.

01 / EARLY ACCESS

Free

For developers and agents that need durable, versioned context.

$0today
  • Native CLI
  • MCP integration
  • Local context storage
  • Branches and snapshots
  • History, diff, and merge
Install VContext

No card required. Pricing may evolve as hosted collaboration grows.

FAQ

Frequently asked questions.

What is VContext?

VContext is a versioned context layer for AI coding agents. It stores decisions, tasks, documentation, changes, and project knowledge in a structured, branchable, and synchronizable format that agents can read and write through CLI or MCP.

Does VContext replace Git?

No. Git versions source code. VContext versions the project context that accompanies code — decisions, documentation, tasks, and agent prompts. The two tools complement each other.

What kind of context does VContext store?

Documents (architecture notes, specifications), tasks, change notes, file context (descriptions attached to files and directories), and prompts. Everything is organized in projects with branch and snapshot history.

Which coding agents work with VContext?

Any agent that supports MCP — including OpenAI Codex, Claude Desktop, and OpenCode — can read and write VContext. The CLI also works directly from any terminal.

How does VContext use MCP?

VContext implements the Model Context Protocol, exposing its project context as MCP resources that compatible agents can query and modify. Each project's documents, tasks, and changes become available to the agent through standard MCP tools.

Is VContext open source?

The VContext CLI is open source and available on GitHub at github.com/VeguiDev/vcontext. The Cloud service at app.vcontext.dev is a separate hosted product.

Where is project context stored?

Locally, in a project-scoped SQLite database managed by the VContext daemon. When you connect VContext Cloud, context can also be synced and shared across machines.

Can a team share the same context?

VContext Cloud enables branch-level sync and collaboration across team members. Each team member works with the same project context, synchronized through the cloud layer.

Start here

Give every model the same context.

Install locally in one line. Add Cloud later if the project needs to travel.

One line. That's it.
curl -fsSL https://vcontext.dev/install.sh | bash