Dvara desktop gateway

AI agents, safely connected to your computer.

A local control layer for managed browser work, workspace context, and human-reviewed patches from any compatible AI client.

Local-first. MCP-compatible. Human-approved writes.

Control loop

One governed path from prompt to local action

The website explains and qualifies users. The desktop app remains the actual local runtime.

1LLM chat or MCP client
2Dvara token and grant check
3Managed browser or workspace tool
4Artifact, patch, or structured result
5Local audit and emergency stop
Dvara Desktop
Agent request
Research this page, inspect the repo, and propose a safe copy fix.
Managed browserInspect page and capture evidence
Ready
Patch proposalReview before any file changes
Review
Control state
Browser ready
Workspace grant active
Terminal disabled
browser.navigate allowed
workspace.search redacted
patch artifact created

Full product scope

What Dvara is built to manage

Chat is the front door

Users speak normally to an LLM-backed chat. Browser, workspace, and patch work becomes governed action cards instead of hidden local execution.

Managed browser control

Dvara opens an isolated Chrome-compatible browser profile, navigates, searches, inspects, clicks, fills, types, presses, screenshots, and records artifacts.

Read-only workspace context

Agents can list, search, and read granted workspaces with path containment, blocked secret files, redaction, size limits, and audit-safe summaries.

Human-applied patch proposals

External clients propose patches as artifacts. The desktop UI validates paths and blocked files, previews diffs, and lets the user apply selected hunks.

One permission layer

Per-client tokens, durable grants, domain policy, emergency stop, and audit events keep Claude, Codex-style tools, Qwen, DeepSeek, and MCP clients inside the same control model.

Local audit trail

Tool requests, approvals, denials, failures, artifacts, and cleanup decisions are recorded locally so users can inspect what happened after the fact.

Trust boundaries

Expands LLM capability without silent takeover