Observe
Read within approved paths, inspect runtime status, and reason. No desktop mutation.
Local inference / Windows + browser
DjenisAiAgent reads the current interface, asks a model running on your machine for one bounded action, and checks the result before moving on. No provider key, remote-model fallback, or hidden runtime download.
01objective
02observe
03act
04verify
05finish
01 / System
The loop stays deliberately legible. Screenshots and accessibility data go only to the configured local endpoint; the model returns one structured function call; the host executes only what the active runtime and permission tier expose.
Architecture
Capture the screen and a structured UI snapshot.
Ask the pre-provisioned local model for exactly one declared function call.
Run a tool allowed by the runtime and operator policy.
Feed the outcome into the next turn before claiming success.
02 / Guided demo
This deterministic walkthrough runs entirely in your browser. It demonstrates the orchestration contract; it is not connected to a live desktop or model server.
“Open Calculator and evaluate 12 × 8.”
The operator defines one bounded outcome. The task starts with no implied permission to write files or run shell commands.
Capability matrix
03 / Security model
The default tier can inspect approved files and reason about the current state. Interaction and system control are separate opt-ins. In Docker, agent and model stay internal; a hardened loopback gateway exposes the console, while browser egress remains separate.
Read within approved paths, inspect runtime status, and reason. No desktop mutation.
Use approved UI and browser controls without unlocking shell or file writes.
Shell, file writes, app launch, and saved screenshots require the system tier plus explicit dangerous-action confirmation.
04 / Install v0.3.0
The v0.3.0 web and remote-browser runtime is distributed as a container image through GHCR. There is no desktop installer or downloadable release archive. The canonical release guide provides the source-bound Compose files, immutable image digest, and explicit model-provisioning command.
Check the host. You need Docker Compose and enough local capacity for the model and its configured context window.
Follow the exact release guide. Fetch the Compose definition from its authorized source commit and select the verified GHCR digest.
Provision, then start. Pull the model through the one-time provisioning profile, launch the full stack, and wait for /ready before enabling interaction.
The walkthrough above explains the orchestration contract. Use the Compose stack for the authenticated web console and remote browser. For Windows-native desktop control, clone the exact release with git clone --branch v0.3.0 --depth 1 https://github.com/ejupi-djenis30/DjenisAiAgent.git, then follow its Windows quick start.