Identity Avatar
⚡ ava workspace github @kingstraps @kingfluxxx @kingchainz @kingclique @kingtraxxx @ss5.me
⚡ macOS Native AI Workspace

Ava Workspace Engine

Native macOS AI workspace for deep context analysis, dynamic DAG automations, GUI actions, and Model Context Protocol (MCP) tool integration.

View Repository on GitHub
Ava Terminal Interface
Ava Usage Analytics
Ava Build Mode Active
Ava Multimodal Voice Connected
Ava Cloud Repository Index
Ava Visual Pipeline Canvas
Ava Pipeline Automation Bar
Ava MCP Connector Hub
Ava Engine Capabilities Matrix
Ava Engine Config & Overrides

Built for Agentic Precision

Bridging desktop workflows with Google Gemini 3.7 models, live voice streams, and MCP servers.

🧠

Multimodal AI & Deep Research

Dynamic model toggling between 3.7 Flash for automation speed and 3.1 Pro for deep reasoning. Generates text, code, images, videos (Veo 3.1), and audio (Lyria 3).

🔲

Visual Pipeline Canvas (DAG Engine)

Build Directed Acyclic Graphs visually. Chain Input, AI Prompt, API Request, Python Code, MCP Tool, and Router nodes seamlessly.

🔍

Advanced Vector Retrieval & Grounding

Cloud vector store indexing (file_search_stores) with multi-query semantic expansion and chronological "Connect Dots" map-reduce re-ranking.

🔌

Model Context Protocol (MCP) Hub

Connect external stdio or REST/SSE MCP servers (Pythia Oracle, Financial Datasets, DeepWiki). Automates conversion into native Gemini function declarations.

🎙️

Multimodal Voice & Dictation

Native WebSocket integration delivering real-time speech-to-text dictation and duplex interactive voice communication with low latency.

⚙️

Desktop GUI Automation & Watchers

Integrated ScreenCaptureKit window capture for instant visual audits alongside directory drop-folder watchers that trigger visual DAG flows.

Engine Overrides & Telemetry

Model & Thinking Budget

Fine-tune reasoning turns with Min, Low, Med, and High thinking budgets directly per execution thread.

Retrieval & KB Depth

Configure vector search recall from 1 to 50 chunks with multi-query variations enabled on demand.

Token & Latency Tracking

Live telemetry displaying active request counts, total tokens consumed, time saved, and heaviest query profiles.

macOS Native Stack

Built with SwiftUI, SwiftData, AppKit, and ScreenCaptureKit paired with an async Python 3 backend engine.