Eva

Eva

An AI assistant that sees through your camera, controls your browser and desktop, remembers everything, and learns from experience. Local-first. Open source.

View on GitHub Download AppImage
# Linux or macOS
curl -fsSL https://appatalks.github.io/eva-agent/get-eva.sh | bash
Eva AI Assistant interface preview

What Eva does

Voice, vision, browsing, desktop control, memory, and autonomous task scheduling. No framework, no build step.

👁

Camera vision

Eva sees through your webcam. Face-detection auto-wake, on-demand "look" commands, ambient presence sensing. Frames stay local unless you ask her to describe what she sees.

🌐

Browser agent

Controls a real Chromium browser through the DOM. Persistent login, precise click-by-element, hybrid vision fallback. Shops, fills forms, navigates, pauses for confirmation on purchases.

🖥

Desktop control

Drives your actual mouse and keyboard to operate any application. Focus windows, open apps, click buttons. Optional AT-SPI semantic control via computer-use-linux MCP.

🎤

Voice-first interface

Full-screen voice orb with wake/barge-in, echo management, spoken progress narration. TTS via OpenAI, AWS Polly, browser, or Bark. Eva speaks her results, not just displays them.

🧠

Persistent memory

Kusto/ADX-backed conversation history, emotion tracking, knowledge graph, semantic recall. She remembers what you talked about last week and how you were feeling.

📚

Self-improving skills

Auto-extracts reusable skills from successful complex tasks. Skills are stored as drafts for review and applied automatically to matching future requests.

Cron scheduler

Schedule recurring tasks with standard cron expressions. Morning briefings, periodic market checks, nightly reports. Eva runs each prompt through ACP at the scheduled time.

🔀

Parallel subagents

Spawn up to 4 isolated subagent tasks that run concurrently. Results delivered via notifications. Break complex work into parallel streams.

🔌

Multi-provider

OpenAI, Google Gemini, GitHub Copilot, local models via lm-studio. Switch providers from a dropdown. No code changes, no lock-in.

🛡

Doctor diagnostics

Structured readiness report for every subsystem: ACP, browser, desktop, camera, Kusto, cron, cognition. Tells you exactly what's working and what needs fixing.

MCP ecosystem

Azure, GitHub, Kusto, and computer-use-linux MCP servers configurable from the UI. Extend Eva's capabilities with any MCP-compatible tool server.

🎯

Cognitive layer

Eva + Reviewer dual-agent pipeline with configurable models and max review cycles. Every response is drafted, critiqued, and refined before you see it.

How it's built

No build step. No framework. Pure HTML, CSS, and JavaScript in the browser, backed by a Python bridge that connects to any LLM provider.

Frontend

  • Vanilla JS, no build
  • Electron AppImage
  • Voice orb + chat UI
  • Settings panel
  • LCARS + Eva themes

Bridge

  • Python HTTP server
  • ACP / Copilot CLI
  • MCP server management
  • AIG orchestrator
  • Cron scheduler

Agents

  • Browser (Playwright)
  • Desktop (PyAutoGUI)
  • Camera (OpenCV)
  • Subagent spawner
  • Cognition pipeline

Storage

  • Azure Data Explorer
  • Kusto/KQL queries
  • Skills in ADX
  • IndexedDB sessions
  • Semantic embeddings

Eva vs the field

Eva Hermes Agent ChatGPT Desktop Claude Desktop
Open sourceYes (MIT)Yes (MIT)NoNo
Camera/visionBuilt-inNoNoNo
Browser automationBuilt-in (DOM + vision)Via MCPNoVia MCP
Desktop controlBuilt-in + MCPVia MCPNoVia MCP
Voice interfaceFull voice viewTranscription onlyYesNo
Self-improving skillsAuto-learnYesNoNo
Scheduled tasksCronCronNoNo
Persistent memoryKusto/ADXFTS5 + filesLimitedLimited
Multi-provider4+ providers200+ modelsOpenAI onlyAnthropic only
No build stepYespip installN/AN/A

Ready to try it?

One command. No API keys required to start.

Get started Report an issue