An AI assistant that sees through your camera, controls your browser and desktop, remembers everything, and learns from experience. Local-first. Open source.
After installing, Eva is available as a system command and shows up in your application launcher.
Open any terminal and type:
The installer adds eva to ~/.local/bin. It launches the Electron app if built, or starts the bridge and opens your browser.
Search for Eva in your desktop's application menu (GNOME Activities, KDE Kickoff, Rofi, etc.).
The installer creates a .desktop entry with Eva's icon so she appears alongside your other apps.
Voice, vision, browsing, desktop control, memory, and autonomous task scheduling. No framework, no build step.
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.
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.
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.
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.
Local SQLite or Kusto/ADX-backed conversation history, emotion tracking, knowledge graph, and semantic recall. She remembers what you talked about last week and how you were feeling.
Auto-extracts reusable skills from successful complex tasks. Skills are stored as drafts for review and applied automatically to matching future requests.
Schedule recurring tasks with standard cron expressions. Morning briefings, periodic market checks, nightly reports. Eva runs each prompt through ACP at the scheduled time.
Spawn up to 4 isolated subagent tasks that run concurrently. Results delivered via notifications. Break complex work into parallel streams.
OpenAI, Google Gemini, GitHub Copilot, local models via lm-studio. Switch providers from a dropdown. No code changes, no lock-in.
Structured readiness report for every subsystem: ACP, browser, desktop, camera, Kusto, cron, cognition. Tells you exactly what's working and what needs fixing.
Azure, GitHub, Kusto, and computer-use-linux MCP servers configurable from the UI. Extend Eva's capabilities with any MCP-compatible tool server.
Routine requests stay fast on Eva's selected model. Consequential turns receive a one-pass independent review before delivery.
No build step. No framework. Pure HTML, CSS, and JavaScript in the browser, backed by a Python bridge that connects to any LLM provider.
A capability snapshot based on publicly documented product features. MCP and custom integrations can extend several products beyond their built-in experience.
| Eva | Hermes Agent | ChatGPT Desktop | Claude Desktop | GitHub Copilot app | |
|---|---|---|---|---|---|
| Open source | Yes (MIT) | Yes (MIT) | No | No | No (public repo) |
| Camera/vision | Built-in | No | No | No | Not documented |
| Browser automation | Built-in (DOM + vision) | Via MCP | No | Via MCP | Via MCP |
| Desktop control | Built-in + MCP | Via MCP | No | Via MCP | Via MCP |
| Voice interface | Full voice view | Transcription only | Yes | No | Not documented |
| Self-improving skills | Auto-learn | Yes | No | No | Custom skills |
| Scheduled tasks | Cron | Cron | No | No | Automations |
| Persistent memory | Local SQLite or Kusto/ADX | FTS5 + files | Limited | Limited | Session history |
| Offline/local operation | LM Studio + direct MCP | Self-hosted + local models | Cloud service | Cloud service | Local workspace, cloud models |
| Memory deployment choice | Local SQLite or ADX | Local FTS5 + files | Managed | Managed | Session history |
| Multiple local user profiles | Separate sessions + settings | User modeling | Account-based | Account-based | Account-based |
| Outbound messaging | Signal delivery | Signal + 5 other channels | Not documented | Slack integration | Not documented |
| Local voice cloning | Automatic English/Korean + imported profiles | TTS + transcription | Voice conversations | Not documented | Not documented |
| Generated files & artifact workspace | PDF/MD/CSV/JSON/TXT + Assets | Via tools/filesystem | Downloadable files | Creates files | Canvases + workspaces |
| System diagnostics | Subsystem doctor | Hermes doctor | Not documented | Not documented | Debug logs |
| Review/validation loop | Configurable Eva + Reviewer | Delegated agents | Not documented | Not documented | Built-in validation loop |
| Multi-provider | 4+ providers | 200+ models | OpenAI only | Anthropic only | Multi-model + BYOK |
| No build step | Yes | pip install | N/A | N/A | Desktop install |
One command. No API keys required to start.