What this means for you:

• Drop in any folder and Selene indexes it. Codebases, research papers, documents. Ask a question and get answers from your actual files, in seconds.
• Your prompts get better automatically. Before your message reaches the model, Selene adds the relevant context: code snippets, file references, your preferences. You type a simple question, the model sees the full picture.
• Lower costs. Tools load only when needed. The utility agent runs on a cheaper model. Your main agent's context stays clean.

Modes

Selene Dev

Everything you need to write and ship code, built into one place.

• Git, diffs, and PRs. See exactly what changed, stage files, create branches and worktrees, open pull requests. All from the UI or let the agent handle it.
• Built-in browser. Your agent opens your app in Chromium, clicks through pages, reads console logs, and catches issues. You can watch live or replay the session later.
• Output protection. When a build log or test output runs long, a bundled Rust tool trims it before it reaches the model. No more blown context from a noisy terminal.
• Automatic checks. Set up type-checking or linting to run after every code edit. Customize what happens before and after any agent action through hooks.

Selene Fun

Personal AI companions with personality.

• 3D avatar. Your agent gets a face. It lip-syncs when it speaks, and its expressions react to the conversation when emotion detection is on.
• Voice cloning. Make your agent sound how you want.
• Scheduled assistants. Create a tutor that sends quizzes to your Telegram every morning. Or a daily briefing that summarizes your tasks. Set the schedule, pick the channel, and it just runs.
• Agents that learn. Selene watches your conversations and suggests things to remember. You approve or reject from the memory page. Over time, the agent just knows your preferences.

Selene Work (coming soon)

Team agents for company workflows.

Channels

Connect your agent to your apps. Not through webhooks, as a native integration.

| Channel | Setup | What works | |---------|-------|------------| | WhatsApp | Scan a QR code | Messages, voice notes, attachments | | Telegram | Paste a bot token | Messages, voice bubbles, interactive buttons | | Slack | Socket Mode | Messages, files, native UI elements, threads | | Discord | Paste a bot token | Messages, threads, buttons, attachments |

Voice notes from WhatsApp and Telegram are automatically transcribed. When the agent replies with audio, Telegram users hear a native voice bubble. When the agent needs to ask a clarifying question, each app shows it in its own style: buttons, menus, or inline prompts.

Pair channels with the scheduler: set a task to run daily at 9am and have results delivered to your Telegram or Slack automatically.

Voice & Avatar

Talk to your agent. Choose from cloud or local speech-to-text, including a local option that supports 32 languages with no API key.

Hear your agent. Three text-to-speech providers, including a free one that's always available. Clone a voice to make it unique. Long responses get summarized before speaking so you get the gist, not a monologue.

See your agent. Turn on the 3D avatar and your agent speaks with a moving face. Enable emotion detection (off by default) and it reacts: smiles, looks thoughtful, shows surprise.

Quick voice actions. After you speak, run one-click actions: fix grammar, rewrite professionally, summarize, or translate.

Creative Tools

Images. Generate locally or through cloud providers. Pass in reference images for style matching, virtual try-on, or blending. Import custom image generation workflows and they become agent tools automatically.

Video. Turn session images into assembled videos with transitions, motion effects, and text overlays. AI plans the sequence, you get a rendered MP4.

Deep Research. Give the agent a question and it searches the web, reads sources, writes up findings with citations, and refines through multiple passes.

Memory

Your agents get better over time.

After conversations, Selene suggests memories like "user prefers TypeScript strict mode" or "always use pnpm." These show up on the memory page where you approve, edit, or remove them. Approved memories carry into every future conversation.

You can also just tell your agent: "remember that we deploy to Vercel," and it saves immediately.

Scheduler

Set tasks that run on their own: daily standups, weekly digests, code reviews, learning quizzes.

• Flexible timing. Cron, intervals, or one-time. Full timezone support.
• Deliver anywhere. Results go to WhatsApp, Telegram, Slack, Discord, or stay in the chat.
• Ready-made templates. Daily standup, weekly digest, code review, and more. Or create your own.

Extend It

Skills. Reusable instructions your agent can follow. 37+ ship out of the box: deployment, dev tools, productivity, creative tasks. Create your own from the UI.

Plugins. Bundle multiple skills and tools together. Install from GitHub or a URL.

MCP. Connect externa