Alma by Olivares.AI ✓

Alma v21 — Background Agents, a Notion-style Workspace, and Every Source You Already Use

Alma is no longer just a chat. Background agents now run multi-step research, monitor sources, process batches and ship scheduled reports — while you do something else.

A new Notion-style workspace lands with nested pages, rich blocks, slash commands and embedded databases you can view as tables, boards, calendars or galleries.

Connect Google Drive, Gmail, Notion, iCloud, Fastmail, Nextcloud, IMAP and any REST endpoint, and Alma builds memory from the documents that matter to you. Magic-link and Apple sign-in join the front door. The whole product wears a refined, calmer look.

Background agents — work that runs while you do not
Four autonomous workflows: Research (multi-step web research with citations), Monitor (watch sources, ping when something changes), Process (long-running batch transformations), Report (scheduled deliverables like weekly digests).
Brief any agent in plain English; Alma classifies the intent and shows a transparent cost estimate (median + P95) before anything runs.
Agents share your monthly budget — no per-agent subscription, no separate credit currency.
Predictable lifecycle: queued, running, paused, waiting on user, waiting on budget, completed, failed, cancelled — you always know where a job stands.
A critique step on Max double-checks every report before it lands in your inbox, and revises automatically when something is off.
Agents read your memory layer, so they pick up your context, your tone and your priorities without re-briefing every time.
A Notion-style workspace inside Alma
Rich block editor: paragraphs, headings, bullet and task lists, toggles, callouts, code blocks, quotes, images, files, tables and dividers.
Slash commands and drag-and-drop reordering.
Nested pages up to three levels deep, sidebar tree, breadcrumbs, instant search across titles and body.
Embedded databases with table, board, calendar, gallery and list views — filter, sort and group without writing a query.
Memory blocks and agent output blocks live inside the same pages — what Alma knows and what Alma produces share a single canvas.
Existing notes migrate automatically. Nothing to redo.
Every source you already use
WebDAV providers: iCloud Drive, Fastmail Files, Nextcloud, Box, Apache, any standards-compliant server.
IMAP for any email provider.
Custom REST endpoints when your data lives in a private API.
Email-to-Alma forwarding alias: send anything from any inbox to your personal alias and Alma ingests it (signature checks and sender allowlist enforced).
Per-source agent templates — Drive, Gmail and Notion each get a hand-tuned briefing so retrieval is calibrated for that source.
Sign in your way
Magic-link sign-in is the new default — one-time link by email, no password.
Apple Sign-In joins Google and GitHub.
Password remains optional: enable or disable from Settings → Security at any time.
Two-factor (TOTP) and recovery codes apply to every method.
Voice that actually talks back
Conversational voice mode with natural turn-taking, interruption-aware, low-latency.
Pause and resume the mic without losing the session.
Mobile haptics on key interactions where the device supports them.
Battery-aware: voice degrades gracefully in low-power mode.
Notes & Calendar in the same workspace
View, create and reschedule events from chat or directly in the calendar grid.
Google Calendar two-way sync with conflict resolution.
CalDAV support for iCloud, Fastmail, Nextcloud, GroupWise.
ICS subscription for read-only feeds (public calendars, sports schedules, shared work calendars).
Per-calendar colour overrides and a connector health badge.
Smarter, faster memory retrieval
Hybrid memory search blends semantic and keyword rankings with a rank-fusion algorithm — better matches on long, conversational queries.
Procedures (saved how-to steps) gained their own semantic index — they surface even when the wording does not match.
Embedding layer hardened with retry, dimension health checks and a transparent fallback path.
Smart context caching expanded across chat, extraction and embeddings — repeat context is virtually free on follow-up turns.
Studios — image, video and music polish
Image Studio: upscale, in-paint canvas, bulk generation up to 8 variants, ETA bar.
Video Studio: backend ETA, 6 starter templates, batch queue, drag-and-drop scene stitching, YouTube preview modal.
Music Studio: studio-grade tracks up to 10 minutes with vocals and lyrics, all on the unified monthly budget.
Favorites across all studios — keep your best generations one click away.
Better organisation across the workspace
Folders nest up to three levels, with smart criteria, archive and reorder.
Bulk actions on conversations: move, archive, delete, tag.
Default folder per environment.
Pinned and starred items move to the top automatically.
Bring your own providers — BYOK on Max
Seven providers supported: Anthropic, OpenAI, Replicate, Leonardo, ElevenLabs, Google AI, Azure OpenAI.
Health dashboard with reachability and per-provider usage trends.
Calls billed to your own provider account — they do not consume your Alma monthly budget.
Encryption rotation built in.
A refined look across the product
Dark mode rebuilt around a calm, neutral palette — Alma orange remains the single accent.
Light mode keeps the warm ivory you know, with neutral text and tighter contrast for long sessions.
Softer corners on buttons and cards.
Marketing pages — landing, pricing, agents, philosophy, FAQ — rewritten to match.
A smoother mobile experience
Safe-area handling improved on iPhone notch and Dynamic Island devices.
Offline state, visibility changes and slow networks handled gracefully.
Modal sheets and overlays respect device chrome.
Faster initial paint thanks to lazy-loaded language packs and route-level code splitting.
International checkout
Polar Software, Inc. is now our Merchant of Record — VAT, sales tax and FX handled for you.
Local currency at checkout: USD, EUR, GBP, CAD, CHF, AUD, JPY, NOK, SEK, SAR, QAR.
Card and digital wallet support.
Customer portal for subscription, invoices and top-ups without a support ticket.
Onboarding & Skills
Six-step onboarding captures your role, your style and your goals — turned into a starter Soul block automatically.
Skills sheet shows what each skill does, what tools it adds, and which plan unlocks it.
Skills preview their tool effect before you switch.
Import what you already have
ChatGPT, Claude and Gemini exports with live preview before commit.
Streaming progress while large imports run in the background.
Automatic deduplication against your existing memory store.
ZIP archive support for bulk imports across multiple sources.
Hardened against abuse
CAPTCHA on forgot-password, reset-password and magic-link requests.
Per-email and per-IP rate limits on every authentication endpoint.
Single-use, short-lived magic-link tokens — no replay, no leakage by URL sharing.
Same anti-enumeration guarantees on every auth surface.
Pricing
Starter $14 · Pro $29 · Max $99 — one monthly budget per plan, no add-ons, no surprises. Max unlocks BYOK, native web search and the Critic step on agent reports.

Try it: https://alma.olivares.ai

Three Plans, Smarter Chat, Deeper Memory

Simplified from seven plans to three: Starter, Pro and Max.
Every paid plan includes a single weekly USD budget that covers chat, voice, images, video and music from the same pool.

Under the hood, chat and memory received major upgrades: adaptive reasoning on the top tier, parallel tool execution, web citations on Max, more accurate memory retrieval, and support for conversations that stretch across hundreds of turns. Top up any time. Memory, images, voice, video, studio-grade music, code, writing tools, web search and export are all included on every paid plan — nothing to bolt on.

Annual billing saves two months. Your data is preserved indefinitely — cancel any time and resume exactly where you left off.
Three plans, one budget
·Starter — persistent memory with Haiku and Sonnet, all tools, web + mobile apps
·Pro — adds the top reasoning tier (Claude Opus), video, studio-grade music and a larger weekly budget
·Max — everything in Pro plus the full developer surface: API keys, VSCode extension, MCP server, JavaScript SDK and BYOK support
·Annual billing on every plan: pay ten months, get twelve — two months off for the year
·A single USD pool per week covers chat, voice, images, video and music. Resets every Monday 00:00 UTC
Top-ups when you need more
·Top up when the weekly pool runs low and you opt in — nothing auto-charges
·Top-up balance expires 12 months after purchase and is consumed in FIFO order
·Usage breakdown by category (chat, image, voice, video, music) visible in Settings → Billing
Your data stays, no matter what
·Every memory, conversation and file is preserved indefinitely — no purge on cancellation
·Read-only access to everything you created, even without an active subscription
·Resubscribe any time and resume exactly where you left off
·Full export at any time: JSON, .alma, PDF, DOCX, XLSX, HTML and Markdown
Cleaner product surface
·Consolidated seven legacy plans down to three — less decision fatigue, clearer trade-offs
·Music and video integrated into the same weekly budget — no separate add-on subscriptions
·Pricing page rewritten with a compact plan grid, full feature comparison and top-up preview
·Settings → Billing shows live weekly budget, category usage and one-click top-ups
Developer surface on Max
·Programmatic API with X-API-Key authentication
·VSCode extension and MCP server (Claude Desktop, Cursor, Windsurf)
·JavaScript SDK published to npm (@olivaresai/alma-sdk)
·Bring Your Own Key (Anthropic, Replicate, Leonardo AI) — your BYOK calls do not consume your Alma budget
Smarter, faster chat
·Follow-up messages land noticeably faster — shared context is cached across turns
·Parallel tool execution: Alma can run several memory lookups, web searches or fetches at the same time
·Conversation titles generated inline while the first response streams, not after it finishes
·Adaptive reasoning on the Complex tier — Alma thinks deeper on hard questions and stays quick on easy ones, during both tool selection and final reply
Web citations on Max
·Max now uses Claude's built-in web search — every result comes back with structured source citations
·Citations appear as clickable chips below the reply, linking straight to the original page
·Works alongside the existing web search available on all paid plans — Max simply adds the native citation layer
Memory upgraded
·Smarter retrieval: top candidates are re-ranked so the most relevant memory surfaces first
·Semantic search extended to saved procedures — triggers and actions, not just facts
·Automatic retries on transient backend failures so a flaky network does not drop a memory query
Longer conversations without drift
·Conversations stay coherent across hundreds of turns — older tool activity compacts automatically
·Reasoning state carries across tool iterations on the Complex tier
Polished model picker
·Tiers renamed Fast, Advanced and Complex — aligned with the real capability of each model
·Your default model preference lives in Settings and follows you to every new conversation on every device
·1,000,000-token context window on the Complex tier — entire codebases or long documents fit in a single thread
Reliability
·All built-in tools ship with strict schemas and inline examples — fewer malformed calls, faster recovery
·Attachments deliver faster in chat — lower latency and larger effective size

Alma Creator — Everything you need to create — one plan.

What's new:

Alma Creator plan ($89/mo) — AI chat with persistent memory, video generation, music studio, image creation, and 12 creative tools in a single subscription. No separate add-ons.

Creator Max plan ($189/mo) — 3x AI capacity, 480 video credits/month, 25 minutes of music/month. For professionals who need more.

Music Studio — ElevenLabs Premium — Studio-grade AI music generation. Up to 10 minutes per track. Vocals, custom lyrics, instrumentals. 30-second to 10-minute tracks in any genre.

Music Studio — MiniMax Music — Quick music generation included in Pro+ plans. Up to 4 minutes with vocals. 12 genres. No add-on required.

Avatar Videos — HeyGen Avatar IV — Generate talking-head videos with AI avatars. Searchable avatar gallery, voice selection with preview, custom scripts.

Video Studio — Text to Video — Generate videos directly from text prompts. No source image needed. 12 cinematic styles, 12 camera movements.

Image Studio — Dual models — Leonardo AI and Flux Pro. 10 style presets (Natural, Cinematic, Photography, Anime, Pixel Art, Watercolor, 3D, Sketch, Neon, Minimalist).

Public image sharing — Share any generated image via public link with full prompt visible. Recipients can download or generate their own version.

Creator landing page — Dedicated page at olivares.ai/creator with full feature comparison, pricing breakdown, target audience guide, and FAQ.

Annual billing — 10% discount on all plans. Creator annual: $80.10/mo. Creator Max annual: $170.10/mo.

Unified credit system for video — One credit pool that works across Gen-4 Turbo and Gen-4.5. Users choose quality vs quantity per generation.

Tracks in Music History — Play, download as MP3, copy prompts to iterate. Both ElevenLabs and MiniMax tracks in one library.

Complete UI redesign — clean, minimal interface with no clutter. Desktop header removed for full-screen workspace. Dark and light themes refined.

Audio Studio — Generate music with AI. 12 genre presets (pop, rock, electronic, jazz, ambient, lo-fi, cinematic, and more), 3 duration options. Listen, download, and iterate.

Video Studio — Create professional videos with Runway Gen-4. Scene planner, project management, and video stitching. Separate subscription available.

Image Studio — AI image generation with Flux Pro. Style presets, OCR text extraction, full interface visible to all users.

Conversation Manager — Dedicated page to organize all your conversations. Create folders with colors, assign tags, pin important chats, bulk select, search, and sort.

Context Documents — Upload text files, notes, or reference material that the AI reads in every conversation. Global documents (Soul-level) apply everywhere. Folder documents apply only to conversations in that folder.

Code Workspace — AI-powered development environment with 8 skills: explain, refactor, review, test, fix, document, search, and commit. File tabs, markdown preview with live split view, syntax highlighting.

Soul Engine — 12 configurable identity blocks that define your AI's personality, rules, communication style, and expertise. Knowledge Vaults for pre-built configurations.

Demo Video — New /demo page with a 4-minute walkthrough showing every feature in action with real usage.

35 MCP Tools — Connect Alma to Claude Desktop, Cursor, or any MCP-compatible AI tool. Memory, chat, code workspace, video generation — all as native tool calls.

15 Languages — Full professional translations. Spanish reviewed word by word. Arabic, Chinese, Japanese, Korean, Hindi, and 9 more European languages.

Command Palette — Press Cmd+K to navigate anywhere instantly. Quick access to every page and feature.

Smart Budget System — Shared weekly budget across chat, images, audio, and video. Real-time usage tracking. Credits valid for 12 months.

Privacy & Security — PBKDF2-SHA512 passwords, AES-256-GCM for API keys, 15 security audits completed, GDPR compliant, full data export.

Every detail matters.

Full changelog: olivares.ai/changelog

olivares.ai/demo

alma.olivares.ai