LoginSign Up
← Back to all sparks
R

Recall

AI-ASSISTANTS
Velocity6.3

AI-powered knowledge tool that summarizes and organizes online content into a connected knowledge base.

www.getrecall.ai ↗

After Recall 2.0, the second-brain iterates fast on sources, voice, and control

knowledge-managementai-chatsecond-brainpersonascontent-capturemcp
◆Current state
Since April's Recall 2.0 relaunch — agentic chat, an API and MCP, and the Max tier — the product has been in rapid iteration. It has widened what it can ingest (Instagram, LinkedIn, Apple News, text/Markdown), added Listen Mode voice playback, and now Custom Personas that pin how the AI behaves. The consistent thesis is knowledge-first AI: your saved sources come before the open web.
◆Where it's heading
Recall is layering reach and control onto its chat: more sources in, more ways to steer the AI (personas, multi-step actions), and more model choice (Opus 4.8, GPT-5.5). Release notes point toward public profiles, sharing, and a write API as the next expansion beyond personal capture.
◆Prediction
Based on the roadmap notes threaded through these releases, expect public Recall profiles and shared collections, plus a write/bulk-ingest API, to be the next headline moves.

◆Recent moves

  1. 8d ago

    Instagram and LinkedIn saving, plus text and Markdown uploads

    Broadens what Recall can capture — Instagram and LinkedIn posts plus text/Markdown uploads — feeding the knowledge-first thesis that your own sources should come before the open web.

    View source ↗
  2. 16d ago

    Custom Personas: save AI instructions once and reuse them

    ⚡ SPARK

    Custom Personas make the AI's behavior persistent and repeatable across Recall's surfaces — a step from chat-with-your-notes toward tuned, specialized assistants, and the clearest post-2.0 investment in steering the AI.

    View source ↗
  3. 19d ago

    Date grouping, Apple News saving, and passwordless sign-in

    A cluster of quality-of-life additions — home-page date grouping, Apple News saving, passwordless sign-in — plus fixes; incremental polish on the 2.0 base.

    View source ↗
  4. 1mo ago

    Multi-select cards to export or chat across them at once

    Multi-select lets users export or chat across several cards at once, making cross-note reasoning easier — a natural extension of the agentic-chat core.

    View source ↗
  5. 1mo ago

    Claude Opus 4.8 for Max, plus in-app help and bug reporting

    Brings Claude Opus 4.8 to the Max tier and adds in-app help and bug-report flows — a model refresh and support polish rather than a new capability.

    View source ↗
  6. 1mo ago

    Pop-up browser extension returns, with multi-step AI actions

    The pop-up browser extension returns for broader browser support, bundled with multi-step AI actions that plan then let you approve each step — agentic depth arriving through the capture surface.

    View source ↗