Attached: 1 image #PeerSky v1.0.0-beta.24 is here! - 🧠 Your local AI conversations now remember context across all P2P apps, building smarter interactions over time Enable at peersky://settings/llm -> Enable LLM Memory - 🪟 Split View: Right-click any tab -> Split View -> Open any tab side-by-side for multitasking, with adjustable resizing. AI is optional, not forced ;)
While Distracted by AI: The Quiet Rise of Local-First Software
My multi-user + AI agents p2p collaboration app is starting to take shape! Automerge and Iroh are a joy to work wth. #localfirst #cloudless #rust #WIP #learnbybuilding youtu.be/JSqCABm8UQU
Basic Memory
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
Peersky Browser (@peersky@mastodon.social)
Attached: 1 image 💬#PeerSky v1.0.0-beta.23 is here! Introducing #PeerChat, a chat that lives on your machine, not a server! - Create rooms for friends or teams with a name, bio, link, and avatar - Direct Messages: start private chats instantly with automatic key sharing - Real-time chat with live updates, emoji reactions, and unlimited file attachments Try it out! 👉 https://peersky.p2plabs.xyz/ Source: https://github.com/p2plabsxyz/peerchat
Memora scales agent memory to boost long-horizon productivity
AI agents can't remember past conversations. They must constantly reload or retrieve context, which grows less efficient as tasks get longer and more complex. Memora solves this with a scalable memory system separating what’s stored from how it's retrieved.
Peersky Browser (@peersky@mastodon.social)
Attached: 1 image 📝 v1.0.0-beta.20 — Introducing P2PMD A real-time peer-to-peer Markdown editor for notes and collaboration that syncs directly between peers, with no servers in the middle. Release: https://github.com/p2plabsxyz/peersky-browser/releases/tag/v1.0.0-beta.20 #PeerSky #p2pmd #markdown
Limit - Social Bookmarks (@limitapp.bsky.social)
A purposefully constrained Bluesky client for #ios. It remembers your position in the timeline. #AI features - AI timeline, AI post explanation, AI article summarization App store: https://apps.apple.com/us/app/limit/id6748037680 And it’s open source.
Peersky Browser (@peersky@mastodon.social)
Attached: 1 image ✨ PeerSky v1.0.0-beta.21 is here! We've rolled out a complete UI revamp - Customizable P2P Bar: organize your peer-to-peer apps your way Protocol: - Faster p2pmd: syncs seamlessly with CRDT updates for smooth multi-peer collaboration - Hypercore large file upload and streaming performance fixes - Drag-and-drop .torrent file support via magnet URI Full release notes here: https://github.com/p2plabsxyz/peersky-browser/releases/tag/v1.0.0-beta.21 #PeerSky
Supermemory
The memory layer for AI agents. Context engineering platform powering enterprise APIs, developer plugins, and a personal app that remembers everything.
Use Claude’s chat search and memory to build on previous context | Anthropic Help Center
You can prompt Claude to search through your previous conversations to find and reference relevant information in new chats. Claude can also remember context from your chats and carry it into new conversations and Cowork tasks. This article explains how chat search and memory work, what Claude does and doesn't remember, how to review and edit what's saved, and how to turn these features on or off.
Peersky Browser (@peersky@mastodon.social)
Attached: 2 images ⚡v1.0.0-beta.22 is here! Meet the new Peers Dashboard in P2P Markdown: - Track live editing status in real time - See who’s in the room with host/client roles - View Edit History for better collaboration context Try it out! #PeerSky
Shlok Khemani on Twitter / X
Super interesting that eve doesn't ship with any long-term or cross-session memory (yet). The main context-management lever out of the box is conversation compaction. This is unlike OpenClaw and Hermes, each of which comes with a default opinionated memory implementation. https://t.co/DDIyc4rFtW— Shlok Khemani (@shloked) June 17, 2026
Atomic Chat: Free Local AI Chat for Mac, Windows & iPhone | Private & Offline
Free, open-source local AI chat for Mac, Windows & iPhone. Run Gemma, Qwen, DeepSeek, Llama offline. 1,000+ models, no cloud, no subscription. Download free.
Download | Tiles
Tiles is a local-first AI assistant that runs models on your device, syncs privately across devices, and lets you share chats through AT Protocol.
Introducing the OpenMemory Chrome Extension
AI memory Chrome extension for LLM memory and retrieval augmented generation. OpenMemory enables persistent AI agent memory across web browsing sessions.
Scott Jenson — How the Desktop UX needs to evolve to keep up with Local-first