GitHub - AnthonyRonning/sage

kept by eddie feb 10

Sage is an experimental, self-hosted AI assistant with persistent memory, encrypted messaging via Signal or Nostr, and confidential LLM inference inside a TEE.

Signal leaders warn agentic AI is an insecure, unreliable surveillance risk
Signal leaders warn that agentic AI systems are inherently insecure, unreliable, and pose a surveillance risk.
also on Signal, #privacy
The Shapes of Agent Memory – Files, Stores, and Experience
Structured stores beat file memory on accuracy and token cost; files win only for small memories or 'I don’t know' answers, and trained experience helps weak models only.
also on Letta, #developer-tools
Your harness, your memory
Agent harnesses are deeply tied to agent memory, and using a closed one cedes control of memory to a third party, creating vendor lock-in that open harnesses avoid.
also on Letta, #developer-tools
Maybe we don't need a server
Syncthing syncs files directly between devices without a server, and the author imagines a future where calendars, contacts, and email are just synced files.
also on #self-hosting, #privacy
ONCE is back! It's now a full-fledged application server for running dockerized web apps, like Campfire/Writebook/Fizzy or your own vibe-cod
Basecamp releases ONCE as a full application server for dockerized web apps with zero-downtime upgrades, scheduled backups, and a TUI interface.
also on #self-hosting, #developer-tools