Voscko

[Voscko @Voscko]

@joshavant I've been contributing to it now and in contact with Obviyus on Discord :) got more ideas noted down, building and testing myself first before pushing it to github. Quality control for an app should be high.

[Voscko @Voscko]

@_HislilLustFoxy @OpenAI Stop this nonsense...

[Forum voor Democratie @fvdemocratie]

Sinds Pim Fortuyn wordt iedereen die de massale immigratie en de demografische transitie van ons land aankaart, zwartgemaakt en gedemoniseerd.

Het is tijd dat we dit patroon met elkaar doorzien en doorbreken.

Bekijk deze video en oordeel zelf! ⬇️

[Stephen Schoettler @SteveSchoettler]

🚀 hermes-lcm v0.16.0 is live!

Diagnostics release:
🩺 lifecycle fragmentation
📦 payload ref integrity
⏱️ summary timeouts

Update:
git -C ~/.hermes/plugins/hermes-lcm pull --ff-only

Thanks @Voscko

Bounded context, unbounded memory. Nothing is ever lost.

https://t.co/1U2ak2FtWV

[Voscko @Voscko]

@MatthewGunnin @supermemory @memdotai Using local models to embed and rerank? Or actually, how is your hindsight set up?

[Voscko @Voscko]

@cherry_mx_reds Wut? So realtime no longer available through sub?

[Stephen Schoettler @SteveSchoettler]

hermes-lcm v0.15.0 is out.

New in this release: a benchmark-backed codex_spark_context preset for GPT-5.3 Codex Spark, plus smarter preset suggestions for near-128k Codex-style routes.

Bounded context, unbounded memory. Nothing is ever lost.

https://t.co/Jha9lUr0GS

[Voscko @Voscko]

@thsottiaux @egorkabantsov Linux users please :(

[Stephen Schoettler @SteveSchoettler]

@Teknium @Voscko v0.14.1 is out.

Thanks to de-snake + ruangraung.

Active replay + DAG/session drift fixes.
Release stress checks.

git -C ~/.hermes/plugins/hermes-lcm pull --ff-only

Bounded context, unbounded memory. Nothing is ever lost.

https://t.co/Vz2ofnR0bP

[Voscko @Voscko]

@NetworkChuck No link in the comments xD

[Voscko @Voscko]

@cherry_mx_reds First impression?

[Voscko @Voscko]

@sierracatalina I AM NOT LISTENING

[Voscko @Voscko]

@rot13maxi @NousResearch @Teknium Can you maybe explain a bit more what you mean by dynamic workflows? Some ideas pop to mind but instead of assuming, I'd rather read what your thoughts are in this

[Voscko @Voscko]

@melvynx @sama

[Voscko @Voscko]

@thsottiaux These kind of posts are exciting! OpenAI cookin something

[Voscko @Voscko]

@SteveSchoettler @MatthewBerman 🤣

[Voscko @Voscko]

Please watch this if you need more info on what LCM is!! Thanks @SteveSchoettler for setting this up!

@Teknium @NousResearch please have a look!

[Stephen Schoettler @SteveSchoettler]

Made a new short explainer for Hermes-LCM using Manim skill.

Bounded context, unbounded memory. Nothing is ever lost.

[Stephen Schoettler @SteveSchoettler]

Today was bigger than a hermes-lcm release.

v0.14.0 lands with the Hermes Agent host contract LCM needed: 5 PRs folded into one, verified end-to-end.

Huge thanks to @Teknium for jumping in and landing the host side.

Credit to @Voscko for the earlier PR stack.

https://t.co/AaddUEa03T

[Stephen Schoettler @SteveSchoettler]

🚀 hermes-lcm v0.13.0 is live!

Thanks for 600+ stars.

🧠 Budget-aware assembly
🛠 Safer lcm_* diagnostics
🔒 Serialized SQLite writes

git -C ~/.hermes/plugins/hermes-lcm pull --ff-only

Bounded context, unbounded memory. Nothing is ever lost.

https://t.co/kfsIpgH3XG

[Voscko @Voscko]

@steipete Urgent PR: #87455 fixes a silent no-reply path in message_tool_only / source reply turns. If the assistant writes private final text instead of sending to the source chat, runtime now retries once via message(action=send), then fails visibly.

https://t.co/DBU62EU6tG