Sabitlenmiş Tweet
Honcho
562 posts
Honcho
@honchodotdev
Continual learning for stateful agents. SOTA & pareto dominant—accuracy, speed, cost, efficiency. Memory that reasons. Built by @plasticlabs.
https://discord.gg/honcho Katılım Nisan 2025
12 Takip Edilen2.6K Takipçiler
@noestelar Of course!
Feel free to join our discord for help too: discord.com/invite/honcho
English
@honchodotdev Honestly that post converted me to try it. Thanks for the free $100
English
🫡👇
Erick@ErickSky
🚨Si usas Hermes (y sino, ya deberías), esto te podría interesar: Unos gringos se pusieron a hablar en uno de mis posts y me dio curiosidad. Fui a ver y terminé probando Honcho (@honchodotdev). Es una herramienta Open Source que le da memoria infinita al agente: realmente razona, entiende contexto y personalidad. Promete que Hermes recordará TODO, mantendrá consistencia e irá mejorando solo. Lo loco: sale en $2 al mes (usado para el razonamiento, el almacenamiento es gratis). Hay un montón de gente usándolo para tener literalmente memoria infinita en el agente que está provocando que muchos abandonen OpenClaw. ¿Por qué nadie antes lo había posteado antes?? REPOOO👇
ART
The best thing? Honcho gets even better long term.
stableAPY.hl@stableAPY
@3rosika feels like it helps a lot! Hermes has stopped forgetting stuff it used to before, let's see over the weeks
English
@CHRISM4FIA @adamdbrown @KJJKETH @ErickSky @NousResearch @Teknium Excited for you to try it! Real memory makes a difference
English
@adamdbrown @KJJKETH @ErickSky @NousResearch @Teknium @honchodotdev Just set this up and got the $100 free credit while I work on my OpenClaw transfer
Moving to self host after just wish I could run this on my Jetson Orin
English
🚨 HERMES WORKSPACE YA ESTÁ AQUÍ
El tocayo construyó el UI nativo que Hermes Agent (@NousResearch @Teknium) siempre merecía… ¡y con acceso móvil desde el celu! 📲
Esto trae todo:
💬 Chat con tools ejecutándose en vivo
🖥 Terminal integrada
📦 Browser de +90 skills
🧠 Memory viewer
📂 File explorer
🎨 8 temas (dark + light)
⚙️ Config completa de modelos
Todo limpio, rápido y hecho para builders serios.
Open source total, creado para el hackathon de Hermes.
@outsourc_e se mandó una bestialidad con la que deberías aprovechar para usar este agente.
¡NO QUIERO QUE TE QUEDES ATRÁS!
REPOOO👇
Español
@KJJKETH @adamdbrown @CHRISM4FIA @ErickSky @NousResearch @Teknium honcho is soc 2 compliant! you can also self-host
look out for lots more on the privacy and security roadmap
English
@adamdbrown @CHRISM4FIA @ErickSky @NousResearch @Teknium @honchodotdev Data security risk as well as a continuity risk
English
Honcho retweetledi
@KJJKETH @CHRISM4FIA @ErickSky @NousResearch @Teknium try @honchodotdev - memory problem solved forever, Also having shared memory between my Claude Code and my amazing Hermes is a huge win for me. Openclaw was a fun dev/troubleshooting experiment for me- Hermes does real work.
English
Happy to provide SOTA memory layer for multi-agent stacks 🫡
mcray@mcray69
Claude Dispatch changed my whole setup for good (only downside is I'm stuck with Anthropic which I don't mind since I'm running two 200usd MAX subscriptions) Basically I run a Mac Mini that has: 1. Claude Code + VS Code 2. Claude Dispatch 1st is for deep work sessions -- I SSH in from my MacBook via VS Code Remote and work on projects with Opus as my orchestrator + Sonnet sub-agents executing in parallel -> Deep work only. 2nd is for autonomous background ops -- order fulfillment pipelines, multi-channel OMS syncing, email labelling, customer service, and backtesting overnight -> It just works 24/7 while I sleep Access it from anywhere: Phone → Telegram bot for quick tasks and alerts Phone → Claude Dispatch for async workflows MacBook → VS Code Remote SSH for full deep work sessions Any device → Tailscale mesh. Always connected, always running. Both share the same memory layer (@honchodotdev) so there's no signal loss between sessions. One brain, two modes: hands-on and hands-off.
English
Honcho retweetledi
i 👁️ @honchodotdev ! hermes v0.3.0 is out & i'm thrilled to be a contributor, giving the best memory to the best agent . 🫡🪽
Nous Research@NousResearch
Hermes Agent v0.3.0 ☤ 248 PRs. 15 contributors. 5 days. • Real-time streaming across CLI and all platforms • First-class plugin architecture, package and share tools+commands+skills • /browser connect to live Chrome via CDP • @vercel AI Gateway model provider • @browser_use browser tool provider • VS Code, Zed, and JetBrains integration • Voice mode with local Whisper • PII redaction everywhere 9 new skills. 50+ bug fixes. Much more in the full changelog.
English
@twistedmatrices Your account starts with 100$ of credits! Feel free to dm us with your specific use case if that's not enough!
Find us on our Discord: discord.com/invite/honcho
English
@honchodotdev Can i have like $200 to try this out? I really don't want to roll my own and have to OS it...
English
Honcho retweetledi
who are some peeps doing cool stuff around memory?? top of mind i could think of are zep, mem0, supermemory
English
@SALTY_ALTY555 @NousResearch Awesome! Excited to see it. Feel free to join our discord if you have any questions: discord.com/invite/honcho
English
@honchodotdev @NousResearch Local hosting options ftw. Very cool system, my biz partner has been getting it set up.
English
Honcho retweetledi
Honcho retweetledi