Log inSign up
Image
user avatar
EverMind
@evermind
Long-term agent memory | self-improving | agent harness github.com/EverMind-AI/Ev… github.com/EverMind-AI/Ra…
United States
evermind.ai
Joined November 2025
21
Following
4,266
Followers
AffiliatesRepliesArticlesMedia
  • user avatar
    EverMind
    @evermind
    4h
    Memory is the one layer of the agent stack observability can't see. EverOS speaks OTel natively now, so memory operation land in @langfuse: what got stored, what got recalled, how confident that recall was, how conflicting memories got merged, and what it cost. Stop guessing
    Image
  • user avatar
    EverMind
    @evermind
    Aug 3
    Yet another paper. This time, we asked a practical question: Do public SKILL.md files actually make agents better? The open skill ecosystem has a quality problem. The hard part isn’t finding more skills. It’s knowing which ones are unique, useful, safe, permissively licensed,
    Image
  • user avatar
    EverMind
    @evermind
    Aug 1
    DeepSeek-V4-Flash is already a first-class model in Raven 🐦‍⬛. Connect your DeepSeek API key and switch in one command: /model deepseek-v4-flash --provider deepseek Your tools, skills, working environment, and EverOS-backed memory stay with the agent. github.com/EverMind-AI/Ra…
    user avatar
    DeepSeek
    @deepseek_ai
    Jul 31
    🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇 🔷 The official V4-Flash now natively supports the
    Image
  • user avatar
    EverMind
    @evermind
    Aug 1
    Raven 🐦‍⬛ v0.1.10 is out. Choose from 21 providers, or search any provider LiteLLM can route to. Recognized deletion commands now ask for one-shot approval in the TUI. Each model call becomes a collapsible episode. Already using Raven? `raven upgrade` github.com/EverMind-AI/Ra…
    Image
  • user avatar
    EverMind
    @evermind
    Jul 30
    Our new paper. Self-evolving agents have a measurement problem. The hard part isn’t generating changes to an agent harness. It’s knowing which changes genuinely helped rather than got lucky, overfit, or never activated at all. LLMs diagnose failures and propose changes across
    Image