This is a submission for the Hermes Agent Challenge
I'll be honest — I was skeptical.
Every few weeks something in the AI space gets described as "turning heads quietly" and it turns out to be a wrapper around the OpenAI API with a nicer README. So when Hermes Agent started showing up in my feeds with that kind of language, I filed it under probably fine, not urgent and moved on.
Then it crossed 95,000 GitHub stars in seven weeks. That's not hype-shaped. That's word-of-mouth shaped. So I actually installed it.
This post is about what I found.
The problem it's solving (which is real and annoying)
Here's a thing that happens to me constantly. I open an AI assistant, spend the first few minutes re-establishing context — my stack, my project names, my preferences — get into a groove, do good work, close the session. Next day: blank slate. I'm typing the same paragraph again.
It's not a dealbreaker. It's just... friction that compounds. Over weeks it starts to feel like working with a very talented colleague who has anterograde amnesia. You like them. You just have to brief them every single morning.
Most agents acknowledge this problem by shipping a vector database and calling it "long-term memory." Which is fine. Vector search is genuinely useful. But it's passive — you query it, it retrieves, nothing actually changes. The agent doesn't learn anything. It just has better notes.
Hermes Agent is built around a different idea entirely.
What actually makes it different
The core insight is distinguishing between two kinds of memory:
Episodic — what happened in past conversations. Hermes stores this with SQLite FTS5 (full-text search), not vector embeddings. That sounds like a step backward and I thought so too at first. But keyword search has real precision advantages for the stuff that actually matters in developer workflows: project names, service names, variable names, team-specific terminology. If I mention "Gatekeeper" (our auth service) in session 12, Hermes finds it when I mention it in session 89. Vector search would find semantically similar things, which is sometimes what you want and sometimes really not.
Procedural — how to do things. This is the part I hadn't seen before. After completing a multi-step task, Hermes can convert that workflow into a Skill — a concrete, versioned, human-readable procedure saved to disk. Next time a similar task comes up, it loads the Skill, runs through the steps, and if something goes better or worse than expected, it updates the Skill accordingly.
This is closer to how I actually retain knowledge than any AI memory system I've used. I don't re-derive my Docker deployment process from first principles every time. I have a procedure. I refine it when it breaks. I get faster. Hermes is doing a version of that.
There's also a user modeling layer via something called Honcho that builds a representation of who you are across sessions — your preferences, communication style, work context. I haven't been running it long enough to have strong opinions on this part yet, but the architecture makes sense.
Installation (genuinely fast)
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
That's it for Linux/macOS/WSL2. There's a PowerShell version for Windows in early beta. After installing:
hermes setup --portal
One OAuth flow and you have a model plus web search, image gen, TTS, and browser access. No juggling four separate API keys.
hermes chat
I had it running in under three minutes, which is not always how these things go.
The infrastructure stuff that actually matters
One thing I didn't expect to care about but do: Hermes is designed to run somewhere other than your laptop.
It supports six backends — local, Docker, SSH, Daytona, Singularity, and Modal. The Daytona and Modal options are serverless, meaning the environment hibernates when idle. Practically what this means: you spin it up on a cheap VPS, connect to it from Telegram, and the agent is doing work on a machine you never SSH into. Your laptop is just the interface.
Most agents I've used are tethered to wherever I'm sitting. Close the laptop, the agent stops. Hermes is a persistent process that happens to communicate with you — a subtle but real difference for anything involving longer workflows.
The messaging integrations lean into this: CLI, Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Teams, Google Chat... 20+ platforms. You configure once. I've been using it from Telegram while commuting and it's a genuinely different experience from "AI assistant that only exists when I'm at my desk."
The parallelization thing
Hermes can spawn isolated subagents — separate processes with their own terminals and contexts — to run workstreams in parallel. Research task, data pipeline, and file conversion simultaneously, each sandboxed.
I want to be careful not to oversell this because I've only tested it in limited ways, but the architecture is sound. And it's where the word "agent" starts to feel earned rather than marketing.
The thing that actually tripped me up
One thing worth knowing before you dive in: the first time I let it create a Skill automatically, it over-generalized. I'd asked it to pull a summary of my GitHub issues and it turned that into a Skill called something like "fetch repository data" — which then tried to apply that same approach when I later asked about a completely different repo with different auth. Took me a minute to figure out why it was behaving weirdly.
The fix was easy — Skill files are just readable text on disk, so I went in, renamed it to something specific, and tightened the scope. But it wasn't what I expected. Lesson I'd pass on: watch what it names Skills in the first few sessions and rename the vague ones early. A Skill called "fetch repository data" will haunt you. A Skill called "fetch open issues from acme-api repo" will not.
Where I'd actually use it vs. not
Being straight with you:
Good fit:
- You want something that genuinely compounds value over weeks of use
- You need a private, self-hosted setup — no telemetry, your data stays on your machine
- Long-horizon tasks where context continuity matters
- You're already living in Claude Code and wish it had cross-project memory
Probably not the right fit:
- You want a quick throwaway session with zero setup cost — just open a chat tab
- Your workflow is entirely in-IDE
- Domains where you can't reliably judge output quality — and this matters more than it sounds
That last point is worth being honest about. The self-improvement loop is only as good as the feedback it gets. If you're working in a domain where you can't confidently tell when the agent's output is correct, the Skills system can make it faster at doing the wrong thing. Hermes gives you control. It can't make you exercise it.
Why it matters beyond the product
The Stanford HAI AI Index 2026 made a point that stuck with me: agents moved from question answering toward task completion in 2025, but still fail about a third of attempts on structured benchmarks. On OSWorld specifically, accuracy went from ~12% to 66.3% — within six points of human performance.
What that trajectory suggests is that the bottleneck is increasingly not raw model intelligence. It's memory, orchestration, recovery from failure, and repeatability. Which is exactly what Hermes is designed around.
There's also just a values bet embedded in the whole project — MIT license, local-first, readable skills you can inspect and modify, no cloud lock-in. Whether or not Hermes wins the agentic framework wars, that design philosophy being competitive is something worth rooting for.
Try it yourself
# Install
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
# Set up model + tools
hermes setup --portal
# Talk to it
hermes chat
Give it real context about your work on day one. Let it run something non-trivial. Come back two sessions later and notice what it already knows.
That's the test that settled it for me.
Top comments (0)