Source: Nous Research — Hermes Agent site + docs + repo
Repo: github.com/nousresearch/hermes-agent (MIT, 97K+ stars, Python, default branch main)
Homepage: hermes-agent.nousresearch.com
Version (2026-04-17): v0.10.0
Refreshed 2026-10-27 from: raw/The_Best_New_AI_Products_and_the_Key_Trends_They_Represent.md and raw/How_to_Choose_Your_Personal_Agent.md (The AI Daily Brief, Nathaniel Whittemore; https://www.youtube.com/watch?v=WloeFbIX7PU for the second). Version and star figures above are from April and were not re-checked.
Nous Research’s autonomous agent framework. Positioned against two contrasting categories: coding copilots (“tethered to an IDE”) and chatbot wrappers (“around a single API”). Hermes is neither — it’s a long-running agent that installs on a server you control, curates its own memory, generates its own skills, and gets more capable the longer it runs. MIT-licensed; 60-second install on Linux, macOS, or WSL2.
Key Takeaways
- Lives on your server, not in an IDE or SaaS dashboard. The architectural bet is persistence: the agent that remembers how it solved a problem last Tuesday outperforms the one that starts fresh every session.
- Closed learning loop. Agent-curated memory + autonomous skill creation + cross-session recall. Over time the agent accumulates a library of its own solved-problem shortcuts, compatible with the
agentskills.ioecosystem. - 47+ built-in tools, all toggleable per deployment. Keeps the tool surface lean where it matters (safety-sensitive envs) and wide where it doesn’t.
- 6 sandbox backends: local, Docker, SSH, Daytona, Singularity, Modal. Lets the same agent code run from a laptop up to an HPC cluster or a serverless Modal stack.
- 15+ messaging platforms out of the box: Telegram, Discord, Slack, WhatsApp, Signal, Email, CLI, and more. Chat surface is a connector config, not a rewrite.
- Delegation via isolated subagents with their own conversations, terminals, and Python RPC scripts — closer to the Claude Code Agent Teams pattern than to flat function-call “sub-routines.”
- Natural-language cron for scheduled runs (reports, backups, briefings) — the agent can be told “summarize yesterday’s inbox every weekday at 8am” without a cron expression.
- Model-agnostic. Works with Nous Portal, OpenRouter, OpenAI, or any OpenAI-compatible endpoint. Swap providers without reconfiguring the agent logic.
- MCP server integration — Hermes is compatible with the MCP ecosystem, so the same servers you’d plug into Claude plug into Hermes.
October 2026 update: funding, scale and the openness pitch
From The AI Daily Brief’s headlines (raw/The_Best_New_AI_Products_and_the_Key_Trends_They_Represent.md). Figures are Whittemore relaying the Wall Street Journal, not a Nous filing.
- Valuation. Nous Research raised at a $1.5B valuation.
- Scale. Hermes has been installed 22 million times and “accounts for roughly 2.5% of global token usage overall.”
- Revenue. Hermes is free with your own models; subscriptions bundle frontier-model usage and hosted instances. That reached 100M by year end.
- Next product. The funding is meant to launch “Hermes for business.”
- CEO note (Dylan Rolnick, caption spelling): “The marginal cost to reproduce a piece of software has plummeted… Users don’t want lock-in and they deserve observability into the thing they will allow into so many aspects of their lives.”
- The “non-negotiables” list Nous posted on X, abridged: use smarter, cheaper, local, or a different model for every job, and switch “in the middle of a conversation”; choose what data it has and “what it remembers and what it forgets”; choose the computer, including “a machine that never touches the internet,” and run it “while your laptop is closed”; read the prompt, see and disable every tool, know “what it did and when and why”; export the agent; read and change the code. “Your agent should be yours.”
- Where that leaves Hermes in the field. In Whittemore’s buyer’s comparison, Hermes and OpenClaw are the only personal agents that let you bring your own model, run on hardware you pick, and edit memory directly (
raw/How_to_Choose_Your_Personal_Agent.md). The trade-off is setup, which “is going to cut off some full set of users.” See Personal Agents Compared. - How to use the list ^[inferred]: it doubles as an evaluation checklist for any hosted agent. Score each vendor against the 19 items before you connect your accounts.
Architectural Pattern
Hermes sits in the “long-running personal agent” quadrant of the agent hierarchy:
- vs Claude Code Routines — both run autonomously on their own schedule. Routines are Anthropic-hosted, Anthropic-metered, and Claude-specific. Hermes is self-hosted, model-agnostic, and carries persistent memory between runs (Routines are stateless per run).
- vs Claude Managed Agents — both hosted-agent alternatives. Managed Agents is the turnkey Anthropic SaaS. Hermes is the open-source, BYO-infra equivalent.
- vs OpenClaw / Claude Code Subagents — Claude Code’s subagents are ephemeral per session. Hermes subagents are spawned within a persistent parent and can be long-running themselves.
Design tradeoff: Hermes optimizes for agent longevity and memory continuity; Claude-hosted options optimize for zero-ops setup and policy guarantees.
Implementation
Tool/Service: Hermes Agent (open source, Nous Research)
Setup:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setupConfigure a model provider (Nous Portal, OpenRouter, OpenAI, or custom endpoint), select desired messaging connectors (Telegram/Discord/Slack/etc.), pick a sandbox backend (Docker for most; Modal for serverless; SSH for remote hosts), and enable the tool set you want.
Cost:
- Runtime: free — MIT-licensed, self-hosted (your own VPS, home server, or cloud instance)
- Inference: pay the underlying model provider directly (Nous Portal, OpenRouter, OpenAI, etc.)
- Compare against Claude Managed Agents at $0.08/hr runtime + tokens for a hosted equivalent
Integration notes:
- Skills format is compatible with
agentskills.io, so skills built for Hermes are portable to other agentskills-compliant runtimes - MCP server support means existing MCP integrations (GitHub, Linear, Slack, etc.) work directly
- Multi-provider model routing is useful for cost-tuning — route cheap tasks to smaller models, escalate complex reasoning
Try It
- Install on a VPS or spare machine (
curl ... | bash) and runhermes setup. - Point it at OpenRouter with a $5 budget cap and enable the Telegram connector so you can chat with the agent from your phone.
- Install one or two
agentskills.ioskills to seed the memory; let it auto-generate follow-ups from real work. - Schedule a natural-language cron: “At 9am every weekday, summarize yesterday’s inbox and post to briefing.” Compare the output after 2 weeks vs the first day — the learning-loop claim is testable.
- Compare against Claude Code Routines running the same scheduled job: measure output quality, context re-use, and operational overhead.
- Pair Hermes with your existing MCP servers (GitHub, Sentry, PostgreSQL) so the agent can reach the same tools you use in Claude Code.
Related
- Personal Agents Compared (October 2026) — Hermes against the hosted agents
- Claude Managed Agents — Anthropic’s hosted alternative to the same “long-running autonomous agent” problem
- Claude Code Routines — scheduled / event-driven hosted agent runs (stateless per run, vs Hermes’s persistent memory)
- Claude Code Agent Teams — multi-agent coordination pattern comparable to Hermes’s subagent delegation
- Claude Code Subagents — ephemeral worker pattern inside Claude Code sessions
- Claude Agent Hierarchy — When to Use Which — framing for where Hermes fits relative to Claude-first options
- Essential MCP Servers for 2026 — Hermes integrates the same MCP servers
- Five Claude Skills To Build Right Now — skill-authoring examples that translate into Hermes via agentskills.io
Open Questions
- Homepage lists “five backends” for sandboxing (local, Docker, SSH, Singularity, Modal) while the docs page lists “six terminal backends” (adds Daytona). Which is current?
- What are the concrete memory semantics — is memory a single append-only log, topic-scoped, or semantically indexed? The homepage says “never forgets how it solved a problem” but doesn’t detail retrieval.
- How does Hermes handle model-routing decisions — explicit per-tool config, or dynamic based on task complexity?
- What does the
agentskills.iocompatibility contract actually enforce? Is a Hermes skill drop-in on Claude Code Skills, or is there a translation layer? - Is there a hosted Nous Portal equivalent of “Managed Agents” for users who don’t want to self-host?