Hermes Agent

Hermes Agent

The self-improving agent from Nous Research.

An autonomous AI agent that lives on your server, remembers what it learns, and gets more capable the longer it runs. Community guides, skills, and integrations in one place.

chat_bubble 22 messaging platforms · terminal 7 sandbox backends · build 40+ built-in tools

Quick Start

BETA
# Works on macOS. One-liner install. ⚡
$ curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Installs the Hermes Agent CLI and its Python environment.

Capabilities

computer

Runs on Your Server

Linux, macOS, or WSL2. Runs on a $5 VPS, a GPU cluster, or serverless on Daytona and Modal. Your data and skills stay on your own infrastructure.

chat_bubble

Every Chat App

Chat via Telegram, Discord, Slack, WhatsApp, Signal, Email, or the CLI. Start a conversation on one platform and pick it up on another.

psychology

Persistent Memory

Long-term memory plus a dialectic user model via Honcho. The longer Hermes runs, the better it knows your projects, preferences, and past decisions.

public

40+ Built-in Tools

Web search, browser automation, vision, image generation, voice, and multi-model reasoning — all callable in a single conversation.

terminal

Real Sandboxing

Seven terminal backends: local, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Container hardening, namespace isolation, and command approval workflows.

extension

Self-Writing Skills

Hermes creates skills from experience, improves them as it uses them, and syncs with the open agentskills.io standard. Share what works with the community.

schedule

Scheduled Automations

Built-in cron scheduler — describe a job in natural language and let Hermes run it unattended. Daily reports, nightly backups, weekly audits; with `deliver=all` the output fans out to every connected chat platform at once.

account_tree

Parallel Subagents

Spawn isolated subagents for parallel workstreams. Each runs in its own sandbox and reports back. Write Python scripts that call tools via RPC to collapse multi-step pipelines into one zero-context-cost turn.

swap_horiz

OpenAI-Compatible Proxy

Run `hermes proxy` and your Claude Pro, ChatGPT Pro, or SuperGrok OAuth session is exposed as a local OpenAI-compatible HTTP endpoint. Codex CLI, Aider, Cline, and Continue hit it without an API key — one subscription, every tool. New in v0.14.0.

flag

Autonomous /goal Loops

Hand Hermes a target and success criteria with `/goal`. A worker proposes, a separate judge LLM grades — the loop runs until the judge confirms you're done. `/subgoal` adds new criteria mid-flight without restarting. Best fit for tasks with concrete, gradable outcomes.

sync_alt

Live Session /handoff

Mid-conversation, swap to a different model, personality, or profile and `/handoff` migrates the entire session — every message, every tool call, every byte of context — without dropping a thread. New in v0.14.0.

Commands

Two entry points, one set of slash commands

Hermes ships a terminal UI you can spin up locally, and a gateway you can chat to from Telegram, Discord, Slack, WhatsApp, Signal, LINE, SimpleX, Microsoft Teams, and the rest of the 22 supported platforms. Most slash commands work the same in both — these are the ones you reach for daily.

Start chatting
terminal Terminal CLI
hermes
chat_bubble Messaging gateway
hermes gateway setup, then send the bot a message
Start a fresh conversation
terminal Terminal CLI
/new or /reset
chat_bubble Messaging gateway
/new or /reset
Change the model
terminal Terminal CLI
/model [provider:model]
chat_bubble Messaging gateway
/model [provider:model]
Set a personality
terminal Terminal CLI
/personality [name]
chat_bubble Messaging gateway
/personality [name]
Retry or undo the last turn
terminal Terminal CLI
/retry, /undo
chat_bubble Messaging gateway
/retry, /undo
Compress context / check usage
terminal Terminal CLI
/compress, /usage, /insights [--days N]
chat_bubble Messaging gateway
/compress, /usage, /insights [days]
Browse skills
terminal Terminal CLI
/skills or /<skill-name>
chat_bubble Messaging gateway
/<skill-name>
Hand off mid-session
terminal Terminal CLI
/handoff
chat_bubble Messaging gateway
/handoff
Interrupt the agent
terminal Terminal CLI
Ctrl+C or send a new message
chat_bubble Messaging gateway
/stop or send a new message
Platform-specific status
terminal Terminal CLI
/platforms
chat_bubble Messaging gateway
/status, /sethome

Source: NousResearch/hermes-agent README — CLI vs Messaging quick reference.

See It In Action

Hermes Agent In Action

Demos and walkthroughs from the community. See what Hermes can do before you install.

play_circle More videos & community showcase arrow_forward
May 19, 2026 · 8 min read

From OpenClaw to Hermes Agent: a step-by-step migration

If you've been running OpenClaw, Hermes Agent is its successor. v0.14.0 ships a built-in `hermes claw migrate` that imports your SOUL.md, memories, skills, command allowlist, messaging configs, API keys, and TTS assets. This is the practical walkthrough — what gets imported, what flags you have, and the dry-run-first workflow that avoids surprises.

Tutorial Migration
May 18, 2026 · 7 min read

One Claude Pro subscription, every tool: using `hermes proxy` with Aider, Cline, and Codex CLI

v0.14.0 shipped a one-line command that quietly absorbed a whole class of integration questions: `hermes proxy`. Run it once and you get a local `http://localhost:port` endpoint that speaks the OpenAI API, backed by whichever OAuth provider you're signed into — Claude Pro, ChatGPT Pro, SuperGrok. Aider, Cline, Codex CLI, and Continue all expect an OpenAI-compatible endpoint. They just work with your existing subscription, no API key required. Here's the exact workflow, step by step.

Tutorial For Power Users
May 18, 2026 · 9 min read

From 7 to 22 in 14 months: every chat platform Hermes Agent runs on

Hermes Agent launched in March 2026 speaking seven chat platforms from a single gateway. Fourteen months later it speaks 22 — from Telegram and Discord to Microsoft Teams, LINE, and SimpleX Chat. Same memory, same skills, same agent across all of them. This is the complete map: every platform by category, the release each one landed in, and how the gateway architecture makes 'one agent, twenty-two front doors' possible.

Architecture Messaging

What People Say

View all arrow_forward
@opslead_marc avatar

"One config replaced three of our chat bots. This is the one."

@opslead_marc
@low_latency_dan avatar

"Hermes on a $5 Hetzner box with load average 0.03. It is absurdly efficient."

@low_latency_dan
@generalist_greg avatar

"The first self-hosted AI assistant I did not uninstall after a week."

@generalist_greg
@yuki_codes avatar

"The ACP integration into VS Code changed how I code. I do not leave the editor anymore."

@yuki_codes
@memory_mori avatar

"Honcho memory turned a chatbot into something that remembers how I actually work."

@memory_mori
@pocket_engineer avatar

"Running Hermes on my old Pixel in Termux. Free, private, always on."

@pocket_engineer
@opslead_marc avatar

"One config replaced three of our chat bots. This is the one."

@opslead_marc
@low_latency_dan avatar

"Hermes on a $5 Hetzner box with load average 0.03. It is absurdly efficient."

@low_latency_dan
@generalist_greg avatar

"The first self-hosted AI assistant I did not uninstall after a week."

@generalist_greg
@yuki_codes avatar

"The ACP integration into VS Code changed how I code. I do not leave the editor anymore."

@yuki_codes
@memory_mori avatar

"Honcho memory turned a chatbot into something that remembers how I actually work."

@memory_mori
@pocket_engineer avatar

"Running Hermes on my old Pixel in Termux. Free, private, always on."

@pocket_engineer
@infra_priya avatar

"Credential pools saved my weekend. Three Anthropic keys rotating on autopilot."

@infra_priya
@redteam_blue avatar

"MCP OAuth 2.1 PKCE plus OSV scanning. Finally an agent framework that takes plugins seriously."

@redteam_blue
@secdev_sam avatar

"Filesystem checkpoints plus /rollback is how I convince skeptics to try agents."

@secdev_sam
@partnered_pat avatar

"My non-technical partner uses Hermes more than I do now. Best onboarding of any AI tool."

@partnered_pat
@dr_elena_ml avatar

"Self-optimized GPT guidance is the quiet revolution of 2026. They are benchmarking prompts instead of writing them."

@dr_elena_ml
@private_phoebe avatar

"Full MEDIA delivery on Signal means I finally have a private, encrypted line to my assistant."

@private_phoebe
@infra_priya avatar

"Credential pools saved my weekend. Three Anthropic keys rotating on autopilot."

@infra_priya
@redteam_blue avatar

"MCP OAuth 2.1 PKCE plus OSV scanning. Finally an agent framework that takes plugins seriously."

@redteam_blue
@secdev_sam avatar

"Filesystem checkpoints plus /rollback is how I convince skeptics to try agents."

@secdev_sam
@partnered_pat avatar

"My non-technical partner uses Hermes more than I do now. Best onboarding of any AI tool."

@partnered_pat
@dr_elena_ml avatar

"Self-optimized GPT guidance is the quiet revolution of 2026. They are benchmarking prompts instead of writing them."

@dr_elena_ml
@private_phoebe avatar

"Full MEDIA delivery on Signal means I finally have a private, encrypted line to my assistant."

@private_phoebe

Frequently Asked Questions

Common questions about Hermes Agent, sourced from the official README, release notes, and docs.

Stay in the Loop

Community updates on Hermes Agent releases, new skills, and integrations. No spam, unsubscribe anytime.