NousResearchAI apps
Hermes Agent
hermes-agent
A personal AI agent that runs locally or on remote infrastructure with terminal, messaging, memory, skills, and scheduled automation.
- Backend
- Full stack
- Product
- Operations
- AI coding
- Productivity
- CLI
- Desktop
- Windows
- macOS
- Linux
- Self-hostable
- Runs locally
- Docker supported
- Popularity
- 250.7k Stars
- GitHub stars
- Recent activity
- 10/2/2026
- Updated in the last 30 days
- License
- MIT
- Permissive
Why it matters
We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.
Problem
Addresses the limitation of AI assistants being confined to local execution, lacking persistent memory and cross-platform interaction.
Practical value
Provides multi-terminal interfaces, messaging platform integration, scheduled automations, and flexible model switching for complex daily workflows.
Innovation / differentiation
Introduces a self-improving learning loop, experience-based skill creation and evolution, and cross-session memory retrieval.
Leverage potential
Supports deployment from local setups to various cloud sandboxes and servers, compatible with standardized skill interfaces.
Why now
Aligns with the current demand for autonomous personal AI agents, multi-device coordination, and lightweight cloud-persistent execution.
Community activity
In the last 90 days there were 18647 new issues and 54388 pull requests; the bounded issue/PR samples include 49 issue authors and 0 PR contributors, with 17 releases.
Maintainer responsiveness
The 59-issue window sample had a 51% close rate, and the 54388-pull-request sample had a — merge rate. Maintainer-comment observations covered only 29% of that issue sample, so response rate and first-response speed are not reported.
Key highlights
- Provide a terminal TUI with streaming tool output and conversation history
- Continue sessions through Telegram, Discord, Slack, WhatsApp, Signal, and CLI entry points
- Maintain session memory and create or update reusable skills
Quick start
How it is installed, how hard it is, and where to start.
Where it runs
Runs locally
Difficulty
Medium — some setup needed
- 01Use the documented Linux/macOS/WSL installer, or run the official PowerShell installation command on Windows.
- 02After installation, run
hermes setupto configure the model provider and core features. - 03Run
hermesfor the terminal interface, and configurehermes gatewaywhen you want messaging-platform access.
Best for
- Teams that want data on their own servers
- Developers who want to try it on their machine
- People who prefer Docker deploys
More about it
Hermes Agent is a personal agent from Nous Research that can run on a local machine, VPS, GPU cluster, or several cloud execution environments. The official README documents a terminal TUI plus messaging gateways for Telegram, Discord, Slack, WhatsApp, and Signal. It also includes session search, persistent memory, skill creation and updates, scheduled jobs, and isolated subagents for parallel work. Model access is provider-independent and can be switched with hermes model among Nous Portal, OpenRouter, OpenAI, or a custom endpoint.
Sources
Each field shows its status and source — expand to review.
12 · Expand
Sources
Each field shows its status and source — expand to review.
capability tags
Verifiedai_coding, productivity
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
Latest release
Verifiedv2026.9.24
Source: GitHub API · latest_release=v2026.9.24 · 10/2/2026
License
VerifiedMIT
Source: GitHub API · license.spdx_id=MIT · 10/2/2026
needs api key
VerifiedNo
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
One-liner
Verified{"en":"A personal AI agent that runs locally or on remote infrastructure with terminal, messaging, memory, skills, and scheduled automation.","zh":"可在本机、VPS 或云环境运行的个人 AI Agent，支持终端、消息平台、记忆、技能和定时自动化。"}
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
Platforms
Verifiedwindows, macos, linux
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
Category hint
Inferred from materialsai-apps
Source: Project README · hint=ai-apps · 8/15/2026
product forms
Verifiedcli, desktop
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
role tags
Verifiedbackend, fullstack, product, operations
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
supports docker
VerifiedYes
Source: Repository file · dockerfile=true; compose=true · 10/2/2026
supports local
VerifiedYes
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
supports self host
VerifiedYes
Source: manual_curator · Manually curated from the official repository README and project links. · 8/17/2026
Related projects
Other verified projects matched by category, capabilities, and intended roles.
ouroboros
Ouroboros is an open-source, general-purpose AI agent with durable cross-restart memory that coordinates specialist swarms and rewrites its own implementation.
Box
An advanced, fully offline on-device AI suite for Android supporting chat, image generation, and voice features.
OpenBiliClaw
A local-first, cross-platform AI content discovery agent that builds deep psychological profiles to proactively find content you'll love.
sutando
An open-source local AI agent that responds via voice and screen by day, and runs an autonomous build loop by night.
ollama
A local model runner for Windows, macOS, and Linux with a REST API plus Python and JavaScript clients.
ragflow
An open-source RAG engine fusing deep document understanding and agent capabilities to build grounded context layers for LLMs.