HomeProjectsArticlesPK BoardAbout
Explore Projects

Hermes Agent

Active
GitHub Python MIT

Description

An autonomous AI agent framework from NousResearch that supports multiple LLM backends and grows with user needs.

Key Features

  • Self-improving learning loop - Auto-creates skills from experience, self-improves during use, cross-session recall
  • Multi-platform messaging gateway - Single process supports Telegram, Discord, Slack, WhatsApp, Signal, and CLI
  • Six terminal backends - Local, Docker, SSH, Singularity, Modal, and Daytona with serverless hibernation
  • Multi-LLM provider - Supports Nous Portal, OpenRouter (200+ models), OpenAI; switch with hermes model
  • Subagent parallelization - Spawn isolated subagents for parallel workstreams with Python RPC tool calls
  • Scheduled automation - Built-in cron scheduler with natural language config and multi-platform delivery

Use Cases

💡 Deploy on a $5 VPS as a 24/7 personal AI assistant that accumulates memory through Telegram conversations
💡 Use subagents to parallelize multiple research tasks with each agent independently searching and summarizing
💡 Configure scheduled tasks for daily report generation, nightly backups, and weekly system audits
💡 Run on Modal/Daytona serverless infrastructure with near-zero idle cost and on-demand wake-up

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (240.1k stars)
  • • Permissive open-source license (MIT)

⚠️ Limitations

  • • High issue backlog (38.6k open issues)

Tags

agent-framework autonomous-agent llm python

Categories

🤖 Agent Framework 💻 Coding Agent

Quick Start

# One-line install for Linux/macOS
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

# Reload shell
source ~/.bashrc

# Start interactive conversation
hermes

# Choose LLM provider and model
hermes model
Visit GitHub Visit Website

Related Projects

AutoAgent

9.8k · Python
Stale B

Fully-automated and zero-code LLM agent framework that enables users to build and deploy custom AI agents through natural language without writing code.

agent-frameworkzero-codeautomation +2
  • · Fully-automated agent building through natural language — no coding required to create, customize, and deploy AI agents
  • · Zero-code framework democratizing AI development for users without technical backgrounds
  • · Self-managing workflow generation that dynamically creates and optimizes agent pipelines from high-level descriptions
View full details → View on GitHub

ART

10.7k · Python
Active A+

ART (Agent Reinforcement Trainer) trains multi-step agents for real-world tasks using GRPO reinforcement learning, enabling on-the-job training for models like Qwen, Llama, and more.

reinforcement-learningagent-trainingGRPO +3
  • · GRPO-based reinforcement learning for training multi-step agents on real-world tasks
  • · W&B Training serverless RL with 40% lower cost and 28% faster training via shared inference cluster
  • · Pre-built notebooks for email search, 2048, Tic Tac Toe, Codenames, and MCP tool mastery
View full details → View on GitHub

PocketFlow

11.1k · Python
Normal A

PocketFlow is a minimalist 100-line LLM framework that lets Agents build Agents, enabling complex AI agent workflows through a clean abstraction layer.

agent-frameworkllmworkflow +2
  • · Only 100 lines of code, zero dependencies, zero vendor lock-in — ultra lightweight
  • · Graph-based abstraction supporting Agent, Multi-Agent, Workflow, and RAG design patterns
  • · Supports Agentic Coding — let AI agents like Cursor build agents for 10x productivity
View full details → View on GitHub