{
  "$schema": "https://shelldex.com/schemas/compare.schema.json",
  "generated": "2026-05-23T04:17:10.188Z",
  "source": "https://shelldex.com/compare/hermes-vs-nanoclaw/",
  "license": "CC-BY-4.0",
  "pair": {
    "canonical": "hermes-vs-nanoclaw",
    "slugA": "hermes",
    "slugB": "nanoclaw"
  },
  "projects": [
    {
      "name": "Hermes Agent",
      "slug": "hermes",
      "slug_aliases": [
        "hermes-agent"
      ],
      "tagline": "The agent that grows with you",
      "description": "Persistent personal AI agent by Nous Research with multi-level growing memory, self-authored skills, and multi-platform messaging. Learns your projects and builds reusable knowledge over time.",
      "language": "python",
      "category": [
        "memory",
        "self-hosted",
        "multi-platform"
      ],
      "github": "NousResearch/hermes-agent",
      "status": "active",
      "tier": 1,
      "highlight": "Self-improving skill system — agent writes reusable SKILL.md docs as it solves problems, building a personal knowledge base over time",
      "emoji": "🧠",
      "platform": [
        "server",
        "messaging"
      ],
      "requires_llm": true,
      "mcp_support": true,
      "ecosystem_role": "alternative",
      "added": "2026-02-28",
      "github_data": {
        "stars": 163323,
        "forks": 26728,
        "open_issues": 13267,
        "license": "MIT",
        "topics": [
          "ai",
          "ai-agent",
          "ai-agents",
          "anthropic",
          "chatgpt",
          "claude",
          "claude-code",
          "clawdbot",
          "codex",
          "hermes",
          "hermes-agent",
          "llm",
          "moltbot",
          "nous-research",
          "openai",
          "openclaw"
        ],
        "last_commit": "2026-05-23T03:15:11Z",
        "latest_release": "v2026.5.16",
        "latest_release_date": "2026-05-16T09:59:15Z",
        "star_growth_7d": 11664,
        "last_enriched": "2026-05-23T04:16:37.439Z"
      },
      "stars": 163323,
      "leaderboard": {
        "rank": 2,
        "health_score": 75,
        "health": {
          "issues_stars_ratio": 0.0812,
          "days_since_last_release": 6,
          "days_since_last_commit": 0
        }
      }
    },
    {
      "name": "NanoClaw",
      "slug": "nanoclaw",
      "tagline": "Security-first, radically minimal",
      "description": "Five files, one process, OS-level container isolation. NanoClaw strips the agent down to its secure essentials.",
      "language": "typescript",
      "category": [
        "security",
        "lightweight"
      ],
      "github": "qwibitai/nanoclaw",
      "status": "active",
      "tier": 1,
      "highlight": "5 files, one process, OS-level container isolation",
      "emoji": "🔐",
      "mentions": [
        {
          "type": "tweet",
          "url": "https://x.com/swyx/status/2018230334488527022",
          "author": "swyx",
          "author_url": "https://x.com/swyx",
          "quote": "NanoClaw fixes a couple complaints people have about OpenClaw — it's a minimal, hackable reproduction (700LOC), that uses Apple Containers for sandboxing/security.",
          "date": "2026-01-30",
          "source": "X"
        },
        {
          "type": "tweet",
          "url": "https://x.com/Gavriel_Cohen/status/2024514255249096880",
          "author": "Gavriel Cohen",
          "author_url": "https://x.com/Gavriel_Cohen",
          "quote": "I went on CNBC and didn't hold back about OpenClaw. AI agent swarms are a multiplier. That amplifies the value, but it also amplifies the risk if the foundation isn't secure.",
          "date": "2026-02-22",
          "source": "X"
        },
        {
          "type": "article",
          "url": "https://venturebeat.com/orchestration/nanoclaw-solves-one-of-openclaws-biggest-security-issues-and-its-already",
          "author": "VentureBeat",
          "title": "NanoClaw solves one of OpenClaw's biggest security issues",
          "date": "2026-02-18",
          "source": "VentureBeat"
        }
      ],
      "platform": [
        "server"
      ],
      "requires_llm": true,
      "mcp_support": false,
      "ecosystem_role": "reimplementation",
      "added": "2026-02-25T00:00:00.000Z",
      "github_data": {
        "stars": 29286,
        "forks": 12858,
        "open_issues": 680,
        "license": "MIT",
        "topics": [
          "ai-agents",
          "ai-assistant",
          "claude-code",
          "claude-skills",
          "openclaw"
        ],
        "last_commit": "2026-05-22T20:17:35Z",
        "latest_release": "v2.0.64",
        "latest_release_date": "2026-05-18T18:01:05Z",
        "star_growth_7d": 402,
        "last_enriched": "2026-05-23T04:16:42.016Z"
      },
      "stars": 29287,
      "leaderboard": {
        "rank": 6,
        "health_score": 95,
        "health": {
          "issues_stars_ratio": 0.0232,
          "days_since_last_release": 4,
          "days_since_last_commit": 0
        }
      }
    }
  ],
  "key_differences": [
    "Hermes Agent has 6x more stars (163k vs 29k), indicating significantly broader adoption.",
    "Hermes Agent is growing faster with +12k stars this week vs +402 for NanoClaw.",
    "Hermes Agent is written in Python while NanoClaw uses TypeScript, which may influence your choice depending on your stack.",
    "NanoClaw has a higher fork-to-star ratio (44% vs 16%), suggesting more active contributor participation.",
    "Hermes Agent has MCP (Model Context Protocol) support while NanoClaw does not.",
    "Hermes Agent focuses on memory, self-hosted, multi-platform while NanoClaw targets security, lightweight."
  ],
  "urls": {
    "page": "https://shelldex.com/compare/hermes-vs-nanoclaw/",
    "json": "https://shelldex.com/api/compare/hermes-vs-nanoclaw.json",
    "markdown": "https://shelldex.com/md/compare/hermes-vs-nanoclaw.md"
  }
}