{
  "$schema": "https://shelldex.com/schemas/compare.schema.json",
  "generated": "2026-05-15T16:51:32.382Z",
  "source": "https://shelldex.com/compare/hermes-vs-safeclaw/",
  "license": "CC-BY-4.0",
  "pair": {
    "canonical": "hermes-vs-safeclaw",
    "slugA": "hermes",
    "slugB": "safeclaw"
  },
  "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": 151659,
        "forks": 24066,
        "open_issues": 11409,
        "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": "2026-05-15T16:39:27Z",
        "latest_release": "v2026.5.7",
        "latest_release_date": "2026-05-07T16:23:08Z",
        "star_growth_7d": 15959,
        "last_enriched": "2026-05-15T16:50:58.583Z"
      },
      "stars": 151659,
      "leaderboard": {
        "rank": 2,
        "health_score": 70,
        "health": {
          "issues_stars_ratio": 0.0752,
          "days_since_last_release": 8,
          "days_since_last_commit": 0
        }
      }
    },
    {
      "name": "SafeClaw",
      "slug": "safeclaw",
      "tagline": "Zero-LLM OpenClaw alternative",
      "description": "Rule-based and local-first assistant positioned as an OpenClaw alternative with no required LLM API spend.",
      "language": "python",
      "category": [
        "minimal",
        "lightweight"
      ],
      "github": "princezuda/safeclaw",
      "status": "active",
      "tier": 1,
      "highlight": "No LLM required — deterministic, rule-based, zero token costs",
      "emoji": "🧯",
      "platform": [
        "server"
      ],
      "requires_llm": false,
      "mcp_support": false,
      "ecosystem_role": "alternative",
      "added": "2026-02-27T00:00:00.000Z",
      "github_data": {
        "stars": 280,
        "forks": 35,
        "open_issues": 2,
        "license": "MIT",
        "topics": [
          "agentic-ai",
          "ai",
          "ai-agent",
          "ai-assistant",
          "ai-tools",
          "openclaw",
          "safe",
          "safeai"
        ],
        "last_commit": "2026-05-09T13:48:23Z",
        "latest_release": "4.2.4",
        "latest_release_date": "2026-05-09T13:40:00Z",
        "star_growth_7d": 2,
        "last_enriched": "2026-05-15T16:51:10.661Z"
      },
      "stars": 280,
      "leaderboard": {
        "rank": 39,
        "health_score": 85,
        "health": {
          "issues_stars_ratio": 0.0071,
          "days_since_last_release": 6,
          "days_since_last_commit": 6
        }
      }
    }
  ],
  "key_differences": [
    "Hermes Agent has 542x more stars (152k vs 280), indicating significantly broader adoption.",
    "Hermes Agent is growing faster with +16k stars this week vs +2 for SafeClaw.",
    "SafeClaw works without any API keys — zero LLM cost — while Hermes Agent requires an LLM provider.",
    "Hermes Agent has MCP (Model Context Protocol) support while SafeClaw does not.",
    "Hermes Agent focuses on memory, self-hosted, multi-platform while SafeClaw targets minimal, lightweight.",
    "SafeClaw scores higher on project health (maintenance activity, issue management, release cadence)."
  ],
  "urls": {
    "page": "https://shelldex.com/compare/hermes-vs-safeclaw/",
    "json": "https://shelldex.com/api/compare/hermes-vs-safeclaw.json",
    "markdown": "https://shelldex.com/md/compare/hermes-vs-safeclaw.md"
  }
}