Hermes 4

At a glance

What Hermes 4 does

Tool use, Hybrid reasoning, Function calling, Streaming, Steerable persona, Uncensored

Best for

Self-hosted assistants with steerable persona and explicit chain-of-thought support

Works well with

Conflicts & caveats

• Trae's built-in model menu may not include Hermes 4 — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
• Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Hermes 4 is not in the supported model list.
• Kiro's spec mode is tuned for Claude models — Hermes 4 may work but spec-driven flows are best with Claude.
• Cursor's built-in model menu may not include Hermes 4 — verify it's available in your Cursor model picker.
• OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — Hermes 4 is not selectable inside this integration.
• Gemini CLI is locked to Google Gemini models — your LLM is Hermes 4.
• Privacy conflict: Self-hosted Hermes 4 sends code to cloud @codebase (Cursor). Use local context (Continue indexing, ChromaDB, LanceDB, pgvector, Vespa self-hosted) for true privacy.
• Claude Code only works with Claude models — your LLM is Hermes 4.
• Devin uses Cognition's proprietary model internally — your selected Hermes 4 will be ignored.
• OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Hermes 4 will be ignored.
• Jules runs Gemini models internally — your selected Hermes 4 will be ignored.
• The Claude Code SDK is tuned for Claude models — Hermes 4 may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
• Lovable uses a fixed internal model — your selected Hermes 4 will be ignored.
• Replit Agent 3 uses its own model selection internally — your selected Hermes 4 will be ignored.