Hermes Agent with an uncensored model

To run Hermes Agent with an uncensored model, add a custom provider to ~/.hermes/config.yaml with the endpoint's base URL and an abliterated model as the default.

Updated November 18, 2026By unrestrictedaiagent
~/.hermes/config.yamlYAML
model:
  provider: custom:silkcompute
  default: kimi-k3.1-pro-uncensored

providers:
  silkcompute:
    name: Silk Compute
    api: https://api.silkcompute.com
    key_env: SILK_API_KEY
    transport: chat_completions
    default_model: kimi-k3.1-pro-uncensored
    models:
      kimi-k3.1-pro-uncensored: {context_length: 1048576}
      deepseek-v4.1-flash-1017-uncensored: {context_length: 1048576}
      glm-5.3-uncensored: {context_length: 1048576}
      glm-5.3-flash-uncensored: {context_length: 1048576}
OpenAI format
transport: chat_completions
Anthropic format
transport: anthropic_messages
Tool calling
Toolsets
Streaming
Not documented
Browser use
browser_exec
Memory
Persistent memory

Labels link to Hermes Agent's own docs, read November 18, 2026. Compare all 11

Point the agent only at systems, files and accounts you own or are allowed to test.

Deploy it

3 steps, with Kimi K3.1 Pro.

  1. 01

    Install Hermes. The installer is on the project README.

    Terminal
    curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
  2. 02

    Add the key. key_env names the variable Hermes reads from ~/.hermes/.env.

    Terminal
    echo "SILK_API_KEY=..." >> ~/.hermes/.env
  3. 03

    Add a custom provider. Write this to ~/.hermes/config.yaml, then run hermes, or hermes gateway for Telegram and Discord.

    See ~/.hermes/config.yaml above

Which model

The config uses the Silk Compute base URL, which serves both models with a 1,048,576-token context.

Sources

More frameworks