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.
~/.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.
- 01
Install Hermes. The installer is on the project README.
Terminalcurl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash - 02
Add the key. key_env names the variable Hermes reads from ~/.hermes/.env.
Terminalecho "SILK_API_KEY=..." >> ~/.hermes/.env - 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
In this setup
Kimi K3.1 Pro
Long runs, image and video input
- Id
kimi-k3.1-pro-uncensored- Per 1M in / out
- $3.50 / $8.00
DeepSeek V4.1 Flash 1017
Value, image input
- Id
deepseek-v4.1-flash-1017-uncensored- Per 1M in / out
- $0.24 / $0.90
The config uses the Silk Compute base URL, which serves both models with a 1,048,576-token context.