Letta with an uncensored model

To run Letta with an uncensored model, connect an OpenAI-compatible provider with /connect and pick an abliterated model with /model.

Updated November 18, 2026By unrestrictedaiagent
lettaSettings
> /connect
  OpenAI-compatible API
  Base URL  https://api.silkcompute.com/v1
  API key   <your Silk Compute key>
OpenAI format
/connect, OpenAI-compatible API
Anthropic format
Not documented
Tool calling
Required of the endpoint
Streaming
Not documented
Browser use
Not documented
Memory
Memory filesystem

Labels link to Letta'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 Letta Code. It needs Node.js 22.19 or newer.

    Terminal
    npm install -g @letta-ai/letta-code
    letta
  2. 02

    Connect the endpoint. Letta asks for a base URL and an API key. The endpoint must support Chat Completions and tool calling.

    See letta above
  3. 03

    Pick the model. Type /model and choose kimi-k3.1-pro-uncensored.

    Settings
    > /model

Which model

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

Sources

More frameworks