Kilo Code

Kilo Code is an open-source coding agent for VS Code, JetBrains, and the terminal. Connect ai& as a custom OpenAI-compatible provider to use the same models and configuration on every surface.

Note

For agentic repository work, start with zai-org/glm-5.3. For a cheaper, faster loop, use deepseek-ai/deepseek-v4-flash. Both support tool calling.

Prerequisites

• Kilo Code for VS Code, JetBrains, or the CLI
• An ai& API key

VS Code and JetBrains

1. Open Kilo Code settings:

   • VS Code: click the gear icon in the Kilo Code sidebar.
   • JetBrains: open Settings → Tools → Kilo Code.

2. Open Providers, scroll to the bottom, and select Custom provider.

3. Enter:

   Setting	Value
   Provider ID	aiand
   Display name	ai&
   Provider API	OpenAI Compatible
   Base URL	https://api.aiand.com/v1
   API key	Your ai& API key

4. Select models from the fetched list, or add an exact ID from the model catalog.

5. Save the provider and choose aiand/<model-id> in Kilo’s model picker.

Caution

Keep the /v1 suffix. Kilo appends /chat/completions and discovers models from /models.

CLI

Install Kilo:

npm install -g @kilocode/cli

Set your API key:

macOS / Linux

export AIAND_API_KEY="sk-your-aiand-api-key"

Windows (PowerShell)

$env:AIAND_API_KEY = "sk-your-aiand-api-key"

Create the global config at ~/.config/kilo/kilo.jsonc:

{
  "$schema": "https://app.kilo.ai/config.json",
  "model": "openai-compatible/zai-org/glm-5.3",
  "provider": {
    "openai-compatible": {
      "options": {
        "apiKey": "{env:AIAND_API_KEY}",
        "baseURL": "https://api.aiand.com/v1",
      },
      "models": {
        "zai-org/glm-5.3": {
          "name": "GLM 5.3",
          "tool_call": true,
          "reasoning": true,
          "limit": {
            "context": 1048576,
            "output": 131072,
          },
        },
        "deepseek-ai/deepseek-v4-flash": {
          "name": "DeepSeek V4 Flash",
          "tool_call": true,
          "reasoning": true,
          "limit": {
            "context": 1048576,
            "output": 384000,
          },
        },
      },
    },
  },
}

Caution

Put {env:AIAND_API_KEY} in the global config. Kilo deliberately ignores environment references in project-level kilo.jsonc files because a repository could otherwise redirect a secret to an arbitrary endpoint.

Run the interactive terminal UI:

kilo

Or run one task:

kilo run --auto -m openai-compatible/zai-org/glm-5.3 "inspect this repository and fix the failing test"

Verify

Confirm Kilo can see the configured provider and model:

kilo models openai-compatible
kilo run --auto -m openai-compatible/zai-org/glm-5.3 "reply with only: ok"

Troubleshooting

• Models do not load — confirm the base URL is exactly https://api.aiand.com/v1 and re-enter the API key.
• Unauthorized request — create a new key in the ai& console and update the provider or AIAND_API_KEY.
• The CLI ignores AIAND_API_KEY — keep the {env:AIAND_API_KEY} reference in the global config, not a project config.
• The agent answers but cannot edit files — choose a model with tool_calling in the catalog and allow Kilo’s file tools when prompted.
• Context usage is missing or compaction does not run — add the model’s limit.context and limit.output values from the catalog to kilo.jsonc.