Coding agents

Configure OpenCode to use offmem (an API compatible with OpenAI). The key is already in the OFFMEM_API_KEY environment variable; do not show the key in your reply.

Create or edit ~/.config/opencode/opencode.json (Windows: %USERPROFILE%\.config\opencode\opencode.json), merging this content without deleting what is already there:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "offmem": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "offmem",
      "options": {
        "baseURL": "https://api.offmem.app/v1",
        "apiKey": "{env:OFFMEM_API_KEY}"
      },
      "models": {
        "offmem-glm-5.3-flash-abliterated": {
          "name": "GLM 5.3 Flash"
        },
        "offmem-deepseek-v4.1-flash-abliterated": {
          "name": "DeepSeek V4.1 Flash"
        },
        "offmem-glm-5.3-abliterated": {
          "name": "GLM 5.3"
        },
        "offmem-kimi-k3.1-pro": {
          "name": "Kimi K3.1 Pro"
        },
        "offmem-minimax-m3.1-flash": {
          "name": "MiniMax M3.1 Flash"
        },
        "offmem-deepseek-v4.1-flash-fast": {
          "name": "DeepSeek V4.1 Flash Fast"
        }
      }
    }
  },
  "model": "offmem/offmem-glm-5.3-abliterated",
  "small_model": "offmem/offmem-glm-5.3-flash-abliterated"
}

At the end, tell me: Open OpenCode, type /models and pick "GLM 5.3" from the offmem provider.

Configure Claude Code to use offmem (an API compatible with Anthropic). The key is already in the OFFMEM_API_KEY environment variable; do not show the key in your reply.

Create or edit ~/.claude/settings.json (Windows: %USERPROFILE%\.claude\settings.json), merging this content without deleting what is already there:

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.offmem.app",
    "ANTHROPIC_AUTH_TOKEN": "COLE_SUA_CHAVE_AQUI",
    "ANTHROPIC_MODEL": "offmem-glm-5.3-abliterated",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "offmem-glm-5.3-abliterated",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "offmem-glm-5.3-abliterated",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "offmem-glm-5.3-flash-abliterated",
    "CLAUDE_CODE_SUBAGENT_MODEL": "offmem-glm-5.3-abliterated",
    "CLAUDE_CODE_MAX_CONTEXT_TOKENS": "200000"
  }
}

Replace COLE_SUA_CHAVE_AQUI with the value of the OFFMEM_API_KEY environment variable (this file does not read variables).

At the end, tell me: Reopen Claude Code and run /status: "Anthropic base URL" should show the offmem address.

Configure OpenClaw to use offmem (an API compatible with OpenAI). The key is already in the OFFMEM_API_KEY environment variable; do not show the key in your reply.

Create or edit ~/.openclaw/openclaw.json, merging this content without deleting what is already there:

{
  agents: {
    defaults: {
      model: { primary: "offmem/offmem-glm-5.3-abliterated" },
    },
  },
  models: {
    mode: "merge",
    providers: {
      offmem: {
        baseUrl: "https://api.offmem.app/v1",
        apiKey: "${OFFMEM_API_KEY}",
        api: "openai-completions",
        models: [
          { id: "offmem-glm-5.3-flash-abliterated", name: "GLM 5.3 Flash" },
          { id: "offmem-deepseek-v4.1-flash-abliterated", name: "DeepSeek V4.1 Flash" },
          { id: "offmem-glm-5.3-abliterated", name: "GLM 5.3" },
          { id: "offmem-kimi-k3.1-pro", name: "Kimi K3.1 Pro" },
          { id: "offmem-minimax-m3.1-flash", name: "MiniMax M3.1 Flash" },
          { id: "offmem-deepseek-v4.1-flash-fast", name: "DeepSeek V4.1 Flash Fast" },
        ],
      },
    },
  },
}

At the end, tell me: Restart OpenClaw and send "ok" to test.

Configure Hermes Agent to use offmem (an API compatible with OpenAI). The key is already in the OFFMEM_API_KEY environment variable; do not show the key in your reply.

Create or edit ~/.hermes/config.yaml, merging this content without deleting what is already there:

model:
  default: offmem-glm-5.3-abliterated
  provider: custom
  base_url: https://api.offmem.app/v1
  key_env: OFFMEM_API_KEY

Back up config.yaml first. If Hermes cannot see the variable, put it in ~/.hermes/.env. If key_env is not accepted, tell me instead of saving the key in the config.

At the end, tell me: Restart the session and send "ok" to test.

Configure Pi to use offmem (an API compatible with OpenAI). The key is already in the OFFMEM_API_KEY environment variable; do not show the key in your reply.

Create or edit ~/.pi/agent/models.json, merging this content without deleting what is already there:

{
  "$schema": "https://pi.dev/schemas/models.schema.json",
  "providers": {
    "offmem": {
      "name": "offmem",
      "baseUrl": "https://api.offmem.app/v1",
      "api": "openai-completions",
      "apiKey": "$OFFMEM_API_KEY",
      "models": [
        {
          "id": "offmem-glm-5.3-flash-abliterated",
          "name": "GLM 5.3 Flash"
        },
        {
          "id": "offmem-deepseek-v4.1-flash-abliterated",
          "name": "DeepSeek V4.1 Flash"
        },
        {
          "id": "offmem-glm-5.3-abliterated",
          "name": "GLM 5.3"
        },
        {
          "id": "offmem-kimi-k3.1-pro",
          "name": "Kimi K3.1 Pro"
        },
        {
          "id": "offmem-minimax-m3.1-flash",
          "name": "MiniMax M3.1 Flash"
        },
        {
          "id": "offmem-deepseek-v4.1-flash-fast",
          "name": "DeepSeek V4.1 Flash Fast"
        }
      ]
    }
  }
}

Create or edit ~/.pi/agent/settings.json, merging this content without deleting what is already there:

{
  "defaultProvider": "offmem",
  "defaultModel": "offmem-glm-5.3-abliterated"
}

At the end, tell me: Run /reload, pick the model with /model and send "ok" to test.

Configure DeepSeek Harness to use offmem (an API compatible with OpenAI). The key is already in the OFFMEM_API_KEY environment variable; do not show the key in your reply.

Create or edit ~/.dsh/profiles/<profile>/cordis.patch.yml, merging this content without deleting what is already there:

- name: '@deepseek-ai/dsh-llm-pi-ai'
  config:
    providers:
      offmem:
        displayName: offmem
        apiKeyEnv: OFFMEM_API_KEY
        api: openai-completions
        baseURL: https://api.offmem.app/v1
        models:
          - id: offmem-glm-5.3-flash-abliterated
            name: GLM 5.3 Flash
          - id: offmem-deepseek-v4.1-flash-abliterated
            name: DeepSeek V4.1 Flash
          - id: offmem-glm-5.3-abliterated
            name: GLM 5.3
          - id: offmem-kimi-k3.1-pro
            name: Kimi K3.1 Pro
          - id: offmem-minimax-m3.1-flash
            name: MiniMax M3.1 Flash
          - id: offmem-deepseek-v4.1-flash-fast
            name: DeepSeek V4.1 Flash Fast
- name: '@deepseek-ai/dsh-agent-default-model'
  config:
    provider: offmem
    model: offmem-glm-5.3-abliterated

At the end, tell me: Validate with "dsh --profile <profile> --dump-config", restart dsh and send "ok".

Configure OpenBot to use offmem (an API compatible with OpenAI). The key is already in the OFFMEM_API_KEY environment variable; do not show the key in your reply.

Create or edit .env (OpenBot root), merging this content without deleting what is already there:

OPENAI_BASE_URL=https://api.offmem.app/v1
OPENAI_API_KEY=COLE_SUA_CHAVE_AQUI
COPILOTKIT_OPENAI_API=chat
BOT_MODEL=offmem-glm-5.3-abliterated

Create or edit model.yaml (tenant package), merging this content without deleting what is already there:

provider: openai
credential_secret_ref: openai-api-key
default_model: offmem-glm-5.3-abliterated

Replace COLE_SUA_CHAVE_AQUI with the value of the OFFMEM_API_KEY variable and do not delete the CopilotKit key.

At the end, tell me: Restart with scripts/start.sh and send "ok" to a Bot.

Base URL: https://api.offmem.app/v1
API key:  om_...
Model ID: offmem-glm-5.3-abliterated