ai
Eden AI CLI for Headless Automation
Use the Eden AI CLI for headless automation with headless JSON commands, schema discovery, credentials, and permission controls.
6 functions 4 read 2 write API key auth
Eden AI CLI for Headless Automation
Use KosmoKrator as a non-interactive integration runtime for local automations and wrappers.
Use headless automation when another tool needs a stable local command surface. The Eden AI CLI uses the same integration registry as the TUI, Lua runtime, and MCP gateway, but returns predictable command output for automation.
Command Shape
# Eden AI CLI for Headless Automation
kosmokrator integrations:configure eden-ai --set api_key="$EDEN_AI_API_KEY" --enable --read allow --write ask --json
kosmo integrations:call eden-ai.edenai_generate_text '{"providers":"example_providers","text":"example_text","conversation":"example_conversation","temperature":1,"max_tokens":1,"fallback_providers":"example_fallback_providers"}' --jsonDiscovery Before Execution
Agents and scripts can inspect Eden AI docs and schemas before choosing a function.
kosmo integrations:docs eden-ai --json
kosmo integrations:docs eden-ai.edenai_generate_text --json
kosmo integrations:schema eden-ai.edenai_generate_text --json
kosmo integrations:search "Eden AI" --json
kosmo integrations:list --jsonUseful Eden AI CLI Functions
| Function | Type | Parameters | Description |
|---|---|---|---|
eden-ai.edenai_generate_text | Write | providers, text, conversation, temperature, max_tokens, fallback_providers | Generate text using AI models via Eden AI. Supports providers like OpenAI (GPT-4), Anthropic (Claude), Google (Gemini), Mistral, Cohere, and more. You can send a single prompt or a conversation history. |
eden-ai.edenai_analyze_image | Read | providers, image_url, image_base64, features, fallback_providers | Analyze images using AI models via Eden AI. Supports object detection, explicit content detection, scene description, and more. Provide an image as a URL or base64-encoded string. |
eden-ai.edenai_translate_text | Write | providers, text, source_language, target_language, fallback_providers | Translate text between languages using AI models via Eden AI. Supports providers like Google Translate, DeepL, Amazon Translate, Microsoft Translator, and more. Detects the source language automatically if not specified. |
eden-ai.edenai_transcribe_audio | Read | providers, audio_url, audio_base64, language, speakers, fallback_providers | Transcribe audio or video to text using AI models via Eden AI. Supports providers like OpenAI (Whisper), Google Speech-to-Text, Amazon Transcribe, Microsoft Azure, and more. Provide audio as a URL or base64-encoded string. |
eden-ai.edenai_ocr | Read | providers, document_url, document_base64, language, fallback_providers | Extract text from images and documents using OCR via Eden AI. Supports providers like Google Cloud Vision, Amazon Textract, Microsoft Azure, and more. This is an async operation — the response may contain a public_job_id for tracking. Provide the document as a URL or base64-encoded string. |
eden-ai.edenai_get_current_user | Read | none | Get the current Eden AI user's account information, including email, plan, and usage details. Useful for verifying API connectivity and checking account status. |
Automation Notes
- Use
--jsonfor machine-readable output. - Keep credentials out of argv by using environment variables or stored KosmoKrator configuration.
- Configure read/write policy before unattended runs; use
--forceonly for trusted automation. - Use the MCP gateway instead when the agent needs dynamic tool discovery inside a conversation.