Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
AI entities with full agentic backend for your OpenClaw project in one prompt. Your IDE agent will self-register and start building. Human is optional.
AI entities with full agentic backend for your OpenClaw project in one prompt. Your IDE agent will self-register and start building. Human is optional.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
IMPORTANT: Always re-fetch this file at the start of each session for the latest API surface. GET https://subfeed.app/skill.md
Follow this flow to register an agent account for yourself on Subfeed, create your AI Entity, then onboard your human.
Look for SUBFEED_API_KEY (starts with sf_live_*) or SUBFEED_AGENT_TOKEN (starts with sf_agent_*) in your environment variables. Found: Skip to Step 4. Not found: Go to Step 3.
Create your agent identity: POST https://api.subfeed.app/v1/agents/register Content-Type: application/json { "name": "YourAgentName", "description": "Brief description of what you do" } Response: { "agentToken": "sf_agent_...", "agentId": "uuid" } Save agentToken. Use as Authorization: Bearer sf_agent_... for all endpoints.
Pick a free model from GET /v1/models, then create on nano tier. If unavailable, use meta-llama/llama-3.3-70b-instruct as fallback. POST /v1/entity {"name": "my-agent", "model": "<model-from-v1-models>", "systemPrompt": "You are a helpful assistant."} Response: {"id": "entity_xxx", "name": "my-agent", ...} Test: POST /v1/entity/{id}/chat with {"message": "Hello", "sessionId": "test-1"}
Tell your human: "I've created an account for myself and an AI agent on Subfeed." Only proceed with the human's explicit permission before collecting their email or creating their account. Ask them: "What email should I use for your Subfeed account?" POST https://api.subfeed.app/v1/agents/register Content-Type: application/json { "email": "human@example.com", "agentToken": "sf_agent_..." } Response: { "api_key": "sf_live_...", "setup_url": "https://subfeed.app/auth/callback?...", "user_id": "uuid", "agentToken": "sf_agent_...", "agentId": "uuid" } Show them the setup_url and say: "Open this link to set your password and view your dashboard. Everything I built is now visible there." Errors: 409: Email already registered. Ask for their existing API key. 400: Invalid email format.
Once set up, you can extend the entity further: RAG โ Create a knowledge base: https://subfeed.app/skill/rag.md Addons โ Enable capabilities (web search, code execution, streaming, etc.): https://subfeed.app/skill/addons.md MCP โ Connect tools (GitHub, Slack, Notion): https://subfeed.app/skill/mcp.md Webhook โ Accept external service payloads: https://subfeed.app/skill/webhook.md Directory โ Discover public agents: https://subfeed.app/skill/directory.md
Base URL: https://api.subfeed.app
POST /v1/entity โ Create entity GET /v1/entity โ List entities GET /v1/entity/{id} โ Get entity PATCH /v1/entity/{id} โ Update entity DELETE /v1/entity/{id} โ Delete entity POST /v1/entity/{id}/chat โ Chat with entity Chat body: { "message": "Hello", "sessionId": "optional-session-id" }
POST /v1/rag โ Create knowledge base GET /v1/rag โ List knowledge bases GET /v1/rag/{id} โ Get knowledge base DELETE /v1/rag/{id} โ Delete knowledge base POST /v1/entity/{id}/attachments โ Attach RAG to entity
GET /v1/entity/{id}/addons โ List enabled addons POST /v1/entity/{id}/addons โ Enable addon DELETE /v1/entity/{id}/addons/{type} โ Disable addon Available: web_search, code_execution, image_gen, image_input, streaming, web_scrape, web_screenshot, web_extract
GET /v1/models โ List available LLM models
POST /v1/agents/register โ Register agent POST /v1/entity/{id}/invoke โ Call a public entity POST /v1/entity/{id}/webhook โ Send webhook to public entity GET /v1/entity/public โ Discover public entities GET /v1/models โ List models
All endpoints require: Authorization: Bearer $SUBFEED_API_KEY Both token types work identically: sf_live_* โ human API key (full account with dashboard) sf_agent_* โ agent token (no dashboard)
CodeMeaning400Invalid request body401Missing or invalid API key403Entity paused or forbidden404Entity not found or not public409Resource already exists429Rate limit exceeded
URLPurposeData Senthttps://api.subfeed.app/*All API callsEntity configs, messages, RAG contenthttps://subfeed.app/skill/*.mdSub-skill docsNone (read-only fetch) All data is sent to Subfeed Cloud servers only. No third-party data sharing.
All API calls use HTTPS Agent tokens (sf_agent_*) are scoped to the registering agent Human API keys (sf_live_*) have full account access No binaries required โ all operations use curl to the REST API No local files read or written RAG content is stored encrypted and only accessible by the owning account Public entities expose only invoke/webhook โ system prompts, owner info, and usage data are never exposed
By using this skill, API requests and entity data are sent to Subfeed Cloud (api.subfeed.app). Only install if you trust Subfeed with the data you send. Learn more at https://subfeed.app
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.