agent-infrastructure

Agent infrastructure that runs itself. Six tools for autonomous agents: free LLM model recommendations across 17 models, real-time provider availability monitoring, LLM routing proxy with 3% margin, and stateless memory compression with 5 free sessions. All paid services via x402 on Solana USDC. No human accounts, no API keys — agents connect and go.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://agent-infrastructure--getkin.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "agent-infrastructure": {
      "url": "https://agent-infrastructure--getkin.run.tools"
    }
  }
}

能力清单

工具	说明
recommend_model	Get the optimal LLM for any task based on cost, speed, and quality. Compares 17 models across 6 providers (Anthropic, OpenAI, Google, Mistral, DeepSeek, Meta). FREE — no payment required. Args: task: Task type — code-generation, summarization, translation, creative-writing, data-analysis, classification, conversation, reasoning, extraction, or general priority: What to optimize for — cost, speed, or quality max_tokens: Expected output length in tokens
check_availability	Check real-time availability and latency of LLM provider APIs. Monitors Anthropic, OpenAI, Google, Mistral, DeepSeek, and Meta endpoints. Tells you if a service is up before you call it. Costs $0.005 USDC via x402 on Solana. Args: provider: Filter by provider name, or 'all' for everything. Options: anthropic, openai, google, mistral, deepseek, meta, all
route_llm_call	Route an LLM chat completion through GetKin's proxy. OpenAI-compatible format. We forward to the provider, return the response, and charge a 3% margin. Currently supports Google Gemini models. Costs provider rate + 3% margin via x402 on Solana. Args: model: Model ID (e.g. gemini-2.5-flash, gemini-3-flash-preview, gemini-3.1-pro-preview) messages: Chat messages in OpenAI format [{"role": "user", "content": "Hello"}] max_tokens: Maximum output tokens temperature: Creativity (0.0 to 2.0)
compress_memory	Compress a raw session dump into structured short-term, medium-term, and long-term memory. Stateless — we never store your data. Send your existing memory files (if any) plus the new session dump, get back updated structured memory. First 5 compressions free, then $0.03 USDC via x402. Args: agent_id: Your unique agent identifier (used for free tier tracking only) session_dump: Raw session content — conversation logs, decisions, observations, anything from this work session existing_memory: Your current memory from a previous compression. Include short_term, medium_term, long_term fields. Omit on first use. session_metadata: Optional info about the session — task_type, duration_minutes, tools_used
list_models	List all models available through GetKin's routing proxy with current pricing. Returns model IDs, providers, and per-token costs. FREE — no payment required.
check_memory_usage	Check how many free memory compressions remain for an agent. FREE — no payment required. Args: agent_id: The agent identifier to check usage for

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。