GroqCloud runs Llama 3.3 70B at 250+ tok/sec on LPU silicon. OpenAI-compatible API. Free tier, sub-second TTFT, ideal for streaming.
GroqCloud Quickstart — 250 tokens/sec OpenAI-Compat API
GroqCloud runs Llama 3.3 70B at 250+ tok/sec on LPU silicon. OpenAI-compatible API. Free tier, sub-second TTFT, ideal for streaming.
这个资产会安全暂存
这个资产会先安全暂存。复制的指令会要求 Agent 读取暂存文件,并在激活脚本、MCP 配置或全局配置前先确认。
npx -y tokrepo@latest install 8ac70a0d-0996-4fa9-a316-c9e586d54f86 --target codex先暂存文件;激活前需要读取暂存 README 和安装计划。
讨论
相关资产
xAI Grok API Quickstart — OpenAI-Compatible Frontier Model
xAI Grok API is OpenAI-compatible at api.x.ai/v1. Swap base URL + key, keep the SDK. Grok-3, Grok-2 Vision, 1M-token context.
Phoenix Tracing Quickstart — OpenInference Tracer Setup
Phoenix instruments OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI via OpenInference. Local UI or Arize cloud. No per-call code changes.
SwarmVault — Local-First LLM Wiki + Graph
SwarmVault turns docs/code/transcripts into a durable Markdown wiki plus a local knowledge graph for agents, with a 30-second `quickstart` CLI path.
SEC EDGAR MCP Server — Query Filings from Agents
SEC EDGAR MCP Server lets agents query filings (10-K/10-Q/8-K) with exact numbers and source URLs. Verified 265★; Docker quickstart in ~5–10 minutes.