Skip to content

Dev weekly 2025-Jul-21

Published: at 02:02 AM

AI

The Big LLM Architecture Comparison From DeepSeek-V3 to Kimi K2: A Look At Modern LLM Architecture Design Sebastian Raschka, PhD

Ilya Rice:我是如何赢得企业 RAG 挑战赛的

MemAgent: Reshaping Long-Context LLM with Multi-Conv RL based Memory Agent

Introducing ChatGPT agent: bridging research and action

ChatGPT agent System Card

什麼是 AI 應用評估的錯誤分析 Error Analysis?

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting - 字节跳动

LLM Inference Handbook - bentoml

Seed-X-PPO-7B 字节跳动 powerful series of open-source multilingual translation language models

愛好 AI Engineer 電子報 🚀 頂級 AI 公司的 Prompting 秘訣和 Claude Code 正夯 #28

Practical Guide for Model Selection for Real‑World Use Cases

The most realistic voice AI platform

vanna Chat with your SQL database

FlagEmbedding BGE builds one-stop retrieval toolkit for search and RAG FlagAI是大模型算法、模型,及各种优化工具的一站式、高质量开源项目

Prompt Engineering: From Zero to Hero promptz2h

使用 o3 从我保存的 Pocket 链接中分析自己

Gemini Embedding now generally available in the Gemini API

诱导大模型 | 新型“回音室”攻击和对抗技术 字节跳动技术

ChatGPT 发布 Agent 了,但我更推荐 MiniMax 池建强

让你的 AI Agent 拥有“永不遗忘”的超能力:LangGraph 与 PostgreSQL 实现长期记忆的深度实践

The Batch: 849 | 用于训练网页智能体的生成数据 deeplearning.ai

OpenAI 无需向量化的 RAG 新架构设计范式剖析

基于Dify动态解析异构银行流水:架构拆解→风控报告生成

拆解Agent项目:MindSearch

Agentic AI Architecture Framework for Enterprises

7 best free open source LLM observability tools right now

llm-almanac/advisor interactive chart indicates the per-replica throughput and client-side latency you can expect when running open weights language models on open source inference engines

Improved Knowledge Graph Creation with LangChain and LlamaIndex

ChatPDF. 纯原生实现RAG功能,基于本地LLM、embedding模型、reranker模型实现,支持GraphRAG

知识库基础原理介绍 - fastgpt

Deep Research Agents: A Systematic Examination And Roadmap 深度研究代理: 系统检查和路线图

Kite - News app by Kagi 开源的新闻app

linguist - powerful browser extension that is ready to replace your favorite translation service

Try featured notebooks on selected topics in NotebookLM

LlamaIndex Versus LangChain: Building Better Knowledge Graphs

langchain-graphrag GraphRAG / From Local to Global: A Graph RAG Approach to Query-Focused Summarization

银行流水尽职调查报告生成系统

Graph Mining Library a collection of clustering algorithms from Google

Build a Question Answering application over a Graph Database

EPUB Translator

Language Model Tool API VSCode API

Anthropic launches finance-specific Claude with built-in data connectors, higher limits and prompt libraries

TradingAgents: Multi-Agents LLM Financial Trading Framework

Programming

Everything I know about good system design 我所知道的关于优秀系统设计的一切

hnswlib - Header-only C++/python library for fast approximate nearest neighbors

Caching - planetscale

langchain-mcp-adapters This library provides a lightweight wrapper that makes Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph.

Introducing Amazon S3 Vectors: First cloud storage with native vector support at scale (preview)

Build and deploy Remote Model Context Protocol (MCP) servers to Cloudflare

Roadmap - Step by step guide to becoming a Rust developer in 2025

marimo The future of Python notebooks

Explore your Cloudflare data with Python notebooks, powered by marimo

NebulaGraph lite - minimal, ad-hoc way of plug and play NebulaGraph with pip install, even inside Colab Notebook

图像检索:OPQ索引与HNSW索引

Deploy a Streamlit App to AWS

Check Server-side Rendering (SSR)

Vercel 又出王炸,业界首个 TypeScript MCP 前端框架开源

Envoy AI Gateway 采用者参考架构

MCP规范完整中译稿:2025-3-26版

万字技术干货!LLM工程师必读量化指南,可视化图解揭秘大模型如何量化

一文带你彻底理解AIGC、Agent、MCP的概念和关系

当微信支付开放MCP之后

我是用这个Prompt画架构图的

Other

being too ambitious is a clever form of self-sabotage 过于野心勃勃是一种聪明的自我毁灭形式

一个青年暴君的画像

新疆 10 天自驾:夏日走过山间、草原和古城

谁是掌机行业的卷王?|「世界主宰」的掌机之路