architecture
34 notes tagged architecture in the AI agents topic. How agents are built, tuned and run: loops, harnesses, MCP, skills and coding agents, with what broke and what we measured.
- Agentic engineering: the series map and how to read it
A series on building agentic software for engineers who know the classic lifecycle, and how its pillars, deep dives and reading paths fit together.
- Related notes by meaning: an embedding index won memo's Ask and lost the chat eval
Memo now picks the related notes Ask reads beside each article from a 522-note bge-m3 index instead of the folder a note sits in. The same index lost a blind 40-question…
- Memo, rebuilt: Elixir and DuckDB out, Cloudflare and D1 in
Memo's May 2025 build notes described Elixir, DuckDB and GitHub Pages. This report sets them beside today's Workers, D1, R2 and two-repo publish, with the dates, PRs and…
- Guest writers on memo, keyed by the writer's own domain
How memo.d.foundation publishes posts from writers' own blogs as native notes: domain-verified joins, semi-auto review with a human verdict, ICY rewards per post, and…
- Five layers to tune before you fork your agent
What makes AI agentic, how to split a deterministic core from an agentic edge, and the five layers you can tune without rebuilding the harness. Real numbers from circle…
- DeepSeek harness, dissected
An architecture read of dsh, DeepSeek's new agent harness: the plugin tree, the patch-layer boot, the log-first session model, and what it means for a Claude Code shop.
- CAP breakdown
Technical analysis of CAP, an open-source, cross-platform screen recording system and its Instant mode screen recording implementation.
- Context7 breakdown
Technical analysis of Context7, an intelligent documentation indexing and retrieval system that transforms raw library docs into AI-optimized, ranked snippets for…
- E2b breakdown
Technical analysis of E2B, a cloud infrastructure platform that runs AI-generated code in secure, isolated sandboxes using lightweight virtual machines that start in…
- Dify breakdown
Technical analysis of the Dify platform, its architecture, and engineering decisions that enable scalable LLM application development.
- Umami breakdown
Comprehensive technical analysis of Umami, a modern, privacy-focused web analytics platform.
- Mem0 & Mem0-Graph breakdown
Technical analysis of Mem0, a scalable memory architecture for LLMs, and its graph-based variant, Mem0-Graph, designed for long-term conversational coherence.
- Cline breakdown
Comprehensive technical analysis of Cline's VS Code extension architecture, covering system design, implementation patterns, and architectural innovations
- Ax framework breakdown
Technical analysis of the Ax TypeScript framework for building LLM-powered agents with DSPy capabilities.
- Crawl4AI breakdown
Deep dive into Crawl4AI's architecture, data structures, and algorithms - from async pipelines and strategy patterns to browser management and intelligent content…
- Zen MCP breakdown
Technical analysis of the Zen MCP (Model Context Protocol) Server architecture, implementation, and design patterns.
- Composing the future, part 1: agent basics, LangGraph and Autogen
What makes a system agentic, why multi-agent beats single-agent, how orchestration works, and a close look at LangGraph and Microsoft Autogen.
- Composing the future, part 2: OpenAI's agent tools, MCP and fast-agent
How OpenAI's Swarm and newer agent tools work, why Model Context Protocol matters for tool access, and how fast-agent builds MCP-native agents.
- Composing the future, part 3: Mastra and CrewAI
Two frameworks with opposite instincts: Mastra for TypeScript teams building web-native agents, and CrewAI for role-playing crews of Python agents.
- Composing the future, part 4: LlamaIndex and the framework face-off
LlamaIndex's agent features for document-heavy work, then a side-by-side comparison of the frameworks on differentiators, strengths and ease of development.
Show all 34
- Composing the future, part 5: agent patterns, open problems and how to choose
The common agent composition patterns, the problems that remain unsolved, where the field is heading, and guidance for picking a framework.
- MCP playbook code flow
A detailed look into the mcp-playbook's internal code flow, data handling for chat logs and prompts, and interactions with GitHub repositories like prompt-db and…
- MCP playbook data flow
How data flows through the MCP playbook server, from MCP client requests to tool execution and interactions with the file system and GitHub. This overview helps you…
- Append-only concept embedding log
RFC proposing a novel approach to track concept evolution using TimescaleDB with pgvector/pgvectorscale, enabling historical semantic analysis and preventing…
- MCP authorization over SSE
A Request for Comments (RFC) detailing a comprehensive specification for implementing OAuth 2.1 authorization within the Model Context Protocol (MCP) when using…
- Brainery architecture
An overview of Brainery's architecture, detailing how it ingests, processes, and transforms data from diverse sources into a dynamic knowledge base.
- Building a data-driven project reporting system: A lens into modern data engineering
Learn how to transition from application development to data engineering by building a modern project reporting system. Discover essential mindset shifts, best…
- Why micro frontend
As web applications become more complex and feature-rich, traditional frontend architectures such as monolithic will become harder to maintain, scale, and evolve.…
- Domain-driven design primer, from overview to entities and the domain model
Notes on domain-driven design after Eric Evans, covering what DDD is for, when to use it, how entities get identity and continuity, and how a domain model is built from…
- Finite state machines: automata, transducers, Mealy and Moore machines
How finite-state automata, finite-state transducers, Mealy machines and Moore machines relate, with the formal definitions, the differences between them and TypeScript…
- Architecture decision records: documenting software choices
Learn how Architecture Decision Records (ADR) help teams document software choices, improve project clarity, and guide newcomers with clear context, solutions, and…
- Hyperledger Fabric architecture for permissioned enterprise networks
Learn how Hyperledger's open source blockchain frameworks and tools enable secure, permissioned enterprise networks with smart contracts, distributed ledgers, and…