#agent development SDK
418 related articles
·4 min
Building AgentOS with Claude Agent SDK: Automating 95% of Development and Operations Work
Developer Danny Postma built AgentOS on Claude Agent SDK, automating 95% of coding and ops tasks. Deep dive into container isolation, permission control, task orchestration, and human-in-the-loop design.
Read more →
Tech Frontiers·2 min
Breaking Down the Claude Code SDK Demo Project: Hands-On AI Agent Development from Anthropic's Open Source Release
Deep dive into Anthropic's open-source claude-agent-sdk-demos project, covering Claude Code SDK core capabilities, TypeScript demos, multi-step task orchestration, and tool call integration for AI agent development.
Read more →
·3 min
patent-disclosure-skill: An AI-Powered Open-Source Tool for the Entire Chinese Patent Workflow
Deep dive into patent-disclosure-skill, a trending open-source AI tool covering China's full patent workflow — from patent mining and disclosure drafting to office action responses.
Read more →
·3 min
Vessel: A Local LLM Observability Proxy for Request Capture and Cross-Model Replay Comparison
Vessel is a free, open-source local LLM observability proxy supporting Ollama, LM Studio, and more. Capture requests, track tokens, replay across models, with built-in MCP server and Web UI.
Read more →
·3 min
Grok Lands on the Gemini Platform: The AI Control Plane Is Becoming the Real Product
xAI's Grok 4.6 is now on Google Cloud's Gemini Enterprise Agent Platform, revealing a shift in AI competition from model capabilities to the control plane.
Read more →
·4 min
Getting Started with DeepSeek Harness: An Agent Framework Where Everything Is a Plugin
A detailed guide to DeepSeek's open-source Agent runtime framework Harness—from its core "everything is a plugin" philosophy to installation, source code walkthrough, and hands-on experience.
Read more →
·3 min
Agent Observability: Why Traditional Monitoring Falls Short and Practical Solutions
Explore why traditional monitoring (latency, drift, accuracy) fails for AI agents, and learn practical solutions using LangFuse, LangSmith, and OpenTelemetry.
Read more →
·1 min
Aramb: The AI Agent Operating System — Build and Monetize with a Single Line of Code
Aramb positions itself as an AI agent OS, integrating runtime, memory, browser, tools, models, and billing into a single API to help developers build, ship, and monetize agents fast.
Read more →
·2 min
The Complete AI Coding Tools Landscape: A Selection Guide from Claude Code to Cursor
A systematic comparison of AI coding tools including ChatGPT, Gemini, Claude, Cursor, Claude Code, and Codex — covering pricing, setup, and access solutions to help developers choose the right combination.
Read more →
·3 min
MCP Server Language Selection Guide: How to Choose Between Rust, Go, TypeScript, Python, and Java
Compare Rust, Go, TypeScript, Python, and Java for MCP Server development across deployment complexity, ecosystem maturity, and user-friendliness with scenario-based selection guidance.
Read more →
·3 min
Local MCP over stdio: An Architecture Seam Design Guide for Agentic Applications
A deep dive into using local MCP over stdio as an architectural seam for agentic applications, covering model-tool decoupling, testability, process management, and comparison with cloud MCP.
Read more →
·3 min
Hermes Agent Meets Grafana: A Practical Guide to AI Agent Observability
Explore why AI Agents need observability and how Hermes Agent integrates with Grafana for metrics, tracing, and log analysis to build stable, production-ready agent systems.
Read more →
·2 min
Anthropic Launches Official Claude Code Plugin Directory: A Curated High-Quality Extension Ecosystem
Anthropic launches claude-plugins-official, a curated directory of high-quality Claude Code plugins. Learn about its positioning, core value, and impact on the AI coding ecosystem.
Read more →
·3 min
Human Behavior: How AI Agents Close the Loop on Product Analytics Issues
Human Behavior is an AI-powered product analytics tool that uses a four-step pipeline — collect, understand, act, loop — to let AI agents automatically identify UX issues and submit fixes.
Read more →
·4 min
Benchmarking with Production Data: A Model Migration That Cut Costs by 91%
How to build free eval sets from production logs, validate candidate models with a two-layer architecture (deterministic checks + blind LLM judge), and migrate 14 of 16 tasks to cut 91% of token costs.
Read more →
·3 min
Harness Multi-Agent Framework: A Deep Dive into Planner→Builder→Evaluator Three-Agent Collaboration
Deep dive into the Harness multi-agent framework's three-agent paradigm (Planner, Builder, Evaluator), covering Agent Loop design, circular invocation prevention, Sandbox isolation, and A2A vs SubAgent selection strategies.
Read more →
·3 min
Run Multiple Open-Source OCR Models via a Unified API: 100K Pages for Just $60
VLM.run wraps open-source OCR models like DeepSeek-OCR-2, GLM-OCR, and dots.mocr into a unified OpenAI-compatible API. Parse 100K pages for just $60 with JSON output and MCP server support.
Read more →
·3 min
Complete Tutorial: Building an AI Programming Environment with OpenCode + MCP
Learn how to build an AI programming environment using open-source OpenCode with DeepSeek and MCP services. Covers tool comparison, model selection, and Plan/Build workflow setup.
Read more →
·3 min
Codex Harness Goes Open Source: AI Moats Shift from Models to Runtimes
OpenAI open-sources Codex Harness with Rust core, app server, and full AST processing. Same model scores nearly 3x higher on ARC-AGI-3, saves 6x tokens. Deep analysis of Codex vs DeepSeek Harness.
Read more →
·3 min
Amazon Bedrock Converse API in Practice: A Development Guide to Unified Interfaces and Streaming Chat
A deep dive into Amazon Bedrock's Converse API unified multi-model interface and ConverseStream streaming output, covering message structures, multi-turn conversations, event stream handling, and AWS ecosystem integration.
Read more →