#sub-agent system
426 related articles
·2 min
DeepSeek Harness rc.8 Released: Major Upgrades to Multimodal Image Understanding and Sub-Agent System
DeepSeek Harness rc.8 brings multimodal image processing, on-demand sub-agents, Windows terminal persistence, and SQLite optimization. The open-source Agent framework with 170K+ GitHub stars iterates at remarkable speed.
Read more →
·3 min
In-Depth Review of GPT 5.6 Soul: Sub-Agent Systems, Government Review, and Competitor Comparison
In-depth analysis of GPT 5.6 Soul: multi-sub-agent parallel architecture, Ultra Mode coding in practice, the controversy behind its 91.9% Terminal Bench score, and the trend of frontier AI entering government review.
Read more →
·4 min
Pi Coding Agent Deep Configuration Guide: A Complete Breakdown of Custom Tools, Sub-Agents, and the Skill System
A complete Pi Coding Agent configuration guide refined over two months, covering custom tools, sub-agents, persistent memory, security, and skill systems.
Read more →
·2 min
Deep Dive into DeepSeek Harness: The Ambition to Build Infrastructure, Not Just an Agent
A deep dive into DeepSeek Harness developer preview: its Agent infrastructure positioning, Codex kernel hot-swap design, four run modes, and Creation Mode's self-evolution capability.
Read more →
·4 min
Claude Code Hands-On Tutorial: Complete Guide from Installation to Automated Development
Complete guide to Claude Code covering environment setup, permission configuration, Go Goals autonomous loops, Skills system, MCP protocol integration, and version control for automated development.
Read more →
·2 min
DeepSeek Open-Sources Harness Framework: AI Competition Shifts from Models to Agents and Infrastructure
DeepSeek open-sources Harness framework, gaining 50K GitHub stars in 12 hours; Claude tackles Riemann Hypothesis; OpenAI's wafer-scale chip boosts inference 14x. AI competition shifts to agents and infrastructure.
Read more →
·5 min
What Is DeepSeek Harness? Dissecting the 7 Core Modules of Agent Architecture
Deep analysis of DeepSeek Harness: not just a product, but an Agent architecture paradigm. Dissecting 7 core modules including tool calling, memory systems, and sandbox environments.
Read more →
·3 min
DeepSeek Harness Explained: An Agent Runtime Where Everything Is a Plugin
Deep dive into DeepSeek Harness (DSH): its Agent=Model+Harness formula, Cordis plugin system, four runtime modes, and Trajectory traceability for modular Agent development.
Read more →
·4 min
Five Stages of Agent Evolution: From Model Calls to DeepAgents — A Deep Dive
A detailed breakdown of five evolutionary stages of AI agent development, from simple API calls to DeepAgents multi-agent architecture, helping developers understand the full progression and make informed choices.
Read more →
·3 min
Codex vs Claude Code Real-World Comparison: Efficiency and Quality Differences When Building Apps from the Same Prompt
Real-world test comparing Codex and Claude Code building a Typeform alternative from the same prompt, revealing major differences in quality, efficiency, and cost.
Read more →
·5 min
The Complete Guide to Pi Agent: How Four Tools Beat Codex and Claude Code
Deep analysis of Pi programming Agent's minimalist design: just four tools and a 1000-token prompt outperform Codex and Claude Code in speed, cost, and code quality.
Read more →
·4 min
OpenAI Astra Approaching Release, Qwen Local Model Closing in on Closed-Source Frontier
OpenAI's next-gen model Astra nears release as multi-agent orchestrator; Qwen 3.8 27B local model surpasses multiple closed-source models on Agentic Index; Cursor launches Origin to challenge GitHub.
Read more →
·3 min
LangChain4j No AI Agent in Practice: Agent Architecture Without Accessing LLMs
Deep dive into LangChain4j No AI Agent implementation: inline tool methods as plain Java methods to avoid costly, slow high-frequency LLM calls in Agent systems.
Read more →
·3 min
Claude Code Multi-Session Communication and Collaboration: A Practical Exploration of Multi-Agent Programming
Exploring how multiple Claude Code sessions can communicate and collaborate, enabling multi-agent programming workflows with message-passing mechanisms and AI coordination.
Read more →
·4 min
Context Engineering in Practice: Why Keeping Everything Actually Costs Less
Towards AI tested that keeping full context with prompt caching beats summarization in cost, speed, and recall. Learn why compression can be a trap and how hybrid search solves scaling.
Read more →
·2 min
Deep Dive into Design Patterns and Common Pitfalls of Multi-Agent Systems
Deep analysis of Anthropic's multi-agent system patterns and pitfalls, covering task decomposition, parallel exploration, token cost control, coordination complexity, and engineering best practices.
Read more →
·3 min
OpenAI's Hacker Model Answers 95% of Requests Without Refusal; Claude Advances Riemann Hypothesis Record
OpenAI launches GPT-5.6 Cyber hacker model with 95% response rate; Claude advances Riemann Hypothesis record from 41.6% to 67.2%; Meta open-sources 30B local agent model; Tencent generates 3D worlds from text.
Read more →
·3 min
Getting Started with Langfuse: A Comprehensive Guide to LLM Observability and Agent Evaluation
A comprehensive guide to Langfuse, the open-source LLMOps platform for agent tracing, token cost analysis, prompt version management, automated evaluation, and full-stack LLM observability.
Read more →
·3 min
Antigravity vs Claude Code vs Cursor: How to Choose Your AI Coding Assistant
In-depth comparison of Google Antigravity, Claude Code, and Cursor across features, pricing, and real-world use to help you pick the best AI coding assistant.
Read more →
·2 min
Quickly Understanding Legacy Project Architecture with OpenSpec Explore
Learn how to use OpenSpec explore in VS Code with GitHub Copilot to automatically analyze legacy project architecture, tech stack, and core features for rapid codebase understanding.
Read more →