#composable runtime
101 related articles
·3 min
Vercel Open-Sources fx: A 6MB Zig-Powered Coding Agent Where Minimalist Design Makes Models Stronger
Vercel open-sources fx, a 6MB Zig-powered coding agent with near-instant startup. Supports local/cloud models, MCP protocol, and embeddable design.
Read more →
·2 min
Google Rebuilds the Play Store with Jetpack Compose: A Trial-by-Fire Technical Gamble
Google chose the Play Store — the world's most-installed app — as the first large-scale Jetpack Compose deployment, a high-stakes trial by fire across billions of devices.
Read more →
·3 min
Millwright: Redefining the Boundaries Between MLOps Tools with Rust
Millwright is a Rust-based open-source MLOps framework that composes ML lifecycle stages through a unified contract layer with a Python API. We analyze its architecture and the decoupling vs. unification tradeoff.
Read more →
·3 min
How to Become an AI Developer? A Systematic Beginner's Roadmap
A complete learning roadmap to become an AI developer from scratch: covering Python basics, math foundations, ML/DL core concepts, LLM application development, and hands-on project experience.
Read more →
·6 min
Flask Creator's Conversation: Why We Need to Slow Down in the AI Coding Era
Flask creator Armin Ronacher and minimalist Agent Pi's author Mario Zechner discuss AI coding limitations, code quality decline, MCP vs CLI, and why engineers need to slow down.
Read more →
·4 min
Software Engineering in the Agentic Era: The Development Paradigm Is Being Fundamentally Reshaped
An in-depth analysis of how AI agents are reshaping software engineering paradigms—from code completion to autonomous execution—covering agentic workflows, productivity shifts, reliability challenges, and the evolving role of engineers.
Read more →
·3 min
Custom GPU Kernels Speed Up AlphaFold Protein Model by 6.8x
Open-source GPU kernel library fast_trimul optimizes triangle multiplicative update operations in AlphaFold3 family models, achieving 4.5-6.8x speedup with 2.2-2.4x memory reduction for short sequences.
Read more →
·3 min
DeepSeek Harness Hands-On Review: A Transparent AI Coding Framework Where Everything Is a Plugin
Hands-on review of DeepSeek Harness developer preview: its everything-is-a-plugin architecture, fully transparent tracing, Creator Mode for conversational plugin development, and flexible multi-model support.
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 →
·3 min
Gemini 3.7 Flash Release and GPT-5.6 Ultra-Fast Mode: AI Open Source Enters the Ecosystem Era
Google releases Gemini 3.7 Flash for coding and Agent optimization while OpenAI launches GPT-5.6 Ultra-Fast mode with 14x speed gains. AI open source shifts from open models to open ecosystems.
Read more →
·3 min
DeepSeek Harness Hands-On Review: A New Benchmark for Plugin-Based Agentic Coding
In-depth review of DeepSeek Harness agentic coding system: plugin architecture, 95% cache hit rate, Flash vs Pro comparison, and real-world ISS tracker built with 20M tokens.
Read more →
·3 min
What Are Agent Skills? A Comprehensive Guide to the AI Agent Development Architecture Paradigm
Deep dive into Agent Skills architecture for AI agents, covering Skill framework definitions, MCP protocol, multi-agent collaboration, and practical applications for building enterprise-grade Agent systems.
Read more →
·3 min
LangGraph Beginner's Guide: A Complete Tutorial for Building Enterprise-Grade AI Agents
LangGraph beginner tutorial covering environment setup, state management, and Graph API programming model to help developers build enterprise-grade AI Agent applications from scratch.
Read more →
·4 min
Deep Dive into DeepSeek Harness: Core Design of a Self-Evolving Agent Architecture
Deep dive into DeepSeek Harness (DSH) core architecture: the Intelligence = Model + Harness formula, Codis mechanism, five stages of Agent evolution, and how composable runtimes enable AI self-evolution.
Read more →
·3 min
Extensible Software in the Age of LLMs: Reconstructing the Architectural Paradigm
Exploring how LLMs redefine software extensibility: from natural language interfaces to agent-driven dynamic orchestration, analyzing key principles, tool interface design, MCP protocol, and future challenges.
Read more →
fx: A Deep Dive into the Minimalist Op…
·3 min
fx: A Deep Dive into the Minimalist Open-Source Native Coding Agent
Deep dive into fx, the open-source coding agent built on Tiny, Open, and Native principles. Exploring its unique value in controllability, privacy, and model agnosticism.
Read more →
·3 min
Rust Behavior Tree Library Bonsai Surpasses 100K Downloads: From Game NPCs to NASA Robots
Rust behavior tree library Bonsai hits 100K downloads on crates.io, powering Titanfall 2 game bots and NASA Lunabotics space robots after four years of open-source development.
Read more →
·2 min
GitHub Daily · August 15: The Agent-Native Era and Low-Barrier LLM Fine-Tuning
GitHub Trending Aug 15: cordis meta-framework surges 616 stars, Soup enables 8B model fine-tuning on 4GB VRAM, CLI-Anything drives Agent-Native software.
Read more →
·4 min
Microsoft Agent Framework in Practice: Building Enterprise-Grade AI Agents with .NET
A deep dive into Microsoft Agent Framework for building enterprise AI agents with .NET, covering tool calling, multi-agent orchestration, Qdrant RAG, and A2A, MCP, AGUI protocols.
Read more →
·2 min
Hax: A Minimalist Terminal AI Coding Assistant Written in C
Hax is a minimalist AI coding assistant written in C that runs natively in the terminal. Zero dependencies, ultra-lightweight, and instant startup — built for terminal workflows.
Read more →