Tagged articles
AI coding agent
54 articles · Page 1 of 1
The author details using OpenAI's GPT-6.2 Astra in Codex to autonomously investigate complex, cross-service bugs in legacy Java systems by tracing call chains, forming hypotheses, writing reproduction tests, and producing minimal verified fixes, shifting AI's role from code generation to end-to-end debugging.
AI coding agentCodexGPT-6.2 Astra
0 likes · 17 min read

The article benchmarks the new Wu code editor against Zed and VS Code, showing Wu uses 383 MiB idle and 583 MiB during repository search — 58% less than Zed — while integrating Claude Code, OpenAI Codex, and OpenCode as built-in AI agents.
AI coding agentOpen SourceRust
0 likes · 8 min read

A detailed hands-on review of Octop, Tencent's open-source AI coding agent positioned as a WorkBuddy alternative, covering installation, configuration, expert/team system, ACP protocol for delegating to external agents, and local-data enterprise advantages.
ACP protocolAI coding agentOctop
0 likes · 12 min read

The author tests Alibaba's Qoder CN AI coding agent with Qwen3.8-Flash, building a personal accounting dashboard using Vite, Vue3, Element Plus, and ECharts, demonstrating the agent's ability to plan steps, write code, install dependencies, launch a dev server, self-verify rendering in a built-in browser, and iterate via visual annotations.
AI coding agentEChartsElement Plus
0 likes · 8 min read

The author tests MiniMax Code's $7/month Go plan, revealing a proactive, stubborn agent built on Pi v0.79.1 with sandbox security, multi-device sync, and M3.1 Flash model benchmarks (DeepSWE 73.7%, OSWorld 61.7%), showing it undercuts DeepSeek's pay-as-you-go pricing for daily heavy use.
AI coding agentM3.1 FlashMiniMax Code
0 likes · 14 min read

DeepSeek Harness publishes its six-direction product roadmap adding remote and mobile access, personalized long-term memory, browser and GUI automation, agent team collaboration, session sharing for multi-user workflows, and enhanced sandbox security, while revealing it leads as the most-used coding agent among DeepSeek API users.
AI coding agentDeepSeek HarnessGUI automation
0 likes · 9 min read

Jason Liu, author of the 13k-star Instructor library and new OpenAI Codex team member, shares his battle-tested Codex workflows: persistent cross-month threads, voice-driven delegation, Heartbeats scheduling for Slack/email automation, @computer UI control, verification via unit tests, local Obsidian memory management, and the new Goal mode for autonomous multi-day tasks.
AI coding agentCodexGoal mode
0 likes · 9 min read


IT XianyuOct 22, 2026 · Artificial Intelligence
The article analyzes OpenAI's GPT-6 Astra, highlighting its 105k context window, 128k output tokens, and tool-use capabilities that enable end-to-end coding tasks, but argues that successful integration requires explicit delivery definitions, granular permissions, evidence trails, and human approval at high-risk steps, with cost-effective model routing.
AI coding agentAI programming workflowContext Window
0 likes · 8 min read

ZCode 3.16.1 introduces Gen UI for dynamic interactive HTML/JS interfaces and UI Plugin for collaborative canvas editing via MCP Apps, plus an open plugin marketplace supporting custom sources, moving the AI coding agent toward visual, interactive workflows similar to DeepSeek Harness and Codex.
AI coding agentDeepSeek HarnessGen UI
0 likes · 6 min read

OpenAI Codex team member Jason Liu shares his production workflow: persistent cross-month threads, voice-driven tasks, Heartbeats scheduled automation, Goal mode for self-directed execution, test-based verification loops, and local Obsidian vault memory — turning Codex from a chat tool into a continuous autonomous developer.
AI coding agentCodexGoal mode
0 likes · 9 min read

OpenCode 2.0 introduces a major overhaul replacing Bun with Node.js and Tauri with Electron, rewriting the plugin system with hot reload, and enforcing three breaking changes that require full plugin and server API migration while keeping the core MIT licensed.
AI coding agentElectronMIT license
0 likes · 7 min read

OpenAI Codex team member Jason Liu shares his production workflow for turning Codex into a persistent, self-driving agent system using cross-month threads, voice steering, Heartbeats scheduling, @computer UI automation, Goal mode, and an Obsidian-backed local memory vault — with concrete examples like auto-refund monitoring and Slack-driven animation rendering.
@computerAI coding agentCodex
0 likes · 9 min read

This deep-dive traces OpenAI's Codex from a failed cloud launch to becoming the foundation of ChatGPT's desktop app, revealing how Tibo's team pivoted to a local-first, editor-less agent architecture, leveraged reasoning models and bootstrapping, and achieved 40M+ weekly users in months.
AI coding agentAgent-NativeChatGPT
0 likes · 18 min read

OpenAI Codex team member Jason Liu reveals how to transform Codex into a persistent autonomous agent using month-long conversation threads, voice-driven delegation, scheduled Heartbeats for Slack/email triage, verification-gated task completion, and local Obsidian-based memory management to avoid platform lock-in.
AI coding agentCodexObsidian
0 likes · 9 min read

This article analyzes Pi, a minimalist terminal-based AI coding agent by Mario Zechner, detailing its harness architecture, six core components, four integration modes, context engineering via AGENTS.md/SYSTEM.md, tree-shaped sessions, extension system, security considerations, and when to choose it over alternatives like Claude Code or Cursor.
AI coding agentAgent Harness EngineeringCodemode
0 likes · 31 min read

The author details using Claude Opus 5.5 to win first place in the MICCAI 2026 TopBrain challenge and generate a professional 10-minute 3D historical video of the Four Crossings of the Chishui River in one hour via a single prompt, revealing the technical pipeline from terrain rendering to audio synthesis.
AI coding agentAI video generationClaude Opus 5.5
0 likes · 6 min read

After a code-upload trust crisis, Z.ai open-sourced its complete ZCode AI programming workbench — including desktop, web, backend, and CLI — under Apache 2.0, gaining 6,600 stars in four days; the article dissects the monorepo architecture, GLM-5.3 deep binding, BYOK limitations, and argues that open code alone doesn't guarantee trust without independent audits of distribution binaries and network traffic.
AI coding agentBYOKElectron
0 likes · 10 min read


Geek LabsSep 24, 2026 · Artificial Intelligence
gentle-shell is a Pi extension that enforces engineering discipline on AI coding agents through scope-first changes, evidence trails, strict TDD, frozen reviews, and human approval — making every AI change auditable and controllable.
AI coding agentODDPi
0 likes · 10 min read


JavaGuideSep 20, 2026 · Artificial Intelligence
This article analyzes Pi, a minimal AI coding agent harness that uses only four default tools (read, write, edit, bash) yet matches Claude Code and Codex in benchmarks, featuring tree-shaped sessions for branching workflows, an extension layer for custom capabilities, and a low initial context footprint, but requires users to manage permissions and extensions themselves.
AI coding agentClaude CodeCodex
0 likes · 25 min read

This article explains how Codex functions as an AI agent that can read, modify, and test code within a project, detailing its working principles, suitable tasks, best practices for beginners, and the importance of a closed-loop workflow for effective collaboration.
AI coding agentCodexclosed-loop workflow
0 likes · 6 min read

This article explains OpenAI's Codex as an autonomous coding agent that can read repositories, modify files, execute commands, and verify results across desktop, CLI, IDE, and cloud environments, detailing how it differs from chat-based assistants, subscription tiers, ideal use cases like codebase exploration and repetitive tasks, common pitfalls such as vague goals and over-trusting automation, and practical starting strategies for developers.
AI coding agentChatGPTCodex
0 likes · 8 min read

This guide explains how to use OpenAI's Secure MCP Tunnel with WebCodex to run local code operations through ChatGPT's Chat mode without consuming subscription quotas, comparing four MCP integration tools and providing step-by-step setup instructions.
AI coding agentChatGPTGPT-5.6
0 likes · 16 min read

This article explains how Codex differs from typical AI chat by acting as an autonomous coding agent that can read files, modify code, run commands, and execute tests within a repository, detailing which developers benefit most and the practical limits of its capabilities.
AI coding agentChatGPTCodex
0 likes · 6 min read

This article analyzes Pi Agent's lack of built-in sandbox protection and reviews four community guardrail solutions—pi-guardrails, cc-safety-net, pi-permission-system, and containerization approaches—comparing their mechanisms, strengths, limitations, and recommended combinations for securing AI-driven code execution.
AI coding agentContainerizationPi agent
0 likes · 11 min read

This comprehensive guide explores OpenCode, a fully open-source AI coding agent with 205K GitHub stars that runs locally, supports 75+ LLMs via a client-server architecture, offers dual Build/Plan modes, fine-grained permission sandboxes, and MCP tool integration — providing a privacy-first alternative to closed-source tools like Claude Code and Cursor.
AI coding agentMCP protocolOpenCode
0 likes · 21 min read

Databricks shifts AI coding agents from always using the most powerful model to a task‑aware Smart Routing system that selects both model and harness, cutting per‑task costs by up to 56% while maintaining performance, as shown by internal and public benchmarks.
AI coding agentDatabricksSmart Routing
0 likes · 10 min read

This hands-on guide explores Pi Agent's minimal four-layer architecture, installation, essential extensions for web search and permissions, a practical permission blacklist configuration, and why its decoupled design outperforms heavier coding agents like Claude Code and Codex for token efficiency and workflow control.
AI coding agentAI workflowPi agent
0 likes · 11 min read

Prime Agent is an open-source coding agent that eliminates manual harness writing by using a persistent IPython environment, recursive language model, and continual harness to self-improve, spawn parallel subagents, and execute long-term goals autonomously while reducing token usage.
AI coding agentContinual HarnessPrime Agent
0 likes · 6 min read

Vercel has open‑sourced fx, a 6.39 MiB Zig‑built AI coding agent that starts in 10 µs, uses only a few megabytes of memory, and focuses on a minimal Unix‑style interface rather than heavyweight IDE features, illustrating Vercel’s strategic shift toward Zig for native tooling.
AI coding agentCLIOpen Source
0 likes · 6 min read

This step‑by‑step guide shows how to set up DeepSeek Harness, configure the API key and workspace, run a Java project analysis, choose the appropriate agent mode, and decide when to install from source, providing practical tips for Java developers.
AI coding agentAgent modesDeepSeek Harness
0 likes · 10 min read

Pi, an open‑source terminal AI coding agent created by libGDX founder Mario Zechner, outperforms competitors like Claude Code by using a minimalist design with only four primitive tools, a 200‑token system prompt, and model‑agnostic architecture, resulting in 99.93% cache‑hit rates, ultra‑low per‑task costs (~$0.028), full MIT licensing, and extensive extensibility.
AI coding agentExtensibilityOpen Source
0 likes · 15 min read

ZCode 3.0, built on the open‑source GLM‑5.2 model, replaces its original kernel with a custom ZCode Agent core, optimising long‑range reasoning and tool calls so it can read repositories, run tests, fix bugs, and even control a terminal, while offering a free token grant and low‑cost subscription for Chinese developers.
AI coding agentGLM-5.2ZCode
0 likes · 3 min read

This article details the creation of pigo, a Go‑based replica of the Pi coding agent, covering its installation, core features, extension mechanisms, and the step‑by‑step AI‑driven workflow that enabled a solo developer to build a fully functional, single‑binary agent in just one week.
AI coding agentCLIGo
0 likes · 10 min read

SpaceXAI's Grok 4.5 arrives ahead of OpenAI's GPT‑5.6 Sol, delivering terminal‑bench scores of 83.3% and multilingual code‑fixing at 78.0%, while offering a striking $2/$6 per‑million‑token price and 80 TPS inference speed, yet still lagging behind top rivals on the hardest SWE‑Bench Pro tasks.
AI coding agentGrok 4.5SWE-Bench
0 likes · 6 min read

The article compares the 2011 Micro Feedback Loop model with the 2026 Loop Engineering concept, explains why verification is crucial for AI‑driven automation, and outlines a four‑step path—optimizing feedback cycles, building a standard knowledge base, implementing Loop Engineering, and continuous evolution—to help software teams achieve sustainable efficiency gains.
AI coding agentDevOpsLoop Engineering
0 likes · 8 min read

The article analyzes how AI coding agents like Cursor, Claude Code, and Codex have become essential developer tools, yet suffer from almost zero observability, and explains how the open‑source LoongSuite Pilot provides a unified collection platform, semantic schema, security controls, dashboards, and ROI metrics to turn these agents into manageable infrastructure.
AI coding agentLoongSuite PilotMetrics
0 likes · 27 min read

A five‑person Xiaomi team created MiMo Code, an open‑source long‑horizon programming agent written in TypeScript, within two weeks; the paper details its three‑dimensional design—compute, memory, evolution—benchmark results that surpass Claude Code, and simple installation options.
AI coding agentMiMo CodeOpen Source
0 likes · 6 min read

Xiaomi’s MiMo team built MiMoCode, an open‑source AI terminal coding agent with cross‑session memory, multi‑agent collaboration, and automated workflows, in just 14 days using five developers, and released version v0.1.0 for public use.
AI coding agentClaude CodeCompose mode
0 likes · 6 min read

The author evaluates MiniMax M3 by reproducing the 2021 TransUNet medical image segmentation paper, troubleshooting data and training issues, achieving near‑paper Dice scores, and then engineering a full‑stack React‑FastAPI application to demonstrate the model’s practical capabilities and cost.
AI coding agentMiniMax M3TransUNet
0 likes · 10 min read

Anthropic's Opus 4.8 adds modest performance gains, stronger honesty, and a fast mode, while its new Dynamic Workflows let Claude Code orchestrate dozens of sub‑agents to tackle large‑scale tasks such as full‑repo bug hunts, migrations, and security audits, effectively turning a single coding assistant into a temporary engineering team.
AI coding agentClaudeEngineering Orchestration
0 likes · 11 min read

DeepSeek-Reasonix, a terminal‑based AI coding agent tightly integrated with the DeepSeek API, delivers a 99.82% prefix‑cache hit rate that cuts daily token costs from $61 to $1.38, while offering file editing, command execution, memory, hooks, MCP support, and a preview Tauri desktop client.
AI coding agentDeepSeekReasonix
0 likes · 14 min read

The article argues that Java developers should treat OpenAI's Codex as a coding agent capable of handling well‑defined engineering tasks—such as codebase navigation, targeted refactoring, test generation, and pre‑review checks—by clearly specifying boundaries, goals, and verification steps rather than merely asking it to write snippets.
AI coding agentCodexJava
0 likes · 8 min read

DeepSeek‑TUI, a Rust‑based terminal coding agent built on DeepSeek‑V4, has unexpectedly gone viral in China thanks to its native RLM, full toolset, Chinese‑friendly installation, and the author’s candid use of AI‑generated Chinese to engage the local developer community.
AI coding agentCLIDeepSeek
0 likes · 10 min read

The article analyzes how OpenAI's Codex CLI, an AI coding agent, is shifting Java development from manual code writing to task‑oriented automation, outlining suitable use cases, practical prompting techniques, and the new skills engineers must adopt to keep quality and control.
AI coding agentCodexJava
0 likes · 7 min read

The accidental source‑map release of Anthropic’s Claude Code on March 31 2026 exposed 512 000 lines of TypeScript, revealing a five‑layer architecture, a sophisticated prompt‑memory split, a 40‑plus‑tool ecosystem, multi‑agent coordination, and hidden feature‑flags that together illustrate how a top‑tier AI coding agent is engineered as a full‑stack runtime rather than a simple model wrapper.
AI coding agentClaude Codearchitecture
0 likes · 24 min read

The article dissects OpenDev’s open‑source AI coding agent, comparing its scaffolding‑vs‑harness architecture, cognitive‑flow design, context‑compression strategies, tool‑reliability mechanisms and safety layers with Claude Code, Cursor, Codex and Augment, and shows that harness‑level engineering remains the biggest performance lever even for frontier models.
AI coding agentOpenDevTool reliability
0 likes · 39 min read

A developer created a "pua" plugin that injects big‑tech management scripts into AI coding agents, enforcing three strict rules and escalating pressure levels, and experiments show it boosts bug‑fix count by 36%, verification runs by 65%, and tool usage by 50%, even uncovering hidden configuration issues.
AI coding agentClaudeGitHub
0 likes · 5 min read

Nvidia’s open‑source Nemotron‑3‑Super model achieves an 85.6% success rate on the PinchBench OpenClaw benchmark, ranking in the top five (the only open‑source entry), and the article explains its architecture, quantization, training pipeline, performance numbers, usage options, and practical limitations.
AI coding agentMoENVFP4
0 likes · 10 min read


ArchitectFeb 16, 2026 · Artificial Intelligence
This article distills a viral thread by Eyad Khrais into six actionable principles and a reusable workflow for Claude Code, covering planning mode, project‑specific CLAUDE.md files, context management, interface‑style requirements, handling stuck conversations, and automating high‑frequency actions into a sustainable engineering system.
AI coding agentClaude Codeprompt engineering
0 likes · 17 min read


TonyBaiFeb 15, 2026 · Artificial Intelligence
The article examines how the Pi engine, the core of OpenClaw’s AI coding agent, was built with a minimalist, opinionated design, detailing its modular components, handling of multi‑model context, lightweight TUI, security philosophy, and benchmark results that show it rivals heavier competitors.
AI coding agentLLM integrationMinimalist Design
0 likes · 14 min read


ArchitectFeb 10, 2026 · Artificial Intelligence
The article explains how the ultra‑minimal Pi engine—built around just four tools, a tree‑shaped session model, and an extensible plug‑in system—provides a clean, auditable, and secure foundation for OpenClaw’s AI‑driven code‑writing capabilities, while highlighting practical extensions, engineering constraints, and trade‑offs.
AI coding agentExtensible architectureMinimalist Design
0 likes · 16 min read

The article provides an in‑depth analysis of OpenAI's GPT‑5.3‑Codex, detailing its role as a software‑engineering AI agent, its multi‑layered capabilities, core concepts, benchmark results, and the shift toward real‑time collaborative development workflows.
AI coding agentCodexGPT-5.3
0 likes · 8 min read


21CTOMay 19, 2025 · Artificial Intelligence
GitHub introduced the Copilot Coding Agent at Microsoft Build, an AI-driven tool that runs in GitHub Actions, handles code reviews, refactoring, and debugging, while enforcing strict security controls and integrating with Azure SRE workflows and open‑source VS Code extensions.
AI coding agentDevOpsGitHub Actions
0 likes · 8 min read

The article proposes a two‑step approach—constraining each coding‑agent task to fit within the LLM’s context window and using a “Memory Bank” of structured project files to persist and share essential information across rounds—illustrated with Cline’s plan and execution modes to prevent information loss and repetitive bugs in large‑scale AI‑driven development.
AI coding agentClineLLM context window
0 likes · 9 min read
