Skip to main content
株式会社オブライト

Column

Useful articles about SEO, Web Development, and IT

773 articles

AI2026-06-05
The Complete Guide to Hermes Agent & Hermes Desktop Skills and Tools — 19,932 Skill Catalog, 40+ Built-in Tools, and the Use-Case Patterns That Matter (June 2026)
A comprehensive guide to the Skills & Tools system in Nous Research's open-source agent Hermes Agent v0.15.2 (and the Hermes Desktop GUI), grounded in official docs and GitHub releases. Covers Skills (on-demand procedural docs) with the three-level Progressive Disclosure loading scheme starting at ~3k tokens, the SKILL.md format, the skills.sh catalog that exploded from 858 to 19,932 entries in v0.15.1, the standout new skills (openhands, code-wiki, web-pentest), the self-improving loop where the agent creates / patches / edits / deletes its own Skills, and Tools — 40+ built-ins like web_search, x_search, terminal, patch, browser_navigate, vision_analyze, cronjob, memory, delegate_task. Also covers MCP client + server support, the macOS Computer Use background execution that doesn't move the cursor or switch Spaces (5–20ms/event), and the 25+ messenger gateway (Slack / Discord / Telegram / Teams / WhatsApp / LINE / Feishu / WeCom and more). Ends with eight category-specific combination patterns — research, writing, data analysis, coding, customer support, social listening, internal automation, personal work — sized for Japanese enterprise practice.
Hermes AgentHermes DesktopNous Research+5
AI2026-06-04
Gemma 4 12B Deep Dive — The Encoder-Free Multimodal LLM That Runs on a 16GB Laptop Under Apache 2.0 (June 3, 2026)
A deep dive into Gemma 4 12B, released by Google DeepMind on June 3, 2026, grounded in the official announcement and Developer Guide. The standout property is encoder-free multimodal architecture — replacing the prior vision encoder (~550M parameters) with a 35M-parameter lightweight embedder plus a single matrix multiplication, and removing the 12-layer Conformer audio encoder entirely by projecting raw audio straight into the LLM's embedding space. Runs on a 16GB VRAM laptop (Copilot+ PC or Apple Silicon Mac), shipped under Apache 2.0, available through Hugging Face / Ollama / LM Studio / MLX / Vertex AI on day one. Covers the architectural rationale, the "approaches 26B MoE at less than half the memory" benchmark claim, positioning within the Gemma 4 family (E2B / E4B / 26B / 31B), competitive comparison against Llama 4 / Qwen 3.5 / Phi-5, and the fit with Japanese enterprise on-prem AI, voice workflows, and data-sovereignty requirements.
Gemma 4Gemma 4 12BGoogle DeepMind+5
AI2026-06-03
Hermes Desktop Deep Dive — Nous Research's OSS Resident Personal Agent for Every Platform
Hermes Desktop by Nous Research is the native desktop app version of Hermes Agent, first demoed by Jensen Huang at the NVIDIA GTC keynote and now in public preview. Released under the MIT license, it supports macOS, Windows, and Linux with voice mode, cron scheduling, Computer Use, and MCP gateway integration — all sharing the same config, skills, and memory as the CLI and TUI. This column covers features, competitive positioning, and key considerations for Japanese enterprise adoption.
Hermes DesktopNous ResearchAI Agent+4
AI2026-06-03
Microsoft × OpenClaw Partnership & Microsoft Scout — Build 2026's Paradigm Shift Explained
At Microsoft Build 2026 Day 1 Keynote on June 2, 2026, the open-source AI agent 'OpenClaw' was officially announced as a Windows-native integration, MXC sandbox-ready runtime, and the foundation for enterprise product Microsoft Scout. This column covers the full paradigm shift — from Agent 365 governance to pricing, competitive comparison, and implications for Japanese enterprises. Note: The OpenClaw discussed here is the OSS by Peter Steinberger and is unrelated to Obright's 'OpenClaw Setup Service'.
OpenClawMicrosoftMicrosoft Scout+5
AI2026-06-03
OpenAI Codex Sites Explained — The AI Dev Environment That Deploys a URL for You
On June 2, 2026, OpenAI added a 'Sites' feature to Codex. Users can generate web apps, dashboards, and games inside Codex and instantly share an OpenAI-hosted URL within their workspace. The supported runtime is limited to Cloudflare Worker-compatible ES Modules, and the feature is currently available as a preview for Business and Enterprise plans only. There is no staging environment, and no official statement on public (anonymous) access. While ideal for internal PoC and departmental dashboards, it is too early to adopt as a foundation for customer-facing production services. The unusual structure of Vercel, Replit, and Lovable being both competitors and partners is drawing attention.
OpenAICodexCodex Sites+4
AI2026-05-30
OpenAI Codex Computer Use Comes to Windows — Reading "Windows users, this one's for you." from the Primary Sources and What It Means for Japanese Enterprises (May 2026)
On May 29, 2026, OpenAI's Codex desktop app v26.527 brought Computer Use (Codex driving any app by seeing, clicking, and typing on the screen) to Windows for the first time — previously macOS-only. This column reads the official Changelog and Codex Computer Use docs as primary sources to cover the Windows-specific foreground-only execution constraint (unlike macOS's parallel background mode), the OS-level PowerShell sandbox, install via Microsoft Store and winget, the regional rollout excluding the EEA / UK / Switzerland at launch (Japan is included), pricing, comparisons with Anthropic Claude Computer Use, Claude Code, Cursor, and UiPath, and what this means for Japanese enterprises where Windows 11 dominates office endpoints.
OpenAICodexComputer Use+4
AI2026-05-30
Windsurf × Devin (Cognition AI) Integration Deep Dive — The 72 Hours That Reshaped the AI IDE Market and the Windsurf 2.0 Vertical Stack (May 2026)
The Windsurf (Codeium-origin AI IDE) and Devin (Cognition AI's autonomous engineer) story — grounded in the official docs.windsurf.com/windsurf/devin page and Cognition's announcement. Covers the July 2025 "72 hours" that reshuffled the market (OpenAI's $3B deal lapsed → Google's $2.4B reverse-acquihire of the CEO, co-founder, and ~40 R&D staff → Cognition's acquisition of the remaining assets the next Monday), the April 15, 2026 release of Windsurf 2.0 with native Devin integration, automatic inclusion across Pro / Max / Teams plans, the $50 GitHub-connection credit, the Agent Command Center bringing local Cascade and cloud Devin into a single Kanban view, head-to-head comparison with Cursor, Claude Code, Antigravity, and Codex Computer Use, and adoption guidance for Japanese enterprises.
WindsurfDevinCognition AI+4
AI2026-05-25
Gemma 4 System Requirements — 5–62GB VRAM, RTX 3060 to H100 by Variant (E2B/E4B/26B/31B) [2026 Guide]
Gemma 4 needs 5GB VRAM (E2B/E4B), 16GB (26B MoE), or 24-62GB (31B Dense) depending on quantization. Requirements by model: RTX 3060 to H100, Apple Silicon M1-M4, CPU-only operation, RAM sizing, and budget builds. Updated July 2026.
Gemma 4ハードウェアGPU+4
AI2026-05-25
Gemma 4 Performance Benchmark — Compared Against Llama 4, Qwen, Mistral, and DeepSeek on Quality, Speed, and Cost-Efficiency [2026 Open-Weights LLM Showdown]
A 2026 Q2 performance benchmark of Gemma 4 (E2B / E4B / 26B MoE / 31B Dense) against the major open-weights peers — Llama 4, Qwen 3.5, Mistral, and DeepSeek — across MMLU-Pro, GPQA, HumanEval, MATH-500, and MT-Bench. Adds throughput (tokens / s), memory efficiency (quality per GB VRAM), cost per million tokens, Japanese-language performance, native function calling, and Apache 2.0 / MIT / commercial-use licensing as of May 2026, plus a use-case selection matrix for in-house LLM, edge AI, coding assistants, and RAG.
Gemma 4Llama 4Qwen+5
AI2026-05-22
Argent (Software Mansion) Meets Gemma 4 — Reading the On-Device AI Agent + iOS Simulator Trend from the Primary Sources
A primary-source read on the trend of on-device AI agents driving iOS simulators, anchored on Argent — Software Mansion's MCP-based iOS / Android simulator toolkit released May 8, 2026 — paired with Google's Gemma 4 E4B edge multimodal model. Covers Argent's actual spec (screenshot-first feedback + accessibility + profiling, MCP server implementation), Gemma 4 E4B's requirements (~2.5 GB model memory, 8 GB+ RAM, native function calling), the fact that Software Mansion's officially published Argent demo actually uses Gemini 3.5 Flash (cloud), the separate on-device Gemma 4 E2B demo on an iPhone 17 Pro, and what this actually means for Japanese mobile QA and internal-app automation.
ArgentSoftware MansionGemma 4+5
AI2026-05-21
Google Antigravity 2.0 Deep Dive — From IDE to Agent Platform, Gemini CLI Sunset, the $200 Ultra Tier, and the Developer Backlash (Google I/O 2026)
A grounded read of Google Antigravity 2.0 — announced at Google I/O 2026 — from the official sources. Antigravity has shifted from being a VS Code fork to a four-surface platform (desktop app + Antigravity CLI + SDK + Managed Agents) centered on agent orchestration. Covers the June 18, 2026 Gemini CLI / Code Assist IDE shutdown, Gemini 3.5 Flash as the new default, the $200 AI Ultra tier price cut, Gemini Enterprise Agent Platform integration, and the developer backlash over the disappearing IDE experience.
GoogleAntigravityGemini+4
AI2026-05-21
Gemini 3.5 Flash and Gemini Omni — How Google I/O 2026's New Model Strategy Beats Pro-Class with Flash and Unifies Veo, Imagen, and Lyria
A comprehensive guide to Gemini 3.5 Flash and Gemini Omni announced at Google I/O 2026 (May 19 PT). Covers benchmarks that surpass Gemini 3.1 Pro, 4x output speed, over-1M-token context, the strategic significance of unifying Veo, Imagen, and Lyria into a single model, pricing, and adoption guidance for Japanese enterprises.
GoogleGeminiGemini 3.5 Flash+3
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465