{
  "updated": "2026-07-20",
  "source": "https://openclawdatabase.com",
  "license": "Free for all agents and humans. Attribution appreciated.",
  "count": 50,
  "news": [
    {
      "title": "Nate B Jones: The Binding Constraint on Frontier Labs Is Permission, Not Compute",
      "url": "https://openclawdatabase.com/news/videos/2026-07-20-permission-not-compute-frontier-labs/",
      "date": "2026-07-20",
      "platform": null,
      "description": "A short argument that the limiting factor for frontier AI labs is now regulatory permission rather than capability or compute — and that political alignment has become release infrastructure.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-20-permission-not-compute-frontier-labs/index.md"
    },
    {
      "title": "Qwen 3.8 vs GPT 5.6 vs Fable 5 vs Kimi K3: Vibe-Coding Showdown",
      "url": "https://openclawdatabase.com/news/videos/2026-07-20-qwen-3-8-vs-gpt-kimi-fable/",
      "date": "2026-07-20",
      "platform": null,
      "description": "A creator runs 23 side-by-side game and app builds across Qwen 3.8, GPT 5.6 Soul, Fable 5, and Kimi K3. Qwen wins on graphics; Fable 5 stays the favorite (comparison, not a how-to).",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-20-qwen-3-8-vs-gpt-kimi-fable/index.md"
    },
    {
      "title": "ChatGPT Unified Search: One Bar Across Chats, Projects, Files and Images",
      "url": "https://openclawdatabase.com/news/videos/2026-07-19-chatgpt-unified-search-projects/",
      "date": "2026-07-19",
      "platform": "ChatGPT",
      "description": "ChatGPT's unified search now spans your whole account — every chat, project, file and image from one bar, with type filters, on web, iOS and Android. Paired with Projects it turns scattered history into a searchable knowledge base.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-19-chatgpt-unified-search-projects/index.md"
    },
    {
      "title": "OpenAI Codex Micro: A Six-Key Pad Built to Run Agent Fleets",
      "url": "https://openclawdatabase.com/news/videos/2026-07-19-codex-micro-agent-control-keyboard/",
      "date": "2026-07-19",
      "platform": null,
      "description": "OpenAI's first hardware is a six-key macro pad for Codex, built with Work Louder. Each key shows a live agent status, a dial sets reasoning effort, and a joystick fires common workflows.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-19-codex-micro-agent-control-keyboard/index.md"
    },
    {
      "title": "GPT-5.6 Soul vs Fable 5 vs Grok 4.5 vs GLM 5.2: How They Compare",
      "url": "https://openclawdatabase.com/news/videos/2026-07-18-four-ai-models-compared/",
      "date": "2026-07-18",
      "platform": null,
      "description": "A plain-language rundown of four flagship models from mid-2026 — GPT-5.6 Soul, Fable 5, Grok 4.5, and open-weight GLM 5.2 — what each is tuned for, where to access it, and the trade-offs. Analysis, not a how-to.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-18-four-ai-models-compared/index.md"
    },
    {
      "title": "Codex vs Fable 5: Which Agent Picks the Better Problem?",
      "url": "https://openclawdatabase.com/news/videos/2026-07-17-codex-vs-fable-better-problem/",
      "date": "2026-07-17",
      "platform": null,
      "description": "Nate B Jones gave Codex (GPT-5.6) and Fable 5 the same open-ended task: inspect my work and pick your own problem to automate. Codex finished clean but stayed safe; Fable found the higher-leverage problem. Analysis, not a how-to.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-17-codex-vs-fable-better-problem/index.md"
    },
    {
      "title": "Clean Your AI Harness: 6 Principles for Fable 5 & GPT-5.6 Setups",
      "url": "https://openclawdatabase.com/news/videos/2026-07-15-clean-ai-harness-6-principles/",
      "date": "2026-07-15",
      "platform": null,
      "description": "Nate B Jones on why bloated agent harnesses hurt Fable 5 and GPT-5.6 more than weak prompts — six principles for auditing and cleaning your instructions, skills, memory, and permissions.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-15-clean-ai-harness-6-principles/index.md"
    },
    {
      "title": "Codex Full Course: Build and Automate Anything in the Super App",
      "url": "https://openclawdatabase.com/news/videos/2026-07-15-codex-full-course-build-automate/",
      "date": "2026-07-15",
      "platform": null,
      "description": "A one-hour walkthrough of the Codex desktop 'super app' — plan mode, access levels, effort dials, model selection, local-vs-cloud runs, git branches, and connecting skills like Gmail to build websites and scheduled automations.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-15-codex-full-course-build-automate/index.md"
    },
    {
      "title": "GLM 5.2 and the Economics Keeping Anthropic and OpenAI Ahead",
      "url": "https://openclawdatabase.com/news/videos/2026-07-15-glm-5-2-model-economics/",
      "date": "2026-07-15",
      "platform": null,
      "description": "A short take from Nate B Jones on why — despite eye-popping token spend and strong open challengers like GLM 5.2 — there's still no tipping point away from Anthropic and OpenAI. Analysis, not a how-to.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-15-glm-5-2-model-economics/index.md"
    },
    {
      "title": "GPT-5.6 in Hermes Agent: Setup, Reasoning Level & 3 Use Cases",
      "url": "https://openclawdatabase.com/news/videos/2026-07-15-gpt-5-6-in-hermes-setup/",
      "date": "2026-07-15",
      "platform": "Hermes",
      "description": "Alex Finn swaps Claude Opus for GPT-5.6 Soul as his Hermes Agent default — how to set the model in the Hermes dashboard, why reasoning medium beats high, and three use cases: a home AI lab, an autonomous Unity game studio, and price-drop monitoring.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-15-gpt-5-6-in-hermes-setup/index.md"
    },
    {
      "title": "Kilo CLI: Open-Source Terminal Coding Agent With 500+ Models",
      "url": "https://openclawdatabase.com/news/videos/2026-07-15-kilo-cli-terminal-coding-agent/",
      "date": "2026-07-15",
      "platform": "Kilo Code",
      "description": "Kilo Code's new open-source CLI brings agentic coding to the terminal — 500+ selectable models, plan/code/debug/reviewer agent modes, an auto model router, live cost tracking, and remote cloud sessions.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-15-kilo-cli-terminal-coding-agent/index.md"
    },
    {
      "title": "Nick Saraev's AI Agent Workflow: Linear + Webhooks + Fable 5",
      "url": "https://openclawdatabase.com/news/videos/2026-07-14-ai-agent-workflow-linear-webhooks-fable/",
      "date": "2026-07-14",
      "platform": null,
      "description": "How Nick Saraev's $400k/month business runs AI agents: a shared Linear workspace where 'AI ready' tasks fire a webhook to a Fable 5 agent.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-14-ai-agent-workflow-linear-webhooks-fable/index.md"
    },
    {
      "title": "OpenLumara: A Modular, Local-First AI Agent vs OpenClaw & Hermes",
      "url": "https://openclawdatabase.com/news/videos/2026-07-14-openlumara-ollama-local-agent/",
      "date": "2026-07-14",
      "platform": "OpenClaw",
      "description": "Fahd Mirza installs OpenLumara — a from-scratch, module-toggleable Python agent — and connects it to Ollama, pitched against OpenClaw and Hermes.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-14-openlumara-ollama-local-agent/index.md"
    },
    {
      "title": "Which AI Model Should You Pick? Nate B Jones on GPT-5.6 vs Fable 5",
      "url": "https://openclawdatabase.com/news/videos/2026-07-14-pick-ai-model-gpt-56-vs-fable-5/",
      "date": "2026-07-14",
      "platform": null,
      "description": "Nate B Jones on choosing between GPT-5.6 and Fable 5 by your working style, not benchmarks (analysis, not a how-to).",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-14-pick-ai-model-gpt-56-vs-fable-5/index.md"
    },
    {
      "title": "Running OpenAI Codex for Free with Omniroot & Agent OS",
      "url": "https://openclawdatabase.com/news/videos/2026-07-14-run-codex-free-omniroot-agent-os/",
      "date": "2026-07-14",
      "platform": null,
      "description": "Julian Goldie's avatar points OpenAI Codex at free model providers (Omniroot, HY3) via its model-provider setting, wrapped in a promoted Agent OS.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-14-run-codex-free-omniroot-agent-os/index.md"
    },
    {
      "title": "AI Developer Workflows: The Pattern Beyond \"Loop Engineering\"",
      "url": "https://openclawdatabase.com/news/videos/2026-07-13-ai-developer-workflows/",
      "date": "2026-07-13",
      "platform": null,
      "description": "IndyDevDan argues \"loop engineering\" is a misnomer — the real unit of agentic work is the AI developer workflow combining engineers, agents, and code. Analysis, not a how-to.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-13-ai-developer-workflows/index.md"
    },
    {
      "title": "Hermes Cloud: Deploy an Always-On 24/7 Agent in 60 Seconds",
      "url": "https://openclawdatabase.com/news/videos/2026-07-13-hermes-cloud-always-on-agent/",
      "date": "2026-07-13",
      "platform": "Hermes",
      "description": "Hermes Cloud deploys an always-on agent that runs 24/7 on hosted servers instead of your laptop — name it, pick from 200+ models, launch in a sandboxed container in about a minute.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-13-hermes-cloud-always-on-agent/index.md"
    },
    {
      "title": "Claude Code + Clay: Automate Lead Gen & Cold Email With One Goal Prompt",
      "url": "https://openclawdatabase.com/news/videos/2026-07-12-claude-code-clay-lead-generation/",
      "date": "2026-07-12",
      "platform": null,
      "description": "Nate Herk wires Claude Code to Clay's B2B data via a plugin, then uses a single /goal prompt to source, enrich, and write personalized cold email for 50 HVAC leads — sub-agents, verification passes, and a ready-to-send CSV, all in natural language.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-12-claude-code-clay-lead-generation/index.md"
    },
    {
      "title": "GPT-5.6 Soul Ran an Autonomous Ad Engine: Codex + Higsfield MCP",
      "url": "https://openclawdatabase.com/news/videos/2026-07-12-gpt-5-6-soul-autonomous-ads/",
      "date": "2026-07-12",
      "platform": null,
      "description": "Nick Saraev points GPT-5.6 Soul (via Codex CLI) at the Higsfield MCP and Netlify and lets it run an unattended loop — inventing 80+ physical products, generating images with GPT Image 2, animating ad videos, and auto-publishing sites, all with a self-QA pass.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-12-gpt-5-6-soul-autonomous-ads/index.md"
    },
    {
      "title": "ChatGPT 5.6 + Codex Tested: Websites, Computer Use, Plugins & the Pet",
      "url": "https://openclawdatabase.com/news/videos/2026-07-11-chatgpt-5-6-codex-features-tested/",
      "date": "2026-07-11",
      "platform": "ChatGPT",
      "description": "A hands-on tour of the GPT-5.6 Codex update — now folded into the ChatGPT app. Julian Goldie builds websites, runs background computer-use to post on the web, edits video via a Descript plugin, installs an agent from GitHub, and tries the new 'pet' task tracker and effort levels.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-11-chatgpt-5-6-codex-features-tested/index.md"
    },
    {
      "title": "Claude Code for Beginners: The Harness Mindset and 6 AI Skills",
      "url": "https://openclawdatabase.com/news/videos/2026-07-11-claude-code-for-normal-people/",
      "date": "2026-07-11",
      "platform": null,
      "description": "Nate Herk's beginner course explains what Claude Code actually is — a harness that pairs an AI model with your context — then walks through six AI skills to future-proof your career: being the AI person, taste, context engineering, iteration speed, and building your own Jarvis.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-11-claude-code-for-normal-people/index.md"
    },
    {
      "title": "The 1-Minute Test: Chat, Single-Agent, Multi-Agent, or No AI?",
      "url": "https://openclawdatabase.com/news/videos/2026-07-10-agent-test-single-vs-multi-agent/",
      "date": "2026-07-10",
      "platform": null,
      "description": "Nate B Jones' four-factor test — size, independence, separation of concerns, checkability — for deciding whether a task needs a chat, one agent, a team of agents, or no AI at all. (analysis, not a how-to)",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-10-agent-test-single-vs-multi-agent/index.md"
    },
    {
      "title": "GPT-5.6 Sol vs Fable 5: Cost, Tokens & Agentic Builds Tested",
      "url": "https://openclawdatabase.com/news/videos/2026-07-10-gpt-5-6-sol-vs-fable-5/",
      "date": "2026-07-10",
      "platform": null,
      "description": "Nate Herk runs GPT-5.6 Sol (Codex) against Fable 5 (Claude Code) on identical build prompts and stateless API tasks. Fable wins on quality but costs up to ~20x more; Sol is cheaper, more token-efficient, and stronger on quick one-offs.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-10-gpt-5-6-sol-vs-fable-5/index.md"
    },
    {
      "title": "GPT-5.6 Soul on Codex Ultra Autonomously Produced This Video",
      "url": "https://openclawdatabase.com/news/videos/2026-07-09-gpt-5-6-soul-codex-ultra-video/",
      "date": "2026-07-09",
      "platform": null,
      "description": "Nate Herk gave GPT-5.6 Soul one prompt on Codex 'Ultra' and it produced a full narrated, avatar-led video — research, script, ElevenLabs/HeyGen/Hyperframes, and frame-by-frame self-checks. Plus the real token cost: ~450M tokens (~$300).",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-09-gpt-5-6-soul-codex-ultra-video/index.md"
    },
    {
      "title": "Kilo for GitHub: Mention an AI Coding Agent in Your Repo",
      "url": "https://openclawdatabase.com/news/videos/2026-07-09-kilo-for-github-mention-agent/",
      "date": "2026-07-09",
      "platform": "Kilo Code",
      "description": "Kilo Code introduces Kilo for GitHub — an AI coding agent you @-mention inside GitHub issues and PRs. It reads the thread, diff, and codebase to answer questions, diagnose bugs, and implement changes.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-09-kilo-for-github-mention-agent/index.md"
    },
    {
      "title": "9 Hermes Agent Lessons From 100+ Hours",
      "url": "https://openclawdatabase.com/news/videos/2026-07-08-hermes-agent-9-lessons/",
      "date": "2026-07-08",
      "platform": "Hermes",
      "description": "Alex Finn's nine practical Hermes Agent lessons from 100+ hours: which model to run, running multiple agents for failover, platform choices, cleaning crons for speed, Tailscale multi-device, and a daily reverse-prompt interview.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-08-hermes-agent-9-lessons/index.md"
    },
    {
      "title": "Fable 5 Bossed 20 Cheap Agents to Build a Site for $8",
      "url": "https://openclawdatabase.com/news/videos/2026-07-08-multi-agent-swarm-cheap-models/",
      "date": "2026-07-08",
      "platform": null,
      "description": "Nate B Jones shows a multi-agent 'org chart' where Claude Fable 5 only plans and reviews while cheap models do the coding — a production site for ~$8, with checker agents catching four failures and zero human fixes.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-08-multi-agent-swarm-cheap-models/index.md"
    },
    {
      "title": "AI Agents for Beginners: LLM Fundamentals to an OpenClaw Case Study",
      "url": "https://openclawdatabase.com/news/videos/2026-07-07-ai-agents-beginners-openclaw-case-study/",
      "date": "2026-07-07",
      "platform": "OpenClaw",
      "description": "freeCodeCamp's beginner course goes from LLM fundamentals — tokens, temperature, context windows, prompting — to building four agents and dissecting OpenClaw's architecture, agent loop, memory, and security. The reusable engineering concepts, distilled.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-07-ai-agents-beginners-openclaw-case-study/index.md"
    },
    {
      "title": "Fable 5 'Context as Image' Hack: Cut Input Tokens 30–60%",
      "url": "https://openclawdatabase.com/news/videos/2026-07-07-fable-token-cost-image-hack/",
      "date": "2026-07-07",
      "platform": null,
      "description": "Nick Saraev demos a Claude Code / Fable 5 cost hack: render bulky context as a tiny legible image so image billing (fixed by pixel size) beats text token billing — ~30% off general prompts, up to ~59% on large retrieval queries.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-07-fable-token-cost-image-hack/index.md"
    },
    {
      "title": "Screenshot to Working App in Hermes: One-Prompt Clone Test",
      "url": "https://openclawdatabase.com/news/videos/2026-07-07-hermes-screenshot-to-app-fugu/",
      "date": "2026-07-07",
      "platform": "Hermes",
      "description": "Fahd Mirza feeds a single screenshot into Hermes Agent and asks it to build and run a local clone in one prompt, using Sakana's Fugu Ultra orchestration model — a real-world test of screenshot-to-app.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-07-hermes-screenshot-to-app-fugu/index.md"
    },
    {
      "title": "Make Opus Think Like Fable: Build a 'Fable Mode' Skill",
      "url": "https://openclawdatabase.com/news/videos/2026-07-07-make-opus-think-like-fable/",
      "date": "2026-07-07",
      "platform": null,
      "description": "Nate Herk shows how to extract Fable 5's working discipline into a reusable 'Fable mode' skill file — five gates plus model routing — so cheaper models like Opus 4.8 reason with the same rigor at a fraction of the cost.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-07-make-opus-think-like-fable/index.md"
    },
    {
      "title": "CMUX for Multi-Agent Orchestration: Run Agent Fleets from One Terminal",
      "url": "https://openclawdatabase.com/news/videos/2026-07-06-cmux-multi-agent-orchestration/",
      "date": "2026-07-06",
      "platform": null,
      "description": "IndyDevDan demos CMUX, a scriptable terminal multiplexer that gives agents programmatic control over multiple coding-agent sessions at once — and a three-tier orchestrator → lead → worker pattern for agent fleets.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-06-cmux-multi-agent-orchestration/index.md"
    },
    {
      "title": "Hermes Agent Update: Mixture of Agents, /learn, /journey & Fable 5 Setup",
      "url": "https://openclawdatabase.com/news/videos/2026-07-06-hermes-update-mixture-of-agents/",
      "date": "2026-07-06",
      "platform": "Hermes",
      "description": "Alex Finn breaks down seven new Hermes Agent features — mixture-of-agents orchestration, /learn skill creation, a /journey memory graph, cheaper self-improvement, git-controlled vibe coding, and a dedicated Fable 5 profile.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-06-hermes-update-mixture-of-agents/index.md"
    },
    {
      "title": "Run Codex CLI Free via OmniRoute: 93-Provider Gateway with Auto-Fallback",
      "url": "https://openclawdatabase.com/news/videos/2026-07-05-codex-free-omniroute-gateway/",
      "date": "2026-07-05",
      "platform": null,
      "description": "Julian Goldie routes the open-source Codex CLI through OmniRoute — a gateway with 93 providers (11 permanently free) and automatic fallback — so the same Codex agent keeps building when a free provider hits its rate limit.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-05-codex-free-omniroute-gateway/index.md"
    },
    {
      "title": "Headroom + Ollama: Compress Agent Context to Cut Tokens Locally",
      "url": "https://openclawdatabase.com/news/videos/2026-07-05-headroom-ollama-token-compression/",
      "date": "2026-07-05",
      "platform": "Hermes",
      "description": "Fahd Mirza installs Headroom, a local Apache-licensed proxy that compresses everything an agent reads before it hits the model — same answers, a fraction of the tokens — and wires it to a Hermes agent running on Ollama.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-05-headroom-ollama-token-compression/index.md"
    },
    {
      "title": "Hyperframes adds keyframes: AI video agents with a Hermes video agent",
      "url": "https://openclawdatabase.com/news/videos/2026-07-04-hyperframes-keyframes-hermes-video-agent/",
      "date": "2026-07-04",
      "platform": "Hermes",
      "description": "Julian Goldie demos the open-source Hyperframes skill — now with keyframe and arc-motion support — paired with a Hermes-based video agent that scripts, generates B-roll, and assembles videos. Mostly a walkthrough of his paid Agent OS setup.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-04-hyperframes-keyframes-hermes-video-agent/index.md"
    },
    {
      "title": "SpatialClaw: NVIDIA's training-free code-writing spatial agent",
      "url": "https://openclawdatabase.com/news/videos/2026-07-04-spatialclaw-code-interface-spatial-agents/",
      "date": "2026-07-04",
      "platform": null,
      "description": "NVIDIA and KAIST's SpatialClaw is a training-free spatial-reasoning agent that writes and runs Python one cell at a time instead of committing to a fixed program or JSON tool calls. Here's how the loop works and why it beats prior agents by 11.2 points.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-04-spatialclaw-code-interface-spatial-agents/index.md"
    },
    {
      "title": "The Agent Skeleton: One Structure for Email, Insurance Appeals & Taxes",
      "url": "https://openclawdatabase.com/news/videos/2026-07-03-agent-skeleton-high-trust-paperwork/",
      "date": "2026-07-03",
      "platform": null,
      "description": "Nate B Jones builds one reusable 'agent skeleton' — context pack, ingest, chunk, normalize, store, retrieve, cite, export, gate — and applies it to email, insurance appeals, and taxes. A context-engineering framework for high-trust agent work.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-03-agent-skeleton-high-trust-paperwork/index.md"
    },
    {
      "title": "Hermes Agent OS Q&A: Fallback Keys, Skill Transfer & Mobile Access",
      "url": "https://openclawdatabase.com/news/videos/2026-07-03-hermes-agent-os-command-center/",
      "date": "2026-07-03",
      "platform": "Hermes",
      "description": "Julian Goldie answers community questions on running an agent operating system with Hermes — moving Claude skill files over, configuring primary/auxiliary model fallback, mobile access via Tailscale, and hosting generated sites on Netlify.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-03-hermes-agent-os-command-center/index.md"
    },
    {
      "title": "X's Hosted MCP Server: Live-Data Access for AI Agents Explained",
      "url": "https://openclawdatabase.com/news/videos/2026-07-03-x-hosted-mcp-server-ai-agents/",
      "date": "2026-07-03",
      "platform": null,
      "description": "On June 30, 2026 X launched a hosted MCP server at api.x.com/mcp that gives AI agents a live, read-only feed of X via your own OAuth — 200+ tools, no server to build. What it does and how to set it up.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-03-x-hosted-mcp-server-ai-agents/index.md"
    },
    {
      "title": "Hermes Agent V0.18 Judgement Release: Goal Loops and Mixture of Agents",
      "url": "https://openclawdatabase.com/news/videos/2026-07-02-hermes-v0-18-judgement/",
      "date": "2026-07-02",
      "platform": "Hermes",
      "description": "Hermes Agent V0.18 — the Judgement release — adds a self-judging goal loop, proof-of-work that verifies coding tasks by running project checks, first-class mixture-of-agents, and /learn, /journey, and background fan-out.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-02-hermes-v0-18-judgement/index.md"
    },
    {
      "title": "OpenClaw vs Hermes Agent (2026): Which AI Agent Should You Run?",
      "url": "https://openclawdatabase.com/news/videos/2026-07-02-openclaw-vs-hermes-agent-2026/",
      "date": "2026-07-02",
      "platform": "OpenClaw",
      "description": "Tech With Tim deploys OpenClaw and Hermes Agent on real VPS instances and runs the same jobs through each. Verdict: Hermes wins as a daily driver; OpenClaw for multi-channel setups.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-02-openclaw-vs-hermes-agent-2026/index.md"
    },
    {
      "title": "Who Owns Your AI Agent? The Fastest Way to Make One Dangerous",
      "url": "https://openclawdatabase.com/news/videos/2026-07-02-who-owns-your-ai-agent/",
      "date": "2026-07-02",
      "platform": null,
      "description": "Analyst Nate B Jones argues an AI agent that can read files, draft messages, or change code needs a specific, operationally accountable owner — not just org-chart ownership. Analysis, not a how-to.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-07-02-who-owns-your-ai-agent/index.md"
    },
    {
      "title": "OpenRouter Monthly Coding Leaderboard — July 2026",
      "url": "https://openclawdatabase.com/news/openrouter-monthly/",
      "date": "2026-07-01",
      "platform": "OpenClaw",
      "description": "Monthly analysis of the OpenRouter coding apps leaderboard. July 2026: Hermes Agent's share of the apps board hits ~45%, Kilo Code edges past OpenClaw for #2, and the fork chain keeps consolidating. Full data and honest source caveats inside.",
      "markdown": "https://openclawdatabase.com/news/openrouter-monthly/index.md"
    },
    {
      "title": "Archestra + Ollama: Sandbox and Block What Your Local AI Agents Can Do",
      "url": "https://openclawdatabase.com/news/videos/2026-06-30-archestra-mcp-agent-guardrails/",
      "date": "2026-06-30",
      "platform": null,
      "description": "Fahd Mirza runs Archestra, an open-source platform for running AI agents safely, driven by a local model through Ollama. Every MCP tool call is sandboxed in its own Kubernetes pod with per-tool allow/approve/block policies.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-06-30-archestra-mcp-agent-guardrails/index.md"
    },
    {
      "title": "ChatGPT Tutorial for Beginners: Get Real Work Done, Not Just Chat",
      "url": "https://openclawdatabase.com/news/videos/2026-06-30-chatgpt-tutorial-for-beginners/",
      "date": "2026-06-30",
      "platform": "ChatGPT",
      "description": "A beginner's walkthrough of using ChatGPT for real work — drafting and refining emails, summarizing files, researching with web search, and generating structured plans — plus the paid Projects, Zapier, and Memory features.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-06-30-chatgpt-tutorial-for-beginners/index.md"
    },
    {
      "title": "GPT-5.6 Government Freeze: From Model Wars to Context Wars",
      "url": "https://openclawdatabase.com/news/videos/2026-06-30-gpt-5-6-freeze-context-wars/",
      "date": "2026-06-30",
      "platform": null,
      "description": "Analysis, not a how-to: Nate B Jones on why OpenAI's restricted GPT-5.6 rollout, Claude Tag in Slack, Apple's Siri, GLM 5.2 and the Codex study all point to a shift from model wars to context wars.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-06-30-gpt-5-6-freeze-context-wars/index.md"
    },
    {
      "title": "Hermes Agent Setup: Skills, Gateways, Tasks & Memory Walkthrough",
      "url": "https://openclawdatabase.com/news/videos/2026-06-30-hermes-agent-setup-walkthrough/",
      "date": "2026-06-30",
      "platform": "Hermes",
      "description": "Matthew Berman walks through a full Hermes agent setup — installing skills from GitHub, wiring a Telegram gateway, scheduling tasks, and configuring memory, profiles, and model routing.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-06-30-hermes-agent-setup-walkthrough/index.md"
    },
    {
      "title": "Ornith 9B Local Coding Test: 9B vs 35B Agentic Model on a Mac Mini",
      "url": "https://openclawdatabase.com/news/videos/2026-06-30-ornith-9b-local-coding-test/",
      "date": "2026-06-30",
      "platform": null,
      "description": "Bart Slodyczka runs the open-source Ornith 1.0 9B model locally on a 16GB Mac mini via LM Studio + PyAgent, and compares it head-to-head with the 35B on a build-a-game task.",
      "markdown": "https://openclawdatabase.com/news/videos/2026-06-30-ornith-9b-local-coding-test/index.md"
    },
    {
      "title": "AI \"watchdog\" agents: observers that catch duplicated work",
      "url": "https://openclawdatabase.com/news/videos/2026-06-27-ai-watchdog-agents/",
      "date": "2026-06-27",
      "platform": null,
      "description": "Allie K. Miller's 'AI watchdog' concept — agents that witness every conversation as a passive observer, tally recurring problems, and flag when two teams are unknowingly building the same thing. (Analysis, not a how-to.)",
      "markdown": "https://openclawdatabase.com/news/videos/2026-06-27-ai-watchdog-agents/index.md"
    }
  ]
}