Ollama q2_0 GGUF Import: Fit 2-Bit MoE Models, Do the Memory Math, Verify Quality
Ollama 0.40.6 reads q2_0 GGUFs. This ollama q2_0 gguf import runbook covers memory math, the Modelfile import, a q4 check, rollback and runner cleanup.
Read the storyTHE INTEL LIBRARY
Follow your curiosity.
Claude Code Fork Subagents: A Headless Migration Runbook
Claude Code fork subagents now reach headless and SDK lanes by default. Test inherited context, nested waits, permissions and failure evidence before promotion.
Read the story
OpenCode Reasoning Variants: Validate Overrides After 1.19.3
Validate OpenCode reasoning variants after 1.19.3 with a lane inventory, configuration precedence checks, agent override tests and a clear rollback record.
Read the story
Qwen Code Background Tasks: Require a Completion Receipt
Qwen Code background tasks need exit evidence, verified artifacts and resolved approvals. Apply a completion contract and five canaries before unattended runs.
Read the story
llama.cpp Default Port Change: A v0.7.0 Upgrade Runbook
The llama.cpp default port change moves bare servers to 9931. Audit clients, preserve Docker mappings, test MoE cache budgets and coordinate RPC builds safely.
Read the story
Claude Agent SDK Hook Rewrites: Prove the Input That Executes
Claude Agent SDK hook rewrites now undergo input validation. Use migration fixtures to verify executable arguments, preserve approvals and record outcomes.
Read the story
Claude Code Notification Setup (and Codex): Get a Sound, Desktop Alert or Phone Push When the Agent Finishes or Needs You
Claude Code notification and Codex alert setup: terminal defaults, Notification and Stop hooks, notify and [tui] keys, a phone push, a test drill and rollback.
Read the story
Claude Desktop MCP Setup: Find claude_desktop_config.json, Add Local Servers or .mcpb Extensions, and Fix Servers That Won't Connect
Claude Desktop MCP setup: find claude_desktop_config.json, add a local server or .mcpb bundle, add remote connectors, and fix servers using the mcp*.log files.
Read the story
Claude Code Sandbox Setup: Turn On /sandbox, Write the settings.json Block, and Fix Commands That Fail Only in the Sandbox
Set up the Claude Code sandbox: run /sandbox, write a reviewed settings.json block, prove each boundary with probes, and fix commands that only fail inside it.
Read the story
Claude Code Subagents: Write .claude/agents Files, Restrict Their Tools, Pick the Model and Prove It Works
Create Claude Code subagents as .claude/agents files: three definitions, tool allowlists, model precedence, delegation tests, troubleshooting and rollback.
Read the story
llama-server Flags for Coding Agents: Context Size, GPU Layers, KV Cache, Slots and --jinja, Then Prove What Loaded
Set llama-server flags for a coding agent on purpose: context, GPU layers, KV cache, slots and --jinja, then prove them with /props, /slots and a tool call.
Read the story
Claude Code Cron Job Setup: Choose /loop, Desktop, Cloud Tasks or claude -p, Then Add a Cost Gate
Set up a Claude Code cron job the right way: choose /loop, Desktop, cloud tasks or claude -p, then add a cheap pre-screen, spend cap, logs and a stop path.
Read the story
GitHub Copilot CLI Sandbox Proxy: Route Host-Rule Traffic Through HTTPS_PROXY After 1.0.100
GitHub Copilot CLI sandbox proxy runbook: route host-rule traffic through HTTPS_PROXY after 1.0.100, verify proxy logs, and keep NO_PROXY hosts direct.
Read the story
OpenAI Codex: Startup and Configuration Diagnosis After 0.162.1
OpenAI Codex after 0.162.1: diagnose background-server startup, configuration layers, MCP failures and output contracts with a practical fleet diagnostic guide.
Read the story
OSC 7501: The Agent Status Protocol Your Fleet Dashboard Should Consume
Claude Code 2.1.295 now speaks the OSC 7501 agent status protocol. Stop scraping spinner titles: consume the states, and fail closed when a guard hook breaks.
Read the story
AI Agent Screenshot Leak: Audit Where Your Agents Publish Images After PixelLeak
PixelLeak found 13,000+ agent-posted images in public GitHub repos. Map where your agents publish screenshots, run a 30-minute audit, close the public paths.
Read the story
Consistent AI Character Video Needs Approval Gates: The Viral Playbook, Rebuilt as an Agent Pipeline
A viral AI persona reached tens of millions of views with no label. Run character sheet, clip and schedule as gated stages with dated labels and a kill switch.
Read the story
WebKit Says Agents Are Assistive Tech: The WebMCP vs ARIA Fight and Which Bet to Make
WebKit opposes WebMCP, Mozilla is neutral, one client ships. Use this surface-bet table to choose ARIA, WebMCP or both for each job your site lets agents do.
Read the storyPUT THE IDEAS TO WORKMany assistants.
Meet Automater Many assistants.
One place to remember.
Bring your AI sessions, context, and usage together with Automater.
Get started
Be the boss of all your AIs.
Lite is free forever, installs in about a minute, and reads the session history you already have.
Download Lite
Also for macOS (Apple silicon) and Linux.
Signed installer. No account. Session content stays on your disk.
