The Intelcraft Log
A field guide to what we’re learning.
Original essays, working notes, formal publications, and a human-validated knowledge base. Each format serves a different stage of turning information into practice.
01 / Perspective
Writing
Longform arguments and practical essays from anant.us — developed ideas with a clear point of view.
How to Audit Your Professional AI: A Practical Framework for Businesses
Artificial intelligence is moving into customer support, software development, analytics, marketing, finance, human resources, and internal operations. Many organizations now use AI through everyday software as well as dedicated assistants,
Read essayHow to Audit Your Personal AI: A Practical Guide to Safe and Responsible AI Use
Artificial intelligence has become part of everyday life. People use AI assistants to draft emails, summarize documents, learn new topics, plan projects, write code, and make sense of complex information. […]
Read essay
7 AI Contract Terms That Protect the Record
What police reports can teach every organization handling sensitive data Contracts exist to allocate risk, and AI makes that risk harder to predict. Generative drafting and autonomous agents raise questions […]
Read essay
It’s Bananas: The Third Circuit in ROSS Views Headnotes as ‘Creative Spark’
What the Third Circuit’s ROSS AI copyright opinion reveals about the creative spark AI copyright is reaching the federal courts of appeals, and the lines are becoming more specific. In […]
Read essay
The Wild West of AI Ownership Is Still Taking Shape
What the latest copyright decisions mean for the human work inside AI A company can buy an AI service in an afternoon. Explaining the rights behind its training material, retrieved […]
Read essay02 / In progress
Notes
Fast observations, session records, and ideas still being worked through — useful before they become polished.

#57.1 - User-Owned Memory and Knowledge Bases: Market Scan
#57 - Design a Company Brain / History, Memory & Knowledge / The Modern Enterprise Canvas
#56 - Build The Eval Bench: Prompts, Runs & Screens
#56 - Grading AI with Evals / Multi-Bot Rubrics / LLM as Judge
studyhall 1.2 - Notion as an AI Knowledge Harness / Skills Collector / Notion AI Workers
#55 - AI & Law & Order : Copyright in the Age of AI
#54 - Agent Platforms / Hermes, Devin, Grok, Codex / Harness Strategy
#53 - Evaluating AI Skills / Trust Rubrics / Intelligence Crafting
03 / Reference
Publications
Structured, shareable work from the Intelcraft playbook — the most complete expression of a subject.
Published research
intelcraft.3 - Enterprise AI Governance Guide
Published research
intelcraft.2 - Enterprise & Federal Cybersecurity Policy
Published research
intelcraft.1 - Global & National Energy & Water Use
04 / Discovery
Curated Knowledge Base
We use AI to find and prioritize knowledge, then people validate what is worthy. Tagged and organized in Linkwarden with Konotree.com.
Built with Konotree.com
runta-dev/errand: An open-source take on Grok Bot/Muse. Persistent AI teammates with their own cloud computers, powered by Runta.
Open sourcetinyhumansai/openhuman
Open sourceAX — Put your agents on speaking terms
Open sourceenclawed/omcp — OpenMCP fork
Open sourcelemma-work/lemma-platform
Open sourcebolt.gives
Open sourceIntroducing engrams (Cortex)
Open sourceobot-platform/obot ADRs
Open sourceencoredev/encore
Open sourcepamelafox/github-copilot-mcp-skills-workshop
Open sourceSkillsMP — Agent Skills Marketplace
Open sourceSkills.sh — The Agent Skills Directory
Open sourcetigerless-labs/autoharness
Open sourceBloopAI/vibe-kanban
Open sourceupsonic/upsonic
Open sourceKalyanKS-NLP/llm-engineer-toolkit
Open sourceThytu/Agentarium
Open sourcelangroid/langroid
Open sourceAgentOps-AI/agentops
Open sourceAWS Prescriptive Guidance: Foundations of agentic AI on AWS
Open sourceAI Evals: A Hands-On Guide for Product Teams
Open sourceRuli AI - In House Legal AI
Open sourceScoop: Unvetted AI agents are accessing U.S. bank accounts
Open sourceMonid Rankings: the most popular tools, voted by agents
Open sourcefabio-rovai/open-ontologies: Plan, apply and roll back changes to a production ontology, with a blast radius report and a proof an auditor can re-check.
Open sourceOpenship - Open Source, Self-Hostable Deployment Platform
Open sourceYesPress: Coder as governed AI agent workspace layer
Open sourceDruce.ai: Obot MCP gateway write-up
Open sourceBuild This Now: AI SaaS stack still pairs Supabase
Steady Supabase (Postgres/pgvector/auth) + PostHog-adjacent stack guidance.
Open sourceOpen WebUI (desktop / Responses API changelog)
Open sourceZeniteq: Ollama ↔ Codex Desktop integration
Open sourceNimbalyst: OpenCode vs Codex 2026
Visual Editor for Claude Code & Codex (Open Source). Open/model-agnostic vs proprietary ChatGPT integration framing.
Open sourceGeekyGoo: Copilot vs Cursor vs Claude Code practitioner split
Open sourceCodewalkers: OpenCode as leading MIT/BYOK Claude Code alt
Open sourceComposio: Cursor vs Claude Code after 100+ hours
Open sourceObot | Enterprise AI Control Plane & MCP Gateway
MIT MCP gateway + managed cloud. Governance plane between Cursor/Claude/ChatGPT agents and tools.
Open sourceCoder | Enterprise AI Development Infrastructure & Governance
Open sourceOpenHands — The Open Platform for Cloud Coding Agents
Open sourceRunerrand — Errands run themselves
Show-HN-adjacent agent surface this window.
Open source