Tools
Tools: I Built an OS That Runs Any File Format Using AI — Including Ones You Just Invented
What if your OS could run a file format you just invented?
The Core Idea
How It Actually Works
Layer 1: CDM (Capability Decomposition Model)
Layer 2: DynGen (Dynamic Primitive Generation)
Layer 3: SANDBOX_EXEC
Real Working Examples
The Boot Process
What's Not Finished (Being Honest)
What I Learned Building This
What's Next
Try It I created a file called app.icm with this content: .icm is not a real programming language. No interpreter has ever existed for it. I typed: No hardcoded parser. No pre-built interpreter. The AI read the file, understood what it was trying to do, converted it, and ran it. This is ICM-OS — a research prototype of an intent-driven operating system I've been building over the past few months. Current operating systems assume you know exactly what tool you need: ICM-OS tries to collapse this into: You express what you want in natural language — any language — and the system figures out the rest. ICM-OS boots as a real operating system (Linux 6.1.82 kernel, GRUB2 bootloader, Intel e1000 NIC driver, real TCP/IP stack). It's not a Docker container or a fancy Python REPL. It's an OS you can boot from an ISO. The architecture has three layers: When you type an intent, the AMS (Intent Decomposer) calls DeepSeek to break it down into a DAG of primitives — small, composable units that each do one thing. Each primitive is a Python class implementing invoke(). The output of each node flows into the next. The graph is validated for type safety and acyclicity before execution. Here's where it gets interesting. If a needed primitive doesn't exist in the registry, the system: On the next boot, all cached primitives are restored automatically — zero API calls needed. Next time you boot and ask for SHA256, it loads instantly from cache. The system gets smarter over time. This is the "run anything" primitive. It: This is how .icm files work. This is how a file with no extension works. This is how a file written in a language you invented 5 minutes ago works. Actual DNS resolution and HTTP: Multilingual intent — no configuration needed: The AMS extracts intent parameters regardless of input language. No regex, no language-specific parsing — DeepSeek handles it. Webpage summarization: Running a fibonacci script: Reading real kernel data: It's a real bootable system: What happens at boot: 1. Kernel configuration is painful. make oldconfig silently drops options that don't have their dependencies satisfied. I spent hours debugging why CONFIG_E1000=y kept disappearing. 2. exec() is genuinely powerful and genuinely dangerous. Dynamic code generation opens up the system in ways that are hard to reason about. The upside is incredible flexibility. The downside is obvious. 3. Intent extraction is harder than intent execution. Getting the AI to reliably pull target_lang, url, path, and content out of arbitrary natural language inputs — in any language — required more iteration than I expected. 4. Caching is underrated. The first version regenerated every primitive from scratch on each boot. Switching to disk-cached primitives made the system feel dramatically more responsive. For the full bootable experience, see the build instructions in the README. GitHub: https://github.com/jinbohao1688/icm-os
Paper (CDM/GBT theory): https://jinac.vxni.ink Templates let you quickly answer FAQs or store snippets for re-use. Hide child comments as well For further actions, you may consider blocking this person and/or reporting abuse
