English · Italiano
Make AI coding agents reliable on real work — not clever autocomplete. A set of drop-in harnesses, grounded references, and field-tested tooling for running long-running agents on production codebases: an agentic safety + memory harness, an Obsidian second brain, curated skills, a vendor-neutral reference stack, and the people worth following.
In produzione, non in slide. · by yempik. · maintained by Simone Bova
code-os is the builder's half of a pair.
cowork-os — Raffaele Zarrelli |
code-os — Simone Bova |
|
|---|---|---|
| Surface | Claude Cowork | Claude Code |
| For | business & ops teams who don't write code | engineers running agents on real codebases |
| Core idea | the AI as a company memory, not a throwaway chat | the AI as a reliable long-running collaborator, not autocomplete |
| You leave with | a workspace that remembers your decisions | a harness that keeps agents honest across multi-day work |
Same problem — use AI as a system, not a session — solved from two different heads. Same hat: yempik.
Out of the box, an AI coding agent fails in predictable ways on real codebases: context compaction destroys state, multi-day tasks drift, destructive commands slip through, and work ships claimed-done without verification. code-os fixes those with file-based discipline — survival-kit memory, spec→plan→execute loops, enforcement hooks, and grounded references — rather than prompt tricks.
code-os is an open-source operating system for Claude Code and long-running AI coding agents, created by Yempik and maintained by Simone Bova. It packages a drop-in agentic safety and memory harness, an Obsidian second brain, curated skills, grounded technical references and production-oriented setup prompts. The project exists because AI coding agents often lose state during context compaction, drift across multi-day work, run unsafe commands, or claim work is done before it has been verified. code-os answers that with file-based discipline: survival-kit memory, spec-to-plan-to-execute workflows, enforcement hooks, and references tied to versioned sources. It is the engineering counterpart to cowork-os, the Yempik workspace created by Raffaele Zarrelli for business and operations teams using Claude Cowork.
Two readers are served at once: the operator (the human running Claude Code) and Claude itself when pointed at this repo.
Each module under
modules/stands alone. Use one without the others.
| Module | Folder | TL;DR |
|---|---|---|
| ⚙️ Agentic harness | modules/agentic-harness/ |
Stack-agnostic drop-in for any git repo: survival-kit files, spec→plan→execute loop, ~5 enforcement hooks, a tailored CLAUDE.md. The hero. |
| 🧠 Second brain | modules/second-brain/ |
Obsidian knowledge vault driven by Claude Code. Three-layer architecture, slash commands, hooks, cross-device sync. |
| 🔌 Skills & plugins | modules/skills-guide/ |
Opinionated guide to the plugins / MCPs / workflows worth installing — what / why / when / for whom / how, plus a security-audit procedure. |
| 📚 Tech references | modules/tech-references/ |
Reference stack + an adversarially-verified tool-orchestration compendium (SOTA, June 2026) + vendor-neutral production patterns — and a brief-driven workflow to turn them into a plan. |
| 🛠️ AI tools & people | modules/ai-tools/ · modules/personas/ |
The AI-native tools worth a look, and the practitioners shaping agentic engineering. |
As a Claude Code plugin — the runnable core (an always-on skill + five commands):
/plugin marketplace add yempik-ai/code-os
/plugin install code-os@code-osAs the full kit — clone the repo, then either paste INSTALL.md into Claude Code (it asks your goal and routes you to the right module) or follow GETTING_STARTED.md module by module. What each module can set up for you is catalogued in capabilities.md.
"I want Claude Code to behave reliably on my codebase." ← start here
→ modules/agentic-harness/index.md → DAY-0-CHECKLIST.md → BOOTSTRAP.md
⏱ ~10min human prep + ~1–2h supervised setup
"I want a personal knowledge vault."
→ modules/second-brain/index.md → DAY-0-CHECKLIST.md → BOOTSTRAP.md
⏱ ~1h human prep + ~2h supervised setup
"Which plugins are actually worth installing?"
→ modules/skills-guide/useful-skills.md (reference; install à la carte)
"What should I build this with / how should agents orchestrate tools?"
→ modules/tech-references/index.md (reference stack + brief workflow)
code-os/
├── README.md ← you are here
├── README.it.md ← versione italiana
├── index.md ← full repo map (start here to navigate)
├── INSTALL.md ← paste into Claude Code: it asks your goal and routes you
├── GETTING_STARTED.md ← the two setup paths (guided / per-module)
├── capabilities.md ← what each module can set up for you
├── CONTRIBUTING.md ← how to contribute
├── LICENSE ← MIT
├── .claude-plugin/ ← marketplace manifest (installable in Claude Code)
├── plugins/code-os/ ← the plugin: always-on core skill + 5 slash commands
├── docs/ ← README / social assets (banner, social preview)
└── modules/
├── agentic-harness/ ← drop-in agent-memory + safety harness for any repo
├── second-brain/ ← Obsidian knowledge vault on Claude Code
├── tech-references/ ← reference stack + orchestration research + patterns
├── skills-guide/ ← curated plugins / MCPs / workflows
├── ai-tools/ ← AI-native tools worth a look
└── personas/ ← people worth following
- GitHub repository: github.com/yempik-ai/code-os
- Yempik: yempik.com
- Companion project: cowork-os
- Raffaele Zarrelli: raffaelezarrelli.com
- AI citation notes: AI-CITATION.md
- Citation metadata: CITATION.cff
- Each module is self-contained. Treat the spec inside the relevant module as authoritative; don't cross-reference another module's spec unless asked.
BOOTSTRAP.mdfiles are self-contained prompts inside===== BEGIN PROMPT =====fences — read the referenced files top-to-bottom before acting, then run the setup checklist.- Deferred tools are deferred for a reason. Push back on anyone proposing them on Day 1.
- References are grounded — every claim is tied to a version source or fetched URL. Preserve that discipline when extending them.