AI workflows · Developer tools · Automation
See how the system actually works.
Real AI workflows, developer tools and automation, demonstrated through systems that run.
- MIT licensed
- Stock Claude Code
- Obsidian-native
- One command
The vault graph: memory on disk
Featured system
Claude Code + Obsidian: Change How AI Memory Works
Claude Code forgets everything between sessions, so every new chat starts with you re-explaining your project. This architecture builds the fix: an Obsidian vault holding the agent's memory, commands and skills as plain markdown, symlinked back so the agent reads them as its own.
Claude Obsidian Memory
The persistent context and auto-memory system for Claude Code. Includes daily journal automations, bash scripts, and symlink topology.
Watch
The systems, recorded.
Every build runs on camera. Shorts for the one idea, long-form for the full setup. Pick a playlist.
Claude Code: Workflows, Setup & Memory
Obsidian + AI Second Brain: The Complete Setup
AI Context & Memory
Systems library
Three tracks, one standard: it has to run.
Each track covers a different layer of the same stack. Here is what each one will walk through.
- 01
AI Workflows
How an agent setup is arranged so it holds context across a real project: where instructions live, what the model is allowed to see, and how the whole thing is recovered after a restart.
- context layout
- instruction files
- review loops
- 02
Developer Tooling
The small tools that remove friction: command-line utilities, editor integrations, MCP servers, and scripts. Built on screen, with the reasoning behind each design decision left in.
- cli design
- mcp servers
- editor integration
- 03
Automation Systems
Pipelines meant to run unattended: capture, processing, publishing, monitoring. Wired end to end, including the error handling that decides whether they are safe to leave alone.
- scheduling
- failure handling
- observability
Method
Demonstration over commentary.
Predictions about AI are cheap. A system either runs or it does not, so every breakdown follows the same three steps and ends with something that works.
- 01
Problem
Start from friction that costs real time in real work: a step repeated too often, a handoff that keeps breaking, a task that never quite finishes. The problem is stated concretely before anything gets built.
- 02
Working System
Build it on screen until it runs. Config, code, and wiring in full, with the dead ends and the errors left in, because the recovery is usually the part worth watching.
- 03
Reusable Components
Separate the parts that transfer from the parts that were specific to the example: the script, the config, the prompt, the structure. Then they can be lifted into a different setup.
About
About Seestack.
Engineering Lab · Developer Tooling Studio
Seestack is an independent engineering lab and developer tooling studio focused on autonomous coding agents, persistent memory architectures, and verifiable terminal workflows.
The systems come out of real production engineering work and the AI tooling used to ship code day to day, running live on actual projects with the rough edges left visible.
The editorial rule is strict: if a workflow or tool has not been built, run, and battle-tested in a live terminal, it does not get published here. Zero wrappers, plain markdown, verifiable runs.
Subscribe to Get the Script & Custom Mods
Enter your name and email below. Subscribing gives you free weekly developer tools and unlocks the one-line install command, context-bar mod, and Obsidian vault instantly.











