01 / Product
Source Reads Bundle
Understand real AI-agent codebases through annotated architecture reads instead of shallow tool summaries.
Deep technical source reads with architecture notes, tradeoffs, diagrams, and reusable implementation patterns.
Inside
What is included.
Concrete deliverables, not a vague access promise.
- Annotated source-read markdown
- Architecture decision notes
- Pattern glossary
- Related Starkslab notes and tool references
Who it is for
Builders who learn from source code and want the implementation shape behind public agent systems.
Not for
Readers who only want rankings, vendor comparisons, or nontechnical market commentary.
Proof
Related public notes and tools.
Starkslab proof is the work itself: published notes, shipped drops, and operating loops.
OpenAI Symphony Review: What It Actually Does
OpenAI Symphony is an issue-driven coding-agent orchestrator with repo-owned workflow contracts, reconciliation loops, and per-issue workspaces. Here’s what it actually does and what builders should steal.
OpenClaw Architecture Explained: Gateway, Sessions, Memory, and Tools
Skimmable OpenClaw system map covering the gateway, sessions, memory files, heartbeat and cron, and the execution layer from inbound message to action.
OpenClaw Source Code Structure: Gateway, Heartbeat, Skills, and Runtime Architecture
OpenClaw source code teardown mapping the repo structure, gateway, heartbeat, routing, skills, self-modification, and the one trust risk behind the hype.
FAQ
Fit and delivery questions.
What makes this different from docs?
The bundle focuses on architecture decisions, boundaries, and what survives real operation.
Will future source reads be included?
The initial shelf is planned as a maintained bundle, with final access rules decided before launch.