ai-coding-agent-open-source-analysis
Summary
A comparative research repository on AI coding agents, full-source scanning, spec-driven development, and LLM wiki/RAG trends, with analysis reports, category READMEs, CSV tables, and a data/source-inventory.json cataloging the analyzed agents. Useful as the index that cross-references the Tier 4 agents.
Key Takeaways
- source-inventory.json is a machine-readable catalog of coding agents
- Covers spec-driven development as an emerging agent workflow
- Good comparative axes: context strategy, edit format, verification
Reliability Note
Independent survey (original text largely in Korean); inventories verified against the upstream repos.
Flows informed by this source
2
Single-Agent vs Multi-Agent: Decide and Design
A decision flow for the most expensive architecture choice in agent systems - grounded in what actually ships versus what demos well.
+1 more steps to Done
Best forbuilders who have shipped a basic app before
Design the Agent-Computer Interface (ACI)
Apply SWE-agent's key finding: agents perform dramatically better when their commands, viewers, and feedback are designed for models, not humans.
+2 more steps to Done
Best forproduction-grade builds with strict verification