Hopper vs SkillClaw

Hopper, from YC S24 startup Hypercubic, is the first agentic development environment purpose-built for mainframe systems. It lets AI agents navigate TN3270 terminals autonomously, write and submit JCL jobs, monitor JES output, debug failed jobs by analyzing spool data, query VSAM datasets, compile and run COBOL code, and manage CICS transactions—all via natural language prompts. Tasks that traditionally took mainframe specialists hours of manual TN3270 navigation can now be expressed as a single instruction. The technical challenge here is real: mainframes don't have nice REST APIs or modern dev tooling. They run on green-screen terminal protocols from the 1970s, and the humans who know how to operate them are retiring faster than they can be replaced. Hopper essentially wraps the entire mainframe interaction surface in an agent-friendly interface, translating intent into the arcane sequences of keystrokes and JCL that mainframes actually require. The product is free for individual developers (all core features, macOS/Windows/Linux) with Enterprise pricing for SSO, on-prem deployment, and SOC 2 reports. Hypercubic's team includes alumni from Cognition, Apple, and Windsurf. Given that mainframes still process an estimated $3 trillion in daily commerce and the COBOL developer shortage is acute, Hopper is targeting a genuinely underserved market with unusual urgency.

SkillClaw is a research framework from Alibaba's AMAP-ML team that enables collective skill evolution for LLM agent systems deployed at scale. The core idea: instead of each user's agent interactions existing in isolation, SkillClaw aggregates anonymized skill-improvement signals across all users to continuously refine a shared library of reusable agent skills — without requiring centralized fine-tuning. The framework introduces a three-component architecture: a Skill Extractor that identifies and catalogs atomic capabilities from interactions, a Skill Evolver that proposes improvements based on aggregate feedback, and a Skill Selector that routes tasks to the best-available skill version per user context. Published on April 9 and hitting #1 on Hugging Face trending papers this week with 277 upvotes, the paper reports significant improvements over per-user baselines on complex multi-step agentic tasks. This matters especially for production agent deployments where cold-start problems are severe — a new user's agent immediately benefits from millions of prior interactions. It's a fundamentally different model of agent improvement than either fine-tuning (expensive, periodic) or RAG (retrieval-only, no learning).