Auto-Arch Tournament vs ContextPool

Auto-Arch Tournament is an autonomous research system where an AI agent iteratively proposes, implements, and validates microarchitectural improvements to a RISC-V CPU. Starting from a standard 5-stage pipeline, the loop runs hypotheses in parallel, each going through formal verification (53 symbolic checks), cycle-accurate simulation, multi-seed FPGA place-and-route, and CoreMark CRC validation. Only hypotheses that beat the current champion get merged; everything else gets discarded. Starting from 301 iterations/second, the system hit 577 iter/s (+92%) across 73 attempts in 9.8 hours — producing a design 26% faster and 40% smaller in LUTs than the baseline. The insight the author drives home is that the real innovation isn't the AI agent — it's the verifier. The orchestrator is hardcoded to prevent agents from manipulating their own evaluation gates, a simple but critical design constraint that turns a creative process into a trustworthy one. Without a rigorous verification harness, agent-driven optimization becomes a confidence trick. This is early but fascinating proof that AI-driven hardware design loops can produce commercially meaningful gains. The repo uses Claude Code or Codex as the coding agent, SystemVerilog for the RTL, and standard open-source EDA tooling (Yosys, nextpnr, Verilator). It's a compelling template for anyone building agentic optimization loops where correctness matters.

ContextPool solves one of the most frustrating aspects of AI-assisted development: every new session starts cold. It scans your historical Cursor, Claude Code, Windsurf, and Kiro sessions, extracts engineering insights — bugs fixed, design decisions made, architectural patterns used — and automatically surfaces the relevant ones as context at the start of new coding sessions via MCP. Rather than requiring developers to maintain documentation or manually copy-paste context, ContextPool builds a living knowledge base from the work you've already done. The extraction layer identifies decision points, error patterns, and solution paths across all your past sessions, then uses semantic similarity to load only what's relevant to your current task. The open-source core works locally; an optional team sync feature lets engineering teams share session insights across developers so institutional knowledge stops living in individuals' chat histories.