jasisz/aver

Vera: a programming language designed for LLMs to write

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

Make Gemini code like Claude Models. Forces it to inspect files before editing, plan changes, test its work, and back up every “done” with actual evidence.

Specs first. Code second. Proof always. You define the what. LLMs generate the how. hlv validates the proof.

Stops AI coding agents from claiming work is done without evidence. Deterministic hooks decide, TypeSafe's Jev advises. Append-only ledger, zero runtime dependencies.

오철칙(Iron Laws) - AI가 만든 코드의 보안·구조·유지보수 문제를 짚어 주는 소스코드 점검 CLI

SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).

Developer-centered AI engineering: build software with security, quality and governance. One local binary under the agent you already run

A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.