timwhitez/dsh-self-evolving

README 摘要

dsh-self-evolving English 简体中文 An evidence-first, crash-resumable self-evolution engine for DeepSeek Harness. It generates bounded Cordis plugin candidates, runs them through isolated real-Loader admission, evaluates them with Harbor, and preserves an auditable lineage. [!IMPORTANT] v0.2.0 verifies stable iteration and a measurable fixed-replay engineering effect. It does not claim a Terminal-Bench score improvement, sealed promotion, leaderboard result, or SOTA performance. Why this project exists Self-modifying agent systems are easy to demo and hard to trust. dsh-self-evolving treats every candidate as untrusted and makes the controller, evaluator, budget, dataset split, and safety policy part of a trusted computing base. A result is accepted only when its source identity, evidence, cost, lifecycle, and recovery path reconcile. The project is a standard DSH Cordis plugin/service—not a fork of DSH and not a second controller wrapped around it. What is verified Capability Evidence-backed status Standard DSH/Cordis controller and candidate plugins Verified with the real Cordis Loader Bounded multi-file candidate generation Verified through a networkless proposer sandbox Official De…

分类