LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

DSH 破甲插件：token 级重试环 + 十片按需叶子（含邻近交付）+ 分级 prefill + 拒答阶梯 L0–L3 + finish_reason 四路分流 + 请求体级整形。零宿主补丁，188 项测试 / 56 条探针。

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

See what a conversation feeds the model, what your rules keep out, and what one click would change.

Code intelligence for agents: find the code that matters and keep your context window and tokens lean.