
dsh-memory-plus
可以有效减少token消耗!DeepSeek Harness memory plugins (dsh-plugin): CJK-aware session full-text search, tool-result dedup, hybrid vector+FTS5 memory search, cross-session core memory, near-lossless compaction locators. Real-harness verified, 47 tests.
What it doesAI
Memory plugin for DeepSeek Harness that reduces token usage via search, dedup, cross-session memory, and compaction.
- CJK-aware full-text search across sessions
- Hybrid vector + FTS5 memory search
- Cross-session core memory and compaction
AI-generated from the repo README — for reference only.
Installation
dsh plugin --profile web add github:QIANLING-0831/dsh-memory-plusInstall method: GitHub · not yet tested in container (L3+)
Compatibility
| DSH Version | Status |
|---|---|
| not stated | Declared — not tested |
Requirements
- • Node.js: not stated
- • DSH: declared "not stated"
- • External credentials: none detected
Security Report
Automated static scan, not manual review.
No critical or warning findings in the automated scan. The result is valid only for the commit hash shown.
0.1.0c217831f4f482026-08-20c217831f4f48The scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.
Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
vet verdict: vet: clean · score 100
- R10 · info [heuristic] — 依赖清单:11 项(@deepseek-ai/schemastery, @deepseek-ai/cordis, @deepseek-ai/dsh-system-prompt, @deepseek-ai/dsh-tools, @types/node, tsdown, typescript, vitest, @deepseek-ai/cordis, @deepseek-ai/dsh-system-prompt, @deepseek-ai/dsh-tools,供 LLM 审计供应链;已知漏洞核对见后续 OSV 精确版本查询(网络失败静默降级))
vet is advisory and does not change dsh’s four-tier level.
• Static heuristic scan: done (10 files)
• Dependency vulnerabilities: requires deep audit (L3+)
• Permission sandboxing: requires runtime testing (L4+)
Activity
Last commit 2026-08-20 · activity: Active
• Repo created: 2026-08-20
• Stars: ★ 2 · Forks: 0
• Health: Active — committed within last 30 days