Native memory plugin for DeepSeek Harness
yul761/dsh-statecore · productivity
Native memory plugin for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore.
★ 2GitHub stars
0Forks
2026-08-31Last updated
TypeScriptLanguage
MITLicense
Key features
- Auto-ingest — every human user/message and every assistant/message in a session is fed into per-project memory as it happens, with no model cooperation required.
- StateCore — the memory engine this plugin and statecore-mcp both front
- An MCP server can only be pulla model has to decide to call a write tool.
- Machine-composed user/messages (context injections, compaction checkpoints) are recognized by their MessageSource and skipped, so memory captures the conversation, not the scaffolding.
- Auto-inject — each session's agent/pre-step waterfall folds a budgeted digest of project memory into the model's context automatically, the same fold pattern @deepseek-ai/dsh-agent-instructions uses for AGENTS.md/CLAUDE.md instructions.
Requirements
- @deepseek-ai/dsh-compaction is a types-only devDependency (its SessionEventMap declaration merge types the compaction/summary record src/compaction.ts listens for).
- It is erased at runtimehosts that mount no compaction plugin run this plugin unchanged, and hosts with any compaction backend — first-party dsh-compaction-basic or a third-party one — compose with it through the seam's event, not through any package coupling.
Install command
dsh plugin --profile web add github:yul761/dsh-statecore