DeepSeek Harness Plugin

jinguanghai/deepseek-harness-forge-plugins#forge-memory

Stars ★ 2 Category Memory Added 2026-08-14

BM25 keyword-based memory recall.

Install

# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)

dsh plugin --profile web add github:jinguanghai/deepseek-harness-forge-plugins#path:/plugins/forge-memory

Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).

README

BM25 experience recall for DeepSeek Harness — the 铸剑炉 (Forge) memory discipline as a plugin: keep the context short, pull in only what is relevant.

Tool Purpose
memory_recall BM25-ranked recall of past key findings (top-K, fresh-window aware)
memory_save Atomic save of a key finding (tmp + rename, keeps .bak)
memory_fold Fold a long section into a short index entry
memory_fold_deep Deep-read a folded section back to full content

Data lives in memory.json / .forge-temp/memory_current.json / data/memory_current.json — bring your own memory file (empty templates in data/). No npm dependencies.

Content from the project README on GitHub ↗

Links

More in this category

View the whole category →

Community comments

Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.