Plugins

Brings the session history of nineteen other coding agents into DeepSeek Harness: recall, session digest and per-file history tools over a local index, plus optional automatic recall before each step.

Reads the session files nineteen other coding agents on this machine already wrote — Claude Code, Codex, Cursor, opencode, Antigravity, Kimi, Cline, Zed and more — including sessions from before it was installed: deja_recall, deja_session and deja_blame tools, a /deja command, and optional automatic recall added to the runtime context. Local BM25 index, no LLM, no embeddings, no network.

Failure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.

Local-only project memory with zero bundled runtime dependencies or external services: structured JSON plus generated PROJECT_MEMORY.md, token-bounded session-frozen Hot Memory designed to preserve prompt-prefix cache hits, cached cross-project BM25 ranked recall, editable pin/supersede/archive lifecycle, configurable top-level turn-end distillation, and a bilingual Web panel for search, inspection, diagnostics, and live settings.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

General-purpose knowledge base for DSH: import md/txt/json/yml/docx/pdf, folder management, FTS5 full-text search (BM25), and a Web management UI.

BM25 keyword-based memory recall.

Project memory for DeepSeek Harness: project files are indexed into searchable summaries as they are read, so after context loss the agent retrieves hits on demand instead of re-reading files, with source citations and BM25 ranking.

Cross-session plaintext memory: deterministic BM25 keyword recall (no embeddings), memory_save/list/search/confirm/forget tools behind a human-confirm gate, and global + project-scoped JSON stores that follow your git repo.

Native tools for an Obsidian wiki vault: wiki_query, wiki_write, wiki_rename, wiki_scaffold, wiki_archive, and wiki_lint cover BM25 search with link-graph context, bookkeeping writes with sha256 source tracking, vault-wide renames, mode scaffolds, source archiving, and health checks — with cross-process locks and optional git auto-commit.

Conversational DSH plugin finder: four-source unified index, BM25 pre-filter plus LLM semantic ranking, candidates carry evidence grades and local static security audit, safe install flow with post-install verification.

PLUR memory rendered into the system prompt on each assembly rather than exposed as a tool call, so the block is replaced instead of appended and context stays flat across a session. Fully local hybrid search (BM25 + BGE fused with RRF), plain YAML storage you can edit, per-workspace scoping, and a /plur-memory browser.

Code knowledge graph bridge for codebase-memory-mcp: semantic symbol search (BM25), source snippets, architecture overview with Leiden communities, call/data-flow/cross-service traces, graph-augmented grep.