Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

12 plugins found

P

plur

plur-ai/plur

PLUR memory for DeepSeek Harness — engrams injected straight into the prompt, no tool call required

2393 months agoMemoryApache-2.0
T

engramory (plugin)

tinqiao-oss/engramory

Long-term memory for DeepSeek Harness. What the AI remembers is saved as plain markdown files you can open and edit. Every conversation carries a short memory index, so the AI knows what it has saved and opens a note when it needs the detail. The index has a size cap (200 lines / 25 KB by default); a write that would push it over is blocked and the AI is asked to tidy up first. A sidebar Memory page lists every note, and the same memory also works with Claude Code, Codex and others.

2082 days agoMemoryMIT
T

engramory

tinqiao-oss/engramory

Curated file-based long-term memory for DeepSeek Harness — human-readable markdown notes, one plain-file store shared across hosts (git-ignored when it lives inside a project repo), and a deterministic index cap enforced by ctx.tools.guard()

1573 months agoMemoryMIT
K

dsh-engram

kenz1117/dsh-engram

Cross-session long-term memory as a local SQLite store: dual scopes (user + per-git-origin project), hybrid FTS5 + local-vector retrieval fused with RRF, an evidence gate that forces an explicit sufficiency judgement, provenance audit chains, SM-2 spaced-repetition review, consolidation distillation and decay forgetting, and a nine-view "Memory Palace" sidebar panel. 22 narrow-parameter tools, no external service, no API key, no Docker.

752 days agoMemoryMIT
C

Co-Engram (dsh-plugin)

co-engram/co-engram

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

113 months agoMemoryMIT
C

Co-Engram

co-engram/co-engram

Self-evolving team memory as plain Markdown in git: a native Cordis plugin that registers 38 bare-name memory tools plus a prompt-signals section re-evaluated at every assembly, with RPE reinforcement, decay and sleep consolidation; shares one data repo with its Claude Code (MCP) and OpenClaw hosts; verified against DSH 0.1.0-rc.6.

103 months agoMemory
S

dsh-engram

skepsun/dsh-engram

Zero-LLM auto-capture and a symbolic \[ENGRAM\] index with progressive disclosure, an ESR-lite task/evidence protocol (esr_task / esr_node / esr_close / esr_link), and per-workspace usage telemetry with an offline recall benchmark (npm run eval).

93 days agoMemoryMIT
E

dsh-manage

elmaxid/dsh-manage

Forces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every

13 months agoDev & Plugin ToolsMIT
M

dsh-engram-bundle

michengai/dsh-engram-bundle

NPM-installable DeepSeek Harness plugin that bundles Engram persistent memory MCP and injects parent-agent memory protocol.

13 months agoMCP & ConnectorsApache-2.0
Y

dsh-Engram

yhprime/dsh-engram

Experience and skill engine with a sidebar console and exp_record / exp_recall / exp_feedback / exp_consolidate / exp_type tools, stored in a local JSON file. Optional Git backup (off until you configure a remote) pushes the library to a remote you choose; GitHub sign-in uses a device code or a token kept in local settings.

0yesterdayMemoryMIT
M

dsh-kb-curator

mark-mph/dsh-kb-curator

Bundles the kb-curator skill, which keeps a local three-layer knowledge base and refuses to index anything the user has not approved. The L2 retrieval layer needs @kenz1117/dsh-engram installed separately, and the engine runs on Windows only.

0last monthSkillsMIT
Y

dsh-engramory-recall

yffo/dsh-engramory-recall

Local BM25 auto-recall, a fail-closed write guard, a static doctor and a memory panel for an Engramory markdown store. No network, no daemon and no model calls unless you opt in; recall quality is measured by a reproducible benchmark in the repository.

0last monthMemoryMIT