Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

78 plugins found

R

billion-context

ranxianglei/billion-context

The official billion-context plugin: a context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).

8k4 hours agoSessions & Messages
T

billion-context-dsh

tyan66666/billion-context-dsh

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

17111 days agoMemoryMIT
S

sieve (dsh-sieve)

sev7een7/sieve

Filters tool outputs, prunes stale context and discloses skills on demand for DSH 0.2.1-alpha.1.

11320 days agoSessions & MessagesMIT
S

dsh-sieve

sev7een7/dsh-sieve

Context engineering and token optimization plugin for DeepSeek Harness (DSH): tool output filtering, context pruning and progressive skill disclosure for LLM coding agents

106last monthSessions & MessagesMIT
V

capital-generation

v587d/capital-generation

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

3711 hours agoTools & CapabilitiesMIT
W

dsh-plugin-hub (dsh-lan-proxy)

wingsky-1/dsh-plugin-hub

Access the dsh web UI over LAN: HTTP/HTTPS/WS forwarding plus TLS (self-signed or custom certificates); adaptive Brotli/gzip compression for HTTP and permessage-deflate for WebSocket; half-open WebSocket probing keeps mobile clients from going stale after backgrounding; launch-token auto-injection lets LAN devices connect without copying the token; DNS-rebinding protection + loopback-only upstream allowlist. Retired by the author: published npm versions stay installable but receive no further DSH adaptations (migration guide: docs/migrations/dsh-lan-proxy.md in the repository).

329 hours agoIntegrations & RemoteMIT
R

GraphFlow

roarpeng/graphflow

Local-first code knowledge graph for coding agents: 10 MCP tools for layered context compression, DAG planning, incremental AST indexing, a cross-session skill flywheel, diagnostics, and graph artifact import/export.

307 days agoTools & CapabilitiesApache-2.0
G

dsh-web-remote

godchen520/dsh-web-remote

Access DSH from your phone or anywhere: Cloudflare Quick Tunnel public link, LAN HTTP/HTTPS direct access with an auto-generated self-signed certificate, token auth, gzip compression, a floating phone-icon panel with QR codes, configurable public URL and LAN port, and WeChat / Feishu / Telegram bot channels with per-channel health monitoring and session-completion push. Targets DSH 0.2.x (also works on 0.1.2-rc.1+).

2315 days agoIntegrations & RemoteMIT
F

dsh-dcp

fan56/dsh-dcp

Deterministic context compression for dsh — zero LLM calls, rule-based pruning that preserves paths, commands, error traces, and open todos verbatim. Compresses ~80k tokens to a few hundred.

203 days agoTools & CapabilitiesApache-2.0
G

dsh-headroom

giter00/dsh-headroom

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

183 months agoMemoryApache-2.0
W

dsh-plugin-hub (dsh-gzip)

wingsky-1/dsh-plugin-hub

Gzip compression for /api responses, fixing history-load timeouts over remote/low-bandwidth connections; skips SSE and already-encoded responses.

172 months agoDev & Plugin ToolsMIT
D

dsh-auxiliary

dsh-plugins/dsh-auxiliary

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

1619 hours agoTools & CapabilitiesLGPL-3.0
Y

dsh-argp

yoza10635/dsh-argp

Guarded context compaction for DeepSeek Harness (dsh): the LLM proposes, deterministic guards dispose — eager per-atom shrink (extract/summary/false under verbatim guards) + lazy reference-graph eviction (0-LLM) + byte-exact recall from an append-only log.

1521 hours agoSessions & MessagesMIT
D

dsh-context-compression-improved

drscrewdriver/dsh-context-compression-improved

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models. Within a turn it supports skeletonized information compression with a low original-text retrieval rate; at the tail of a turn it supports a turn-tail intent summary implemented purely by content substitution; context content stays safe, and the whole process runs inside the official JSONL compression.

1113 hours agoSessions & MessagesMIT
F

dsh-force-compact

falling-ts/dsh-force-compact

Forces context compression when running low-context llama.cpp models such as Qwen3.8-27B, improving model efficiency and usage smoothness, together with well-refined compaction prompts.

1011 days agoSessions & MessagesMIT
V

capital-generation (dsh-plugin)

v587d/capital-generation

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

82 months agoTools & CapabilitiesMIT
L

dsh-compressor (dsh-compressor)

lifeodyssey/dsh-compressor

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

73 months agoTools & CapabilitiesMIT
K

dsh-compaction-instant

kitdoesit/dsh-compaction-instant

LLM-free lossless* compaction engine for DeepSeek Harness

73 months agoSessions & MessagesMIT
A

dsh-message-gateway

a792883583/dsh-message-gateway

Multi-platform message gateway and WeCom AI bot bridge with session context compression and smartsheet creation.

6last monthIntegrations & RemoteMIT
G

dsh-context-lens

goodandready/dsh-context-lens

AST-based context compression, test log filtering, and token budget guard for DeepSeek Harness: strips redundant syntax, prunes noisy log lines, and enforces a token ceiling so the context window never overflows.

68 days agoTools & CapabilitiesMIT
E

dsh-web-network-optimizer

enterhalf/dsh-web-network-optimizer

Network optimization for the DSH web UI: reduces transfer size with caching and compression to greatly speed up page loading, plus a connection-drop indicator and automatic reconnection. Ideal for users pursuing peak performance or using unstable networks.

62 months agoDev & Plugin ToolsMIT
I

context-assembler-DSH

i1j/context-assembler-dsh

Context Assembler plugin for DeepSeek Harness: topic-block context assembly, water-pressure topic splitting, tool trace/rewrite, reality recall injection and handoff planning.

63 months agoSessions & MessagesMIT
B

dsh-context-zip (dsh-context-zip)

brunhildzhou/dsh-context-zip

Replaces the built-in DSH compaction summarizer with a five-section handoff summary and keeps every shadowed message readable in a segment directory.

5last monthMemoryMIT
M

dsh-GOkifu-compact

mycf711/dsh-gokifu-compact

Kifu-style context compression for long DSH sessions: each step folds new turns into a DAG (node = position, edge = attempted fix), injects only a ~417-token hot list (2000-edge fixture, L5 tier), and adds failure memory plus position-repetition detection. Each span is summarized exactly once, so what is retained does not decay with the number of compactions.

42 days agoSessions & MessagesMIT