DSH-PLUGIN STORE / LIVE CATALOG
聚合 GitHub 上的 DSH 插件，打造 DeepSeek Harness 生态的一站式目录。
15 个项目，匹配「benchmark」
Tiger3807861189
DeepSeek V4 × J-Space capability realization report — benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4 (Flash/Pro).
morluto
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.
openguardrails
The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.
ZK-Andy
Continual self-evolution plugin for DeepSeek Harness: versioned, auditable, rollback-safe harness state refined from session trajectories, with a benchmark-driven validation loop.
hccccc01333
dsh-excel-chat — talk to Excel in DeepSeek Harness: create, edit, repair, and verify spreadsheets by conversation (cells, formulas, styles, filters, tables, charts); every edit is auto-validated.
Apageoflove
Local-first experiment and evaluation workbench plugin for DeepSeek Harness (DSH).
LeslieWylie
A reusable DeepSeek Harness bundle for evidence-driven memory, orchestration, benchmark operations, and plugin release workflows.
dongsheng123132
Deterministic revision-pinned benchmarks and regression evidence for DeepSeek Harness
morluto
Help your agents find the smoking gun they're looking for. Optimization evidence for agents: find complexity hotspots.
Lhy723
Benchmark-driven self-evolution for DeepSeek Harness · 冻结基准上的 Agent Profile 自我进化：评测 → 候选 → 严格接受/回滚
1052326311
Execution-time drift firewall for long-running DeepSeek Harness agents. Real-Harness tests: unsafe stale mutations 12/12 native -> 0/12; valid controls 7/7 both; post-SIGKILL unsafe continuation 2/2 -> 0/2.
PangYiMing
DSH plugin: run a command N rounds, judge by median/distribution — 批量回归取统计结论
PerryLink
Cost governance for DeepSeek Harness: aggregated token/cost metering per model, session and day, budget caps with threshold alerts and over-limit policies, carbon footprint estimation, per-model latency benchmarks, a Settings budget tab, and the /budget command
hccccc01333
Agent evaluation platform for DeepSeek Harness: benchmark YAML, headless dsh orchestration, trace-based metrics, LLM judge, paired A/B, keyless replay, and cross-harness import.
r600a-code
DSH plugin: sub-agent matrix swarm — routes heterogeneous tasks to the most suitable model (OpenRouter-like + cfgpu.com/llm/square), dispatches each via in-process subagents. 32/32 benchmark green.