@trapstreet/dsh-trapstreet
Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run
88 results
Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run
Cloud-backed cross-session memory for DeepSeek Harness: structured entries + vector retrieval persisted to S3-compatible object storage (AWS S3 / MinIO / R2 / OSS), with local cache projection, approval-gated writes and auditable trails
Installable bundle contributing the DaoZang offline retrieval & original-text extraction skill to DeepSeek Harness (v2.0: launcher + self-check + workspace setup)
Local-first, source-linked Markdown wiki storage and retrieval plugin for DeepSeek Harness
DeepSeek Harness (DSH) plugin: a self-contained semantic memory (RAG) over all your chat sessions. Indexes messages live via session/event, stores embeddings in one local JSON file, and exposes a rag_search tool.
Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
边做边学知识库:CRAG 式纠错检索(L1 Markdown wiki + L2 Hindsight)→ 未命中后台经 L3 限流联网补料 → 蒸馏落 staged → 两段式 commit 升入 L1。
RAG 检索增强生成:向量数据库、嵌入、语义搜索、减少幻觉、来源引用。受 wshobson/agents(38k★ MIT)启发。
Turn explicit coding-agent corrections into executable DeepSeek Harness regression tests.
把技能当可训练参数:像训练神经网络一样训练 agent 技能(epochs/batchsize/learning rate/验证门禁,但不碰模型权重)——rollout→reflect→aggregate→select→update→evaluate 循环、候选编辑仅在严格改善 held-out 验证分时接受、文本学习率预算、零推理时模型调用、部署紧凑 best_skill.md。受 microsoft/SkillOpt(MIT)启发。
Pre-write reuse firewall for DeepSeek Harness: before the agent writes a new helper/service, surface the existing implementations that already cover that intent. Deterministic retrieval (no LLM) backed by the Auto_code_audit capability channel.
Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence
Agent benchmark evaluation plugin for DeepSeek Harness: web panel, slash commands, headless CLI, test-set import, model/judge switching, orchestration, scoring, and reports.
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection
DSH plugin: context archiving + historical retrieval — archive_session / search_archive tools over the session-archive skill (zstd session-log decode).
Deterministic regression tests for DSH policy decisions, evaluated without invoking the protected tool body.
几何论(共扼谱几何 CSG)知识库插件:纯离线 BM25 检索 208 篇文章全文 + 3833 分块 + 871 条主库真理层,零运行时依赖。Conjugate Spectral Geometry knowledge base for DeepSeek Harness: fully offline BM25 retrieval over 208 articles, 3833 chunks and 871 verified truths.
DeepSeek Harness plugin exposing the CX Agent Studio Scripting API CLI (cxas-scrapi / 'cxas') as model-facing tools: apps, deployments, evaluations, conversations, traces, tools, callbacks, variables, pull/push, and lint.
Cross-session knowledge for DeepSeek Harness: ctx.knowledge service + knowledge_* tools, SQLite FTS5 trigram retrieval (CJK substring) with L1 query expansion. V1.11 contract (write/update/search/list/delete + budget + events + error codes).
DeepSeek Harness plugin: forces one critique-and-improve round after each completed turn.
Evidence-first multi-model coding comparison workbench for DeepSeek Harness
A durable, bounded lifecycle supervisor with scheduled evaluation for live DeepSeek Harness sessions
Plugin value auditor for DeepSeek Harness: judge a plugin before install and audit installed ones — heuristic scan + LLM judge, with model-switch re-audit reminders. · DSH 插件价值裁判:装前判断值不值得装,装后审计是否还该留,模型切换时提醒复核。