Reusable AI skills and capabilities for agent workflows
dahiya_prtk27
Automatic model failover for OpenCode. A local OpenAI-compatible proxy that routes to the best available model and fails over across providers on rate limits, quota exhaustion, 5xx, timeouts and context-length errors.
...moreataztech910
Google ADK (JS) model adapter for Kitana — lets LlmAgent route through Claude CLI / Codex CLI / Ollama / API-key failover instead of Gemini/Vertex.
...morewannanbigpig
DeepSeek 官方余额、Token 用量、月历热图与离线 tokenizer，内置在 Harness 侧栏
starkyru
Drop-in approval inbox components for LangGraph human-in-the-loop agents
nekocheese
A JavaScript Discord bot framework designed for developers familiar with discord.py.
itspraveen
eval-gpt
GitHub Actions
Locally patch the official OpenAI Codex VS Code extension task list to filter by the active workspace.
kriva
Official B2B WebAssembly Client-Side Image & PDF Optimization SDK. 100% Zero-Upload, Browser GPU/RAM Execution, 0ms Backend Latency.
...moreskywalker2006
dsh-passwords: a server-grade gateway that turns DeepSeek Harness into a multi-tenant platform — remote access + automatic HTTPS, per-subuser permissions & quotas, sandbox enforcement, first-run setup, SQLite auth with at-rest encryption, rate-limit and a
...morelumpenspace
Provider-neutral model discovery and picker metadata
tai42 <[email protected]>
Command-line client for operating a tai42 server over its HTTP API.
millwright-labs
Agent Skill: make Claude write in Barbara Minto's Pyramid Principle - answer first, grouped reasons, evidence under each.
...morecheshireez
In-GUI skill hub for DeepSeek Harness (dsh): browse the full local skill catalog from the official ctx.skills registry (every root + third-party providers), toggle skills on/off, inspect bodies, surface frontmatter diagnostics, and scaffold new skills — p
...moretradejs-dev
MIT-licensed browser-safe helpers for independently packaged TradeJS strategies.
jkwd
A first-person 3D map of a codebase, with a visual coding workflow for Cursor.
taozhi
A transparent local proxy that explains prompt-cache misses.
fmckie
Unified LLM streaming API for Anthropic, OpenAI, and Gemini
buchengjin
Spec-Powered AI Development Framework - 融合 OpenSpec 规范驱动 + Superpowers 执行引擎的企业级 AI 辅助编程框架
woyeshishen
为 DeepSeek Harness 提供外部视觉模型能力：纯文本主模型通过 describe_image 工具调用外部视觉模型看图，拿到纯文字描述（多模态补全）。静态 Cordis 插件，随 DSH 启动自动加载。
tom-villani
TypeScript SDK for LocalVectorDB — a document-first vector database with SQLite + FAISS, hybrid search, and an HTTP server
...moreGitHub Actions
Generic property graph engine with vector similarity search — extracted from scrollstr's PolyGraph
lesliechowsh
Memo — session memory search for DeepSeek Harness agents: cross-session full-text recall (memo_search), distilled notes (memo_remember), and corpus stats (memo_stats) over the official sessionQuery service. Zero infrastructure, local-first.
...moreadityavg13
Run-scoped deferred tools, skills, and duplicate prompt context for Pi.
anweat
DSH 助手消息锻造台：可创建/修改/注入测试用 assistant 消息，并可导入识别 session.jsonl(.zstd) 会话日志。