Grok Build adapter for OffRouter. Integrates via custom model config and plugin/MCP interfaces.

Scaffold a starter Ryu SDK project with a Runnable, gateway-pointed model config, and manifest.json manifest

Entity decorators and metadata for the NattyJS ORM: model config, column mapping, primary keys, and relationship definitions.

ph-clint plugin: resolve a runtime model config into a Mastra model config for OpenRouter / OpenAI-compatible providers alongside the Anthropic default.

Framework-agnostic config-driven form model: config types, zod schema, and configToZod data-schema derivation

Authoring project envelope validation, graph purity checks, and model-config merge-on-save for Graphs Studio.

DSH model channel manager: roundrobin failover engine (host) + model config view tab (client).

portmind core - scanning, enrichment, data model, config, history. No UI, no AI dependency.

Inline model capability controls for stock DeepSeek Harness Models settings

TokenMark CLI — recommend the best local-LLM model + config for your hardware from real benchmarks (Strix Halo, DGX Spark, RTX, and more).

dsh web UI admin plugin: extension-plugin marketplace tab, MCP server & session-history settings pages, subagent management (named delegation-tool instances with persona/tool-filter/model config, plus external CLI backend mounting), slash-command & Claude

`@wujie-shell/config` is the product configuration loader for `wujie-shell`. It reads a UI product project's environment files and `shell.config.mjs`, then normalizes paths, ports, runtime directories, model config, and OpenClaw asset locations for shell-

File upload + vision analysis for DSH (DeepSeek Harness) web GUI and Desktop: categorized composer upload buttons (spreadsheet/document/image/video), per-user vision model config (OpenAI-compatible baseURL + apiKey), optional cross-session sharing, and in

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive s

Model-facing view, create, literal replace, and line insert tool over the Harness filesystem service

Composition-authored deployment persona section for the DeepSeek Harness

Model-facing owner-scoped persistent Bash tool backed by the Harness PTY service

Model-facing workflow tool: run a JavaScript orchestration script over ctx.workflows

Model-facing web tools (web_search, web_fetch) over the DeepSeek Harness web capability seam (ctx.web)

Model-facing owner-scoped persistent PowerShell tool backed by the Harness PTY service