doc: add feature Prompting Creator in the roadmap

Author: 0uep

README.md

@@ -165,7 +165,7 @@ export GI_MODELS_DIR=/path1:/path2:/path3
 ```
 
 `GI_MODELS_DIR` is the root path where your models are stored.
-`goinfer will search `*.gguf` files within all `GI_MODELS_DIR` sub-folders.
+`goinfer` will search `*.gguf` files within all `GI_MODELS_DIR` sub-folders.
 So you can organize your models within a folders tree.
 
 The other environment variables are:
@@ -252,8 +252,8 @@ metricsMaxInMemory: 1000  # maximum number of metrics to keep in memory
 startPort: 6000           # first ${PORT} incremented for each model
 
 macros:  # macros to reduce common conf settings
-    cmd-fim: /home/me/llama.cpp/build/bin/llama-server --props --no-warmup --no-mmap --verbose-prompt --jinja
-    cmd-common: ${cmd-fim} --port ${PORT}
+    cmd-fim: /home/me/llama.cpp/build/bin/llama-server --props --no-warmup --no-mmap --verbose-prompt
+    cmd-common: ${cmd-fim} --jinja --port ${PORT}
     cmd-goinfer: ${cmd-common} --chat-template-file template.jinja
 
 models:
@@ -445,8 +445,7 @@ You receive a JSON response generated by the model running on your GPU rig.
 ### March 2023
 
 In March 2023, [Goinfer](https://github.com/LM4eu/goinfer)
-was an early local LLM proxy swapping models and supporting
-Ollama, Llama.cpp, and KoboldCpp.
+was an early local LLM proxy swapping models and supporting Ollama, Llama.cpp, and KoboldCpp.
 Goinfer has been initiated for two needs:
 
 1. to swap engine and model at runtime, something that didn’t exist back then
@@ -519,19 +518,29 @@ Manage the OpenRouter API key of a AI-powered frontend.
 
 > **contribute** – If you’re interested in any of the above, open an issue or submit a PR :)
 
+### Prompting creator UI
+
+Integrate a Web UI to ease creation of multi-step AI agents like:
+
+- [github/synw/agent-smith](https://github.com/synw/agent-smith)
+- [n8n](https://n8n.io/)
+- [flowiseai](https://flowiseai.com/)
+- tools from [github/HKUDS](https://github.com/HKUDS)
+
+The angentic prompt syntax [YALP](https://yapl-language.github.io) and its [VS-Code extension](https://github.com/yapl-language/yapl-vscode) authored by two Germans: [Nils Abegg](https://github.com/nilsabegg) et [einfachai](https://github.com/einfachai) (see also [einfachai.com](https://einfachai.com)).
+
 ### Nice to have
 
 Some inspiration to extend the Goinfer stack:
 
 - [`compose.yml`](./compose.yml) with something like [github/j4ys0n/local-ai-stack](https://github.com/j4ys0n/local-ai-stack) and [github/LLemonStack/llemonstack](https://github.com/LLemonStack/llemonstack)
-- Multi-step AI agents like [github/synw/agent-smith](https://github.com/synw/agent-smith), [n8n](https://n8n.io/), [flowiseai](https://flowiseai.com/), tools from [github/HKUDS](https://github.com/HKUDS)
 - WebUI [github/oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui), [github/danny-avila/LibreChat](https://github.com/danny-avila/LibreChat), [github/JShollaj/Awesome-LLM-Web-UI](https://github.com/JShollaj/Awesome-LLM-Web-UI)
 - Vector Database and Vector Search Engine [github/qdrant/qdrant](https://github.com/qdrant/qdrant)
 - Convert an webpage (URL) into clean markdown or structured data [github/firecrawl/firecrawl](https://github.com/firecrawl/firecrawl) [github/unclecode/crawl4ai](https://github.com/unclecode/crawl4ai) [github/browser-use/browser-use](https://github.com/browser-use/browser-use)
 - [github/BerriAI/litellm](https://github.com/BerriAI/litellm) + [github/langfuse/langfuse](https://github.com/langfuse/langfuse)
 - [github/claraverse-space/ClaraCore](https://github.com/claraverse-space/ClaraCore) automatizes installation & configuration of llama-swap
 
-## Contributing
+## Contributions welcomed
 
 1. Fork the repository.
 2. Create a feature branch (`git checkout -b your‑feature`)