Construct modular LLM agents with a PyTorch-like API.
npx skills add https://github.com/AIladin/promptimus --skill promptimus
Please help me install this Agent Skill. Skill: promptimus Source: https://github.com/AIladin/promptimus/tree/main Command: npx skills add https://github.com/AIladin/promptimus --skill promptimus
This Skill provides a powerful, PyTorch-inspired framework for building sophisticated, composable Large Language Model (LLM) agents, simplifying complex AI development.
Use the promptimus skill to create a simple memory module agent with an OpenAI LLM provider.
High-intent search queries and answers about installing and using this skill.
You can build composable LLM agents using a modular, PyTorch-inspired API that supports hierarchical component design, advanced tool calling, memory management, and structured output generation.
Retrieval-augmented generation works with Ollama and OpenAI providers by integrating embeddings and vector stores, allowing agents to access and utilize external knowledge bases during generation.
Yes, you can integrate external tools seamlessly using either ReACT patterns or native OpenAI function calling to enable agents to perform actions like booking appointments or checking order status.
The best way to add observability to LLM agents is by integrating tracing with Arize Phoenix, which provides deep insights into agent behavior and execution paths.
No, you do not need a vector store for memory management; the framework implements robust conversation history tracking natively, while vector stores are used separately for retrieval-augmented generation.
SpillwaveSolutionsConfigure LLM providers for agent-memory summarization via interactive wizard.
KappTech88Trace, evaluate, and monitor LLM applications with OpenTelemetry.
dandudziDesign and implement RAG pipelines with chunking, embeddings, and vector stores.
EanLeeDesign autonomous AI agents with tool use, memory, planning, and multi-agent orchestration.
