All activity
Promptise is an open-source Python framework for building Agentic Systems. Turn any LLM into a production-ready agent and skip months of glue code. Five composable modules: the Agent for production-ready agents with zero boilerplate, the Reasoning Engine to design how your agent thinks from the ground up, MCP for scalable, secure and production-ready APIs that agents understand, the Agent Runtime for autonomous agents that run forever and Prompt Engineering for prompts built like software.
PromptiseThe foundation layer for agentic intelligence.
Ruben Manserstarted a discussion
Whats the first thing you are going to build?
Ruben Manserleft a comment
Most agent frameworks help you build an agent. Promptise helps you operate one. There's a big gap between an agent that runs in a notebook and an agent that handles real users safely. Two to three months of infrastructure work, every time: authentication, rate limits, audit logs, memory isolation between users, approval flows for sensitive actions, restart after a crash, guardrails against...
PromptiseThe foundation layer for agentic intelligence.
Ruben Manserstarted a discussion
🚀 DeepMCPAgent 0.4.0 is here!
Hey Product Hunt 👋, We just shipped DeepMCPAgent 0.4.0, a big step forward in making AI agents more reliable, developer-friendly, and production-ready. 🔑 What’s New in 0.4.0 Better Error Handling → safer defaults and clearer exceptions when MCP tools or servers fail. Improved Tool Tracing → see exactly which tools were called, with inputs + outputs. Cleaner CLI → no more flaky auto-gen; we...
Ruben Manserleft a comment
Excited to share DeepMCPAgent with the Product Hunt community! 🎉 I built it to experiment with runtime tool discovery; no more hardcoding: the agent dynamically fetches tool schemas from MCP servers and generates typed LangChain tools out of them. It works with any LangChain-compatible model (OpenAI, Anthropic, Ollama, Groq, local, etc.) and supports both DeepAgents loops and fallback ReAct...
Deep MCP AgentsPlug-and-play AI agents via dynamic tool discovery with MCP
DeepMCPAgent lets you build AI agents that auto-discover and use tools via MCP. No manual wiring—just connect your LangChain model (OpenAI, Anthropic, Ollama, etc.) and the agent dynamically generates typed tools for production-ready workflows.
Deep MCP AgentsPlug-and-play AI agents via dynamic tool discovery with MCP