justvugg

Hi everyone,I built cli-use, a small Python tool that turns any MCP server into a native CLI.The idea is simple: HTTP has curl, Docker has docker, Kubernetes has kubectl — MCP should have a shell-native client too.Why I made it:MCP is useful, but using it through agents has overhead:every session pays schema discovery cost every call carries JSON-RPC framing responses are often verbose JSON...

I built dbcli, a lightweight database CLI designed specifically for AI agents that need fast, low-overhead access to relational databases.The main idea is to make database introspection and querying simple and efficient when an agent has shell access. With a single command (dbcli snap), you can retrieve schema details, table relationships, and basic data profiling (column stats, ranges,...

Hi everyone,I’d like to share a tool I built, called dbcli. It’s a database CLI designed specifically for AI agents, enabling them to understand and interact with any database using a single command. Whether you're developing AI systems that require database access or need a fast and efficient way to query and profile your databases, dbcli is optimized for speed and simplicity.Key...

I built Wiredigg, an open-source network traffic analysis and security tool written in Python. It combines real-time packet capture, protocol inspection, machine learning-based anomaly detection, and local LLM analysis via Ollama.The goal is to provide interactive network visibility with AI-assisted threat interpretation, while remaining local-first and easy to run. A Windows executable build...

PolyMCP is a framework that exposes functions (in Python or TypeScript) as MCP tools, serves them through standardized MCP servers, and orchestrates them with autonomous agents capable of planning and executing complex workflows.With PolyMCP, you can: 1. Expose existing functions (in Python or TypeScript) as MCP tools without rewriting the code. 2. Use the PolyClaw agent to dynamically...

Hi everyone, I have created EasyMemory: a lightweight, fully local memory backend for chatbots, agents and any MCP-compatible LLM (Claude, GPT, Gemini, Ollama…). Key points: • Auto-saves every conversation • Ingests PDFs, DOCX, Markdown vaults, folders • Hybrid retrieval: vector + keyword + graph (no extra libs needed) • Built-in MCP server → plug into Claude Desktop, custom agents, etc. • ...

Hi HN, Built llm-use: a lightweight Python toolkit for efficient agent workflows with multiple LLMs. Core pattern: strong model (Claude/GPT-4o/big local) for planning + synthesis; cheap/local workers for parallel subtasks (research, scrape, summarize, extract…). Features: • Mix Anthropic, OpenAI, Ollama, llama.cpp • Smart router: cheap/local first, escalate only if needed (learned +...

I built PolyMCP, a framework and runtime for exposing Python functions as MCP tools, serving them via standardized MCP servers, and orchestrating them with autonomous agents that can plan and execute multi‑step workflows.PolyMCP is more than just an MCP server: it turns existing Python code into agent‑ready tools and gives agents the ability to discover, compose, and orchestrate across multiple...

I built PolyClaw, an autonomous agent for the PolyMCP ecosystem inspired by OpenClaw.PolyClaw doesn’t just call tools. It plans, executes, adapts — and even creates MCP servers when needed.It’s designed for real-world, multi-step production workflows where an agent must: • Orchestrate multiple tools • Spin up infrastructure dynamically • Recover from failures • Deliver complete, end-to-end...

I built PolyClaw, an OpenClaw-inspired autonomous agent for the PolyMCP ecosystem.PolyClaw doesn’t just call tools. It plans, executes, adapts — and creates MCP servers when needed.It’s designed for real multi-step, production workflows where agents must orchestrate tools, spin up infrastructure, recover from errors, and deliver complete results end-to-end.⸻What PolyClaw Does • Plans complex...

I’ve been working on PolyMCP, an open-source framework designed to make it easier to build and coordinate agents using the Model Context Protocol (MCP).Most MCP tooling today focuses primarily on exposing tools. PolyMCP instead targets the agent layer: how to structure agents properly, connect them to multiple MCP servers, and make them reliable in real-world workflows.PolyMCP provides: • A...

Hi everyone,I’ve been working on PolyMCP, an open-source framework for building and orchestrating agents using the Model Context Protocol (MCP).Most of the tooling around MCP focuses on exposing tools. With PolyMCP, the focus this time is on agents: how to structure them, connect them to multiple MCP servers, and make them reliable in real workflows.PolyMCP provides: • A clean way to define...

Hi everyone,I am Vincenzo and i’m working on PolyMCP, an open-source framework that not only exposes Python functions as AI-callable MCP tools but also lets you orchestrate agents across multiple MCP servers.The idea: instead of rewriting code or wrapping every function with a special SDK, you can: 1. Publish your existing Python functions as MCP tools automatically 2. Spin up a...

PolyMCP now supports compiling Python MCP tools to WebAssembly using Pyodide.This means any Python function exposed as an MCP tool can now run directly in the browser, Node.js, or edge workers, fully sandboxed, without a Python server.Compile your tools, serve the bundle, and AI agents can call them instantly in WASM environments. Existing MCP features like input validation, error handling, and...

Hi HN,I built PolyMCP, an open-source framework around the Model Context Protocol (MCP) that lets you expose existing Python functions as AI-callable tools — without rewriting them or adopting a custom SDK.The goal is simple: If you already have working Python code, you should be able to make it accessible to LLM agents in minutes.What it doesPolyMCP introspects regular Python functions and...

I built PolyMCP, an open-source framework that lets any Python function become an MCP tool usable by AI agents — no rewrites, decorators, or custom SDKs needed.Features: • Expose Python functions as MCP tools (core framework) • PolyMCP Inspector: visual UI to browse, test, and debug servers • MCP SDK Apps: build full AI-powered apps with tools + UI resourcesReal use cases: • Turn existing APIs...

I built PolyMCP, an open-source framework around the Model Context Protocol (MCP) that lets you turn any existing Python function into an MCP tool usable by AI agents — with no rewrites, no glue code, no custom wrappers.Over the last weeks, PolyMCP has grown into a small ecosystem: • PolyMCP (core) – expose Python functions as MCP tools • PolyMCP Inspector – visual UI to explore, test, and...

I built llm-use, an open-source tool to run AI agent workflows across multiple LLMs with routing and cost optimization.Repo: https://github.com/llm-use/llm-useOpenClaw-style agents are powerful but get expensive if every step runs on a single high-end model. llm-use helps by: • using a strong model only for planning and final synthesis • running most steps on cheaper or local models • mixing...

Hi everyone,I built EasyMemory, an open-source Python library that provides a fully local-first memory layer for chatbots and agent-based systems, with no cloud dependency.Most existing agent memory solutions rely on third-party services or embeddings-only retrieval. EasyMemory is designed as a local, modular system to experiment with how agents store, structure, and retrieve information beyond...

I built llm‑use, an open‑source Python framework for orchestrating large language model workflows across local and cloud models with smart routing, cost tracking, session logs, optional web scraping, and optional MCP integration. It’s designed for agent workflows (planner + workers + synthesis) that leverage multiple LLMs without manual switching or custom glue code.ExamplesSimple local...

We’ve added first-class Ollama support to Polymcp to make running large language models easy—whether you’re working locally or deploying in the cloud.By using Ollama as a backend provider, Polymcp can coordinate MCP servers and models with minimal configuration. This lets you focus on building agents instead of wiring infrastructure.from polymcp.polyagent import PolyAgent, OllamaProvideragent =...

I built PolyMCP to make it trivial to expose existing functions as MCP tools, without rewriting logic or adding much glue code.The goal: take “normal” Python or TypeScript functions and instantly make them usable by MCP clients (Claude Desktop, agents, Ollama, etc.).Python examplefrom polymcp.polymcp_toolkit import expose_toolsdef greet(name: str) -> str: """Say hello.""" return...

I made PolyMCP so I could quickly turn normal functions (Python or TypeScript) into MCP tools without much extra work. Python example: from polymcp.polymcp_toolkit import expose_toolsdef greet(name: str) -> str: """Say hello.""" return f"Hello, {name}!"def add(a: int, b: int) -> int: """Add two numbers.""" return a + bapp = expose_tools([greet, add], title="My MCP...

I built PolyMCP, a framework that lets you transform any Python or TypeScript function into an MCP (Model Context Protocol) tool ready to be used by AI agents — no rewriting, no complex integrations.ExamplesPython function:from polymcp.polymcp_toolkit import expose_tools_httpdef add(a: int, b: int) -> int: """Add two numbers""" return a + bapp = expose_tools_http([add], title="Math...

Hi everyone, I added a skills system to PolyMCP to solve a common issue with MCP servers at scale.When the number of tools grows: • Agents burn tokens loading raw schemas • Tool discovery becomes noisy • Different agents need different subsets of tools • Orchestration logic leaks into promptsSkills are curated, structured sets of MCP tools with documentation. Agents load only the skills...

PolyMCP now lets you expose Python MCP (Model Context Protocol) tools in two ways from the same code: 1. Server-based MCP deployments (HTTP endpoints) 2. WebAssembly bundles that run directly in the browserThis means you can reuse the same Python functions for server workflows or client-side experiments without any code changes.⸻Why it matters • Plug-and-play: one Python function, multiple...