A year ago I started working on a agentic RAG idea [1]. I quickly decided that I don't like the existing frameworks and started writing everything from scratch. The agentic RAG is not yet ready - but I extracted the code for dealing with function calling and published it. It is a small library ...
Thread
Stories related to "Show HN: LLMEasyTools – Tools for LLM agents (Python lib)" across the full archive.
A year ago I started working on a agentic RAG idea [1]. I quickly decided that I don't like the existing frameworks and started writing everything from scratch. The agentic RAG is not yet ready - but I extracted the code for dealing with function calling and published it. It is a small library ...
We built tools like web browser, code interpreter etc., needed for LLM agents as part of our LLMStack project. We have now moved them into a single collection as langrocks. We're using this in LLMStack and thought others might find it useful. <a href="https://github.com/tryprompt...
We built a lightweight Typescript library that turns GraphQL APIs into tool definitions for LLMs like GPT, Claude, and others. It also integrates directly with agentic frameworks like LangChain.<p>To build agents and chatbots, we found ourselves building custom tooling and APIs to pull in informatio...
Dumping a 50k-row spreadsheet into an LLM context is expensive and usually unnecessary. Most tasks need surgical access ie: find a region, profile its structure, read a filtered slice.<p>SpreadsheetMCP is a Rust MCP server with 20+ tools that let agents discover -> profile -> extract without b...
After seeing the sublime plugin (https://github.com/jisaacks/GitGutter) and getting a little jealous I decided to write my own version for vim. Still in beta status, and sadly not async - but that's on the roadmap to being fixed.
Worked on this at $dayjob, and we open sourced it yesterday.
Initial driving requirements were:
* Use as part of proof-of-concept testing with a 3rd party memcache proxy that speaks only the binary protocol
* Work well with darner/kestral queues and nosql datastores (via proxies like couchbas...
I've already posted a story about a Python news aggregator I've built with Django:
https://lobste.rs/s/bjfuar/news_aggregator_for_python_community
Now, after the story hit the front page of Hacker News and I got positive reactions from the mentions in the "What are you doing this weekend" threa...
While building my AI-powered dating app, I couldn't find a memory backend that was affordable,accessible and efficient. I built Redcache-ai to meet this need. Redcache-ai is also available as a Python package. Happy to receive feedback and answer questions.<p>Note: I am not a native English spe...
Hey HN!<p>llmio is a lightweight Python library for building LLM-based agents with ease without adding unneccessary bloat to your projects.<p>### Key Features:<p>- Lightweight: A minimalistic library that integrates seamlessly into your projects without adding unnecessary bulk.
- Type Annotation-Bas...
We’ve developed a protocol that allows AI agents to autonomously discover, integrate with, and pay for services in real time.<p>Today is a big step forward. This marks the beginning of a machine-friendly economy, where agents can interact and transact independently.
We built a tool to that makes it easy to create LLM UI automations for IOS and Android.<p>If You've ever tried to create tests that run with an LLM on mobile, probably encountered context problems due to the accessibility view being too long or just sending a screenshot to the LLM, which has lo...
Hi HN! I've been working on a new type of LLM agent framework designed with consistency and observability in mind. The agent behavior is represented as a directed graph, you can save/load agents, and the agent representation is JSON so you can store agents or send over the wire. It's ...
Hi HN<p>My name is Salman and I work on Arch GW - the intelligent gateway designed to protect, observe, and personalize LLM applications with your APIs. <a href="https://github.com/katanemo/arch">https://github.com/katanemo/arch</a><p>Our team built Envoy Prox...
I made this thing where LLM works like a tiny OS kernel - it plans tasks and runs different agents. Right now it's doing security stuff (poking at networks, checking SSL, testing APIs) with WebGoat as a playground.<p>The ultimate goal is to ask it "find vulnerabilities in XYZ" and see...
Hi HN,<p>I want to share a suite of APIs designed to make web scraping and content transformation seamless. These tools empower your agents to handle diverse scraping and formatting tasks:<p>1. Markdownify API Endpoint
Transforms web pages into clean, well-structured markdown.<p>Ideal for content mi...
Anthropic released the Model Context Protocol a couple weeks ago - <a href="https://www.anthropic.com/news/model-context-protocol" rel="nofollow">https://www.anthropic.com/news/model-context-protocol</a>. They have official sdks for python and typescript but n...
It started as a personal frustration with existing frameworks that felt too heavy or focused on flashy demos instead of real-world usability. AXAR is our attempt to keep things simple, giving developers full control while ensuring workflows are reliable and intuitive.<p>GitHub repo: <a href="https:&...
Hey HN,<p>We're John and Nadeesha. We created Inferable. [1]<p>After years of working in operationally-intensive startups, we got tired of watching our internal tools gather dust and break. We've all been there - you build a tool, it works great for a while, then the API changes and sudden...
A benchmark that you could run locally to test out LLM & AI agents' abilities to do real-world tasks