🦞🌯 Lobster Roll

Thread

Show HN: LLMEasyTools – Tools for LLM agents (Python lib) (github.com)
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 ...

Stories related to "Show HN: LLMEasyTools – Tools for LLM agents (Python lib)" across the full archive.

Show HN: LLMEasyTools – Tools for LLM agents (Python lib) (github.com)
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 ...
Show HN: Langrocks – tools like computer access, browser etc., for LLM agents (github.com)
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&#x27;re using this in LLMStack and thought others might find it useful. <a href="https:&#x2F;&#x2F;github.com&#x2F;tryprompt...
Show HN: Acorn.js – Turn GraphQL APIs into Tools for LLMs and Agents (github.com)
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...
Show HN: SpreadsheetMCP – Token-efficient Excel tools for LLM agents (Rust) (github.com)
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 -&gt; profile -&gt; extract without b...
[Show lobste.rs] vim plugin to view git/hg add/mod/del in gutter (bitbucket.org)
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.
show lobste.rs: pyermc - python memcache library (yet another) (github.com)
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...
Show Lobsters: Game where you write Python robots to fight other players (robotgame.org)
chaintools are unix like tools but with a pythonic syntax (github.com)
Show: I've built a social news aggregator for the Python community and it took off (news.python.sc)
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...
python-coverage.el: show python coverage information directly in emacs (github.com)
LLM now provides tools for working with embeddings (simonwillison.net)
MemGPT: Create LLM agents with long-term memory and custom tools (github.com)
Show HN: Redcache_AI – open-source memory framework for LLMs and Agents (github.com)
While building my AI-powered dating app, I couldn&#x27;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...
Show HN: llmio - Lightweight Python Library for Building LLM Agents (github.com)
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...
Show HN: PHP Library for Working with LLM, Agents and RAG (github.com)
Show HN: AI agents integrating tools at runtime (twitter.com)
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.
Show HN: Phidata – Build AI Agents with memory, knowledge, tools and reasoning (github.com)
Show HN: CogniSim – Interaction utilites for crossplatform LLM agents (github.com)
We built a tool to that makes it easy to create LLM UI automations for IOS and Android.<p>If You&#x27;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...
Show HN: Langur – consistent, observable LLM agents (github.com)
Hi HN! I&#x27;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&#x2F;load agents, and the agent representation is JSON so you can store agents or send over the wire. It&#x27;s ...
Show HN: Add human approval layer to monitor and guide LLM agents in production (github.com)
Show HN: Arch GW – Distributed gateway for agents, engineered with small LLMs (docs.archgw.com)
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:&#x2F;&#x2F;github.com&#x2F;katanemo&#x2F;arch">https:&#x2F;&#x2F;github.com&#x2F;katanemo&#x2F;arch</a><p>Our team built Envoy Prox...
Show HN: LLM driven OS to execute network security exploration agents (github.com)
I made this thing where LLM works like a tiny OS kernel - it plans tasks and runs different agents. Right now it&#x27;s doing security stuff (poking at networks, checking SSL, testing APIs) with WebGoat as a playground.<p>The ultimate goal is to ask it &quot;find vulnerabilities in XYZ&quot; and see...
Show HN: AI tools search engine optimized for AI agents-Anthropic's Computer Use (raghut.com)
Show HN: Equip Your Agents with Powerful Web Scraping Tools (scrapegraphai.com)
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...
Show HN: mcp-golang – Build custom tools for LLMs in go (github.com)
Anthropic released the Model Context Protocol a couple weeks ago - <a href="https:&#x2F;&#x2F;www.anthropic.com&#x2F;news&#x2F;model-context-protocol" rel="nofollow">https:&#x2F;&#x2F;www.anthropic.com&#x2F;news&#x2F;model-context-protocol</a>. They have official sdks for python and typescript but n...
Show HN: AXAR AI – a minimalistic TypeScript framework for building LLM agents (github.com)
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:&...
Show HN: Open-source conversational AI agents for internal tools (github.com)
Hey HN,<p>We&#x27;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&#x27;ve all been there - you build a tool, it works great for a while, then the API changes and sudden...
Show HN: Benchmarking LLM Agents on Consequential Real World Tasks (the-agent-company.com)
A benchmark that you could run locally to test out LLM &amp; AI agents&#x27; abilities to do real-world tasks
Show HN: Offeryn – Build Tools for LLMs in Rust, with Model Context Protocol (github.com)
Introduction to MITRE ATT&CK utilization tools by multiple LLM agents and RAG (speakerdeck.com)