Directory
Published directory entries matching your search.
BambooAI is an LLM-driven data analyst tool that operates in a persistent Python kernel. It is available as a web app with Docker-isolated execution, supports user-provided model keys, and is compatible with open weights models via provider or local deployment.
BELLE, short for Be Everyone's Large Language model Engine, is an open-source Chinese conversational large language model hosted on GitHub by LianjiaTech. The project provides relevant training code and open datasets for the model.
A Towards Data Science article by Hui Wen Goh evaluating popular hallucination detectors, including G-eval, Ragas and the Trustworthy Language Model, across four public RAG datasets. Using AUROC and precision/recall, it reports how well the methods automatically flag incorrect LLM responses in retrieval-augmented generation systems.
BentoML is a unified model serving framework. It enables users to build model inference APIs, job queues, LLM applications, and multi-model pipelines. The framework supports local execution and deployment via Docker.
BigModel provides machine-learning models, research, training resources, or evaluation tools.
bitnet.cpp is the official inference framework for 1-bit LLMs such as BitNet b1.58. It provides optimized kernels for inference of 1.58-bit models on CPU and GPU, with NPU support stated as coming next. The repository includes documentation and setup scripts, and the project is released under the MIT license.
Accessible large language models via k-bit quantization for PyTorch.
Blinky is an open-source AI debugging agent for VSCode that uses LLMs to help identify and fix backend code errors. It uses the VSCode API, Language Server Protocol and print statement debugging. Users describe a bug and repro steps in a chat interface, then accept or reject the agent's changes.
Creates, rewrites or summarizes written content with language models.
BigScience Large Open-science Open-access Multilingual Language Model.
Botpress is an open-source project for building and deploying GPT/LLM agents. The repository hosts public integrations on the Botpress Hub, dev tools including a CLI, SDK and API client, example bots written with the SDK and CLI, and plugins for Botpress Studio listed as coming soon. It is released under the MIT license.
BrainSoup supports AI agents, automated workflows, orchestration, or delegated tasks.
Bread Dataset Viewer is a VS Code extension for viewing and handling large datasets. It opens JSONL, Parquet, CSV, TSV, JSON, and Arrow/Feather files by streaming and lazy-loading data, and provides Cards, Table, and Raw views. It includes 16 production LLM tokenizers from GPT, Claude, Llama, and Qwen for chat completion data.
brexhq/prompt-engineering is a GitHub repository containing Brex's Prompt Engineering Guide. It provides tips and tricks for working with Large Language Models such as OpenAI's GPT-4, with content covering the definition of large language models, an incomplete history of language models, and the concept of prompts.
Building Effective Agents is an Anthropic engineering publication that details the company's approach to developing reliable large language model (LLM) agents. It covers research on agent capabilities, safety considerations, technical frameworks, and practical guidance for developers, noting that simple, composable patterns are more effective than complex frameworks for successful agent implementations. It also references Anthropic's Claude Managed Agents.
CAJAL is a local scientific paper generator that runs entirely on the user's machine, connecting a local Ollama or LLM backend without hosted API calls. It produces seven-section papers from a research idea using an Ollama-compatible model.
Role-playing approach for LLMs and auto-agents like BabyAGI & AutoGPT.
Can I Run AI Locally detects a user's GPU or Mac and ranks open models that fit, covering LLMs, coding, image and video models. It reports VRAM requirements, speed estimates and grades for the device.
Interactive Hugging Face app that shares a machine-learning model, framework, demonstration or technical resource.
Chatbox is a desktop client for ChatGPT, Claude and other LLMs, available for Windows, Mac and Linux. It supports multiple LLM providers including OpenAI, Azure OpenAI, Claude, Google Gemini Pro, Ollama and ChatGLM-6B, and stores data locally. This repository covers the Community Edition, open-sourced under GPLv3.
An opinion article by Dan McQuillan arguing that ChatGPT and similar large language models function as a "bullshit generator." It describes LLMs as predicting missing words statistically and producing confident assertions without understanding, and frames the technology as a continuation of class war.
Project that automatically maps relationship networks by parsing public data using LLMs and visualizes it as an interactive graph.
A personal blog about AI system design and bringing AI into production. Posts cover topics including generative AI applications, agents, multimodal models, LLM research challenges, model routing, generation configurations, and machine learning systems.
Clearbit is a B2B data provider that has joined HubSpot and describes itself as the first HubSpot Native Data Provider. It enriches records for leads, contacts and accounts, scores and routes leads in real time, and reveals buying intent from anonymous website traffic. Data comes from public web data, proprietary data and LLMs.
