Directory
Published directory entries matching your search.
Haystack is an open-source AI orchestration framework for building production-ready LLM applications in Python. It provides modular pipelines and agent workflows with explicit control over retrieval, routing, memory and generation, and is intended for RAG systems, multimodal applications, semantic search, question answering and autonomous agents. Installation is available via pip.
Kaito is the Kubernetes AI Toolchain Operator, an operator suite that automates LLM inference, fine-tuning and RAG engine deployment in a Kubernetes cluster. It simplifies the CRD API and provides optimized preset configurations for inference engine scheduling parameters. Workspaces are the basic CRD for managing inference and tuning workloads, and all vLLM-supported models can be run.
Kiln AI is a platform and open-source library for building, evaluating, and optimizing AI systems. It offers tools for working with retrieval-augmented generation, AI agents, synthetic data, model fine-tuning, and prompt optimization, with a free downloadable application available for macOS, Windows, and Linux.
LLM App is an open-source project providing ready-to-run cloud templates for retrieval-augmented generation (RAG), AI pipelines and enterprise search with live data. It is Docker-friendly and designed to stay synchronized with data sources including Sharepoint, Google Drive, S3, Kafka, PostgreSQL and real-time data APIs, hosted by pathwaycom on GitHub.
This is a blog post from Confident AI that serves as a guide to LLM evaluation metrics. It covers retrieval-augmented generation (RAG) metrics such as faithfulness and answer relevancy, agent metrics, LLM-as-a-judge approaches, and includes working DeepEval code examples.
LocalGPT is an on-premise document intelligence platform that lets users chat with their documents on their local device using GPT models. It supports PDF, DOCX, HTML, Markdown, and TXT files and combines dense vector search with LanceDB full-text search and a cross-encoder reranker. It runs with a plain Python RAG core and offers generation models via Ollama.
PraisonAI is an open-source project hosted on GitHub under the MervinPraison/PraisonAI repository. It enables the deployment of autonomous, self-improving AI agents capable of researching, planning, coding, and executing tasks. The tool includes built-in memory and retrieval-augmented generation (RAG) capabilities, supports over 100 large language models, and can be deployed with 5 lines of code.
Neurolink is described as the pipe layer of an AI nervous system, providing one interface connecting provider neurons to an application across three inference types: generate, stream, and a calibrated decide via TypeSafe Jev. It lists MCP-native, voice, RAG, memory and file processor features and powers several Juspay projects.
Onyx is an open-source AI platform that connects to applications to index and surface knowledge, with self-hosted deployment options. It provides agentic RAG search, deep research reports, custom agents, web search, a secure sandbox for code execution, artifacts, and voice mode. It works with major LLMs.
A write-up on practical patterns for integrating large language models into systems and products, drawing on academic research, industry resources and practitioner know-how. It covers seven key patterns, including evals, RAG, fine-tuning, caching, guardrails, defensive UX and collecting user feedback.
PrivateGPT is an open-source API layer for building private AI applications on local models, following the Claude API model. It provides a messages API, file and artifact ingestion, retrieval with citations and agentic RAG, built-in and custom tools, MCP connectors, structured database and CSV access, and embeddings. It connects to any OpenAI-compatible inference server and does not run models itself.
Promptfoo is a tool for testing AI prompts, agents and RAG systems. It supports red teaming, penetration testing and vulnerability scanning for AI, enables performance comparison across models including GPT, Claude, Gemini and DeepSeek, uses simple declarative configuration, and integrates with command line and CI/CD workflows.
Promptly is a no-code generative AI platform built for enterprise use. It allows users to build generative AI applications, AI agents and chatbots without coding experience, and supports features including model chaining, RAG pipeline creation, custom data integration, and multi-language translation. The platform offers pre-built templates for common use cases.
PyGPT is a free, open-source desktop AI assistant compatible with Windows, Linux and macOS operating systems. It supports both cloud-based and local AI models, and offers features including AI chat, multi-agent workflows, RAG-powered knowledge retrieval from user files, skills and plugin support, Python and MCP automation, and voice, vision and content generation capabilities.
Relevance AI is a low/no-code platform for building AI agents and multi-agent teams that autonomously complete tasks. Agents can be built with a no-code builder, pre-built templates or by cloning from a marketplace. The platform also includes a chat interface, a RAG-based knowledge feature, a no-code workflow builder for integrations and a marketplace.
Twig offers Sera, an AI receptionist that answers, qualifies and books calls, texts and web chats. Plans start at $49 per month for the Starter tier, and every plan includes a 15-day free trial with voice. Twig also publishes developer documentation covering its API, MCP server, SDKs, data connectors, RAG strategies and agent configuration.
Vectara-agentic is a Python library hosted on GitHub for creating AI assistants with Vectara using Agentic RAG. The repository provides an overview, key features, and example AI assistants to help developers integrate the technology.
VeritasGraph is an open-source knowledge graph and GraphRAG framework. It supports multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over user data, using nodes, edges, RDF, and linked data. The project runs locally or in the cloud.
