Search Results for "knowledge" - Page 5
Sort By:
Showing 2255 open source projects for "knowledge"
View related business solutions-
Gen AI apps are built with MongoDB AtlasMongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
-
Stigg | SaaS Monetization and Entitlements APIA monetization platform is a standalone middleware that sits between your application and your business applications, as part of the modern enterprise billing stack. Stigg unifies all the APIs and abstractions billing and platform engineers had to build and maintain in-house otherwise. Acting as your centralized source of truth, with a highly scalable and flexible entitlements management, rolling out any pricing and packaging change is now a self-service, risk-free, exercise.
-
1
Oppia
A free, online learning platform to make quality education accessible
...Oppia identifies common wrong answers and provides tailored feedback, so that students get a personalized experience. Our lessons keep students engaged through playful characters and use different strategies to solidify their knowledge. Check out our math lessons with proven results! In addition to developing the Oppia platform, the team is also developing and piloting a set of free and effective lessons on basic mathematics. These lessons are targeted at learners who lack access to educational resources. Oppia is written using Python and AngularJS, and is built on top of Google App Engine. -
2
Laravel Boost
Laravel-focused MCP server for augmenting AI powered local development
...It ships opinionated, composable guidelines tuned for popular Laravel packages, which helps keep generated code idiomatic and consistent with framework norms. The package also curates a large body of vectorized Laravel ecosystem knowledge that’s scoped to what you’ve actually installed, improving retrieval precision and response quality. It’s designed to fit naturally into existing projects, supporting current Laravel releases and modern PHP runtimes with minimal setup. Rather than trying to replace your editor or framework, Boost acts like an intelligent layer that understands Laravel’s conventions and reduces the “explain my app to the AI” friction. -
3
STORM
An LLM-powered knowledge curation system that researches topics
STORM is an open-source virtual assistant framework developed by Stanford's OVAL lab. It is designed for creating natural language interfaces and assistants that can interact with APIs, databases, and services in a modular way. -
4
ScanAPI
Automated Integration Testing and Live Documentation for your API
Given an API specification, written in YAML/JSON format, ScanAPI hits the specified endpoints, runs the test cases, and generates a detailed report of this execution - which can also be used as the API documentation itself. With almost no Python knowledge, the user can define endpoints to be hit, the expected behavior for each response and will receive a full real-time diagnostic report of the API. -
A privacy-first API that predicts global consumer preferencesThrough our API, we provide contextualized personalization and insights based on a deep understanding of consumer behavior and more than 575 million people, places, and things.
-
5
PouchDB
The Database that Syncs!
...It enables applications to store data locally while offline, and once back online it will synchronize with CouchDB and compatible servers, so your data will always be in sync. PouchDB works on various browsers, including Chrome, Firefox, Safari and more. It’s very lightweight and though some programming knowledge is required, is still very easy to learn. -
6
Qwen3
Qwen3 is the large language model series developed by Qwen team
Qwen3 is a cutting-edge large language model (LLM) series developed by the Qwen team at Alibaba Cloud. The latest updated version, Qwen3-235B-A22B-Instruct-2507, features significant improvements in instruction-following, reasoning, knowledge coverage, and long-context understanding up to 256K tokens. It delivers higher quality and more helpful text generation across multiple languages and domains, including mathematics, coding, science, and tool usage. Various quantized versions, tools/pipelines provided for inference using quantized formats (e.g. GGUF, etc.). Coverage for many languages in training and usage, alignment with human preferences in open-ended tasks, etc. -
7
Claude Skills
Public repository for Agent Skills
Claude Skills is a public repository that showcases and serves as a collection of skills — modular, reusable packages of instructions, scripts, and resources that Claude and other compatible agents can dynamically discover and load to extend their capabilities on specialized tasks. Rather than relying on handcrafted prompts every time, Skills teach an AI agent procedural knowledge and task-specific workflows so it can apply that expertise reliably, whether the task involves document creation, data analysis, design generation, or technical automation. Each Skill lives in its own directory with a SKILL.md file containing metadata and instructions, and can include supplemental scripts or assets that the agent uses to perform complex operations when relevant. -
8
Verba
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
Welcome to Verba: The Golden RAGtriever, a community-driven open-source application designed to offer an end-to-end, streamlined, and user-friendly interface for Retrieval-Augmented Generation (RAG) out of the box. In just a few easy steps, explore your datasets and extract insights with ease, either locally with Ollama and Huggingface or through LLM providers such as Anthrophic, Cohere, and OpenAI. This project is built with and for the community, please be aware that it might not be... -
9
Eigenfocus
Self-Hosted - Project Management, Planning and Time Tracker
Eigenfocus is an AI-powered personal knowledge management system that uses embeddings and semantic search to help users organize and retrieve ideas across documents. Designed for researchers and creatives, it enables deep linking between notes and supports querying based on meaning rather than keywords. -
Get to know our award-winning HR software.BambooHR is all-in-one HR software made for small and medium businesses and the people who work in them—like you. Our software makes it easy to collect, maintain, and analyze your people data, improve the way you hire talent, onboard new employees, manage compensation, and develop your company culture. It’s designed to set you free to focus on what matters most—your people.
-
10
Tipi
Runtipi is a homeserver for everyone, one command setup
...Chose any app from our app store and install it pre-configured. It just works and everything can be customized to your needs. Install your favorite self-hosted apps with a single click. No configuration, no docker knowledge required. -
11
FEniCS.jl
A scientific machine learning (SciML) wrapper for the FEniCS
...Alternatively one may use their current FEniCS installation. A low-level development API and provides some functionality to make directly dealing with the library a little bit easier, but still requires knowledge of FEniCS itself. Interfaces have been provided for the main functions and their attributes, and instructions to add further ones can be found here. A high-level API for usage with DifferentialEquations. An example can be seen in solving the heat equation with high-order adaptive time-stepping. Various gists/jupyter notebooks have been created to provide a brief overview of the overall functionality and of any differences between the pythonic FEniCS and the Julian wrapper. ... -
12
ServiceTalk
A networking framework that evolves with your application
...Netty is a great low-level networking framework, but when used for service-to-service communication it presents a few opportunities for improvement. Fully asynchronous and requires knowledge of EventLoop threading model. Executing CPU-intensive or "blocking" code requires manual thread hops. Subtle out-of-order execution of tasks when code executes both on and off the EventLoop thread. APIs are not tailored towards common application use cases (e.g. request/response, RPC, etc..) The asynchronous programming paradigm presents a barrier to entry in scenarios where vertical scalability is not a primary concern. -
13
Gemini Fullstack LangGraph Quickstart
Get started w/ building Fullstack Agents using Gemini 2.5 & LangGraph
...The backend agent dynamically generates search queries based on user input, retrieves information via the Google Search API, and performs reflective reasoning to identify knowledge gaps. It then iteratively refines its search until it produces a comprehensive, well-cited answer synthesized by the Gemini model. The repository provides both a browser-based chat interface and a command-line script (cli_research.py) for executing research queries directly. For production deployment, the backend integrates with Redis and PostgreSQL to manage persistent memory, streaming outputs, & background task coordination. -
14
AWS Agent Skills
AWS Skills for Agents
AWS Agent Skills is a repository that curates AWS-focused agent skills — capability modules that give AI assistants like Claude Code and Codex deep, practical knowledge across key Amazon Web Services domains. Instead of streaming giant documentation sets or relying on episodic web search, this project compresses AWS best practices, usage patterns, edge cases, and real-world engineering guides into pre-structured skill definitions that are token-efficient and tailored for reasoning. The skills cover critical AWS services such as IAM, Lambda, DynamoDB, S3, API Gateway, EKS, and many more, letting agents offer actionable advice on infrastructure as code, debugging, security configurations, and architectural workflows. ... -
15
History LLMs
Information hub for our project training the largest possible LLMs
History LLMs serves as the central information hub for a research project focused on training large language models exclusively on historical texts up to specified cutoff dates, essentially creating time-locked AI that speaks from within a particular era’s worldview. The History LLMs aim to be trained on massive curated datasets of time-stamped documents so that the resulting models can offer responses grounded only in the knowledge available before their cutoff, such as 1913, thereby avoiding hindsight contamination common in modern LLMs. This approach enables researchers in the humanities and social sciences to explore how people at different historical moments would have discussed world events, norms, and ideas without later developments influencing the model. ... -
16
DeiT (Data-efficient Image Transformers)
Official DeiT repository
DeiT (Data-efficient Image Transformers) shows that Vision Transformers can be trained competitively on ImageNet-1k without external data by using strong training recipes and knowledge distillation. Its key idea is a specialized distillation strategy—including a learnable “distillation token”—that lets a transformer learn effectively from a CNN or transformer teacher on modest-scale datasets. The project provides compact ViT variants (Tiny/Small/Base) that achieve excellent accuracy–throughput trade-offs, making transformers practical beyond massive pretraining regimes. ... -
17
CogDB
Micro Graph Database for Python Applications
Cog is a lightweight, embedded graph database for Go that provides a simple interface for storing and querying graph-based data structures, making it useful for knowledge representation and graph analytics. -
18
cognee
Deterministic LLMs Outputs for AI Applications and AI Agents
...Any kind of data works; unstructured text or raw media files, PDFs, tables, presentations, JSON files, and so many more. Add small or large files, or many files at once. We map out a knowledge graph from all the facts and relationships we extract from your data. Then, we establish graph topology and connect related knowledge clusters, enabling the LLM to "understand" the data. -
19
Metabase
The simplest, fastest way to share business intelligence and analytics
Metabase is the easiest way to let everyone in your company access business data and analytics, learn from it and ask questions. Even if you or your colleagues have no experience in SQL, you can easily summarize and visualize your data, share it and let your team ask questions about it. Metabase creates beautiful graphs and charts, with an easy-to-use dashboard where everyone can create, organize and share exceptionally visualized data. It supports a great number of databases, including... -
20
OpenVR SDK
API and runtime that allows access to VR hardware
OpenVR is an API and runtime that allows access to VR hardware from multiple vendors without requiring that applications have specific knowledge of the hardware they are targeting. This repository is an SDK that contains the API and samples. The runtime is under SteamVR in Tools on Steam. The OpenVR API provides a game with a way to interact with Virtual Reality displays without relying on a specific hardware vendor's SDK. It can be updated independently of the game to add support for new hardware or software updates. ... -
21
Jellyfin Android
Android Client for Jellyfin
...If you have a larger feature in mind please open an issue so we can discuss the implementation before you start. Even though the client is only a web wrapper there are still lots of improvements and bug fixes that can be accomplished with Android and Kotlin knowledge. -
22
LeakCanary
A memory leak detection library for Android
LeakCanary is a reliable memory leak detection library for Android. It effectively detects leaks and narrows down the cause of each leak through its in-depth knowledge of the internals of the Android Framework. This helps developers avoid and dramatically reduce OutOfMemoryError (OOM) crashes. A memory leak is a programming error that can cause an OutOfMemoryError crash. It’s often caused by bugs related to the lifecycle of objects, and can occur fairly often in Android applications. LeakCanary helps to find and fix those leaks during development so you never have to experience another OOM crash. -
23
RAGFlow
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data. -
24
MCP Neo4j
Model Context Protocol with Neo4j
An implementation of the Model Context Protocol with Neo4j, enabling natural language interactions with Neo4j databases and facilitating operations such as schema retrieval and Cypher query execution. -
25
Substrate
An Open-source Framework for Human Understanding, Meaning, Progress
...The goal is to enable communities to collectively build and maintain a repository of these objects so that complex systems of meaning and progress can be mapped, analyzed and improved. It is relatively ambitious in scope—seeking to help humanity organise knowledge and action around matters that matter rather than purely technical concerns. The project invites crowdsourced contribution and is structured as modular lists of object types that can interlink and form larger networks of thought. While still early, it reflects a philosophical stance: that in order to progress we must first clarify the objects and relations of meaning, belief, and decision.