A bio-inspired cognitive memory engine — a new paradigm for Graph RAG.

Koog is a JVM (Java and Kotlin) framework for building predictable, fault-tolerant and enterprise-ready AI agents across all platforms – from backend services to Android and iOS, JVM, and even in-browser environments. Koog is based on our AI products expertise and provides proven solutions for complex LLM and AI problems

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Transparent and Efficient Financial Analysis

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tests, process mining models, Markov chain simulation

Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch, Alfresco, Nuxeo DBs. 14 data sources (10 auto-sync), KG auto-building, Ontologies, LLMs, Docling, LlamaParse, LiteParse, GraphRAG, RAG, Hybrid Search, AI Chat. TypeScript React, Vue, Angular frontends, REST, MCP Server. Options: Langflow, CocoIndex

[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.

OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.

Deploy production-ready AI services in minutes. One YAML file for agents, RAG pipelines, and MCP servers — run anywhere. Inspired by docker-compose.

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

Compound Engineering Framework for Alpha Feature Research in Quant Finance

Open-source AI assistant ecosystem with MCP integrations, multimodal workflows, IoT support, and cross-platform voice interaction.

Open Brain — The infrastructure layer for your thinking. One database, one AI gateway, one chat channel — any AI plugs in. No middleware, no SaaS.

Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

Unofficial Go SDK for Claude Code CLI integration. See the Claude Agent SDK documentation for more information. This project has been renamed from claude-code-sdk-go.

A lightweight, lightning-fast, in-process vector database

Solid Tumor Associative Modeling in Pathology

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

Build autonomous AI agents in Python.

The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and more.