{"name":"Open Index: A Deterministic Memory Layer for Your AI Agents","description":"Open Index is a powerful tool for building domain-specific, accurate, and structured data that AI agents can effectively operate on. It enables the creation of a \"brain,\" a searchable and continuously improving context graph tailored to any domain. This system ensures agents have access to reliable, up-to-date information, enhancing their capabilities and decision-making processes.","github":"https://github.com/DrDroidLab/open-index","url":"https://osrepos.com/repo/drdroidlab-open-index","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/drdroidlab-open-index","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/drdroidlab-open-index.md","json":"https://osrepos.com/repo/drdroidlab-open-index.json","topics":["AI Agents","Knowledge Graph","Agent Memory","AI Infrastructure","Context Engineering","Python","Data Management"],"keywords":["AI Agents","Knowledge Graph","Agent Memory","AI Infrastructure","Context Engineering","Python","Data Management"],"stars":null,"summary":"Open Index is a powerful tool for building domain-specific, accurate, and structured data that AI agents can effectively operate on. It enables the creation of a \"brain,\" a searchable and continuously improving context graph tailored to any domain. This system ensures agents have access to reliable, up-to-date information, enhancing their capabilities and decision-making processes.","content":"## Introduction\n\nOpen Index is a powerful tool designed for building domain-specific, accurate, and structured data that AI agents can effectively operate on. It also ensures this data remains correct as circumstances evolve. At its core, Open Index helps you construct a \"brain,\" a searchable and continuously improving context graph tailored to your specific domain. This brain is domain-agnostic, capable of modeling diverse scenarios, from a support organization to a sales pipeline or infrastructure.\n\nThe brain is built upon four fundamental primitives:\n*   **doc_type**: A concept you wish to track and maintain, such as `service`, `customer`, or `issue`.\n*   **doc_schema**: Defines the fields stored for a given `doc_type`.\n*   **entity**: An instance of a `doc_type`, stored according to its schema. Entities can link to others via `related_to` and `relationship_edge_meaning`.\n*   **connector**: An optional source for extracting entities, for example, an MCP server.\n\n## Why Use Open Index and Key Benefits\n\nOpen Index provides a robust context layer for domain-specialized agents, enabling them to access structured knowledge and maintain it effectively. Its MCP server publishes dynamic, brain-specific instructions, allowing agents to navigate the domain before tool calls. Agents can read context using `search_brain()` and `get_entity()`, and write back learnings via `put_entity()` or `create_doc_type()`, fostering a continuously improving loop.\n\nKey benefits include:\n*   **Structured Context for AI Agents**: Provides a reliable, validated way for agents to interact with domain knowledge.\n*   **Domain Agnostic Flexibility**: Model any domain, from customer support to infrastructure, with custom concepts and relationships.\n*   **Continuous Improvement**: Agents can update and refine the knowledge graph, ensuring data accuracy over time.\n*   **Powerful Search and Exploration**: Features like per-field boosting, semantic search, and a UI explorer with map and analytics views.\n*   **Flexible Storage Options**: Supports SQLite for local development and OpenSearch for scalable, multi-writer production environments.\n*   **Granular Data Control**: Distinguish between `file`-backed (git-tracked) and `index`-backed (DB-owned) entities.\n*   **Easy Deployment**: Options for local setup, Docker, and HTTP serving for cloud agents.\n\n## Installation\n\nTo get started with Open Index, you can install it using pip. The `.[all]` extra includes the core functionality, the explorer UI, and the MCP server.\n\nbash\npip install -e '.[all]'\n\n\n## Examples\n\nOpen Index ships with several runnable examples to help you understand its capabilities. You can try the bundled `support-brain`, `infra-brain`, or `personal-brain`.\n\nTo try an example:\n\nbash\nopen-index index --brain examples/support-brain\nopen-index ui    --brain examples/support-brain      # open the Map tab, pick an anchor\n\n\nAlternatively, you can start your own brain from scratch:\n\nbash\nopen-index init my-brain\nopen-index add-doc-type customer --brain my-brain\n# ...add entities under my-brain/entities/**/*.json...\nopen-index index --brain my-brain\nopen-index ui    --brain my-brain\n\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/DrDroidLab/open-index](https://github.com/DrDroidLab/open-index){:target=\"_blank\"}\n*   **Join the Community on Discord**: [https://discord.gg/AQ3tusPtZn](https://discord.gg/AQ3tusPtZn){:target=\"_blank\"}","metrics":{"detailViews":2,"githubClicks":1},"dates":{"published":null,"modified":"2026-09-16T15:05:08.000Z"}}