EpicenterHQ/epicenter
Epicenter
Epicenter is a local-first knowledge management system and data orchestrator designed to structure information generated by large language models into validated schemas. It functions as a storage architecture that persists application data in human-readable files and databases to ensure user ownership and portability.
The system distinguishes itself by projecting language model outputs into structured, schema-validated tables and utilizing conflict-free replicated data types to synchronize application state across multiple devices without a central server. This allows for offline access and consistent state management while maintaining a decoupled content model where machine-generated outputs remain separate from user-curated folders.
The platform covers a broad range of capabilities including API integration with local or remote text models, the definition of typed data schemas for consistency, and file-system-based persistence for long-term data portability.
Features
- LLM Orchestration - Orchestrates LLM interactions to project model outputs into structured, schema-validated tables for knowledge management.
- Local-First Architectures - Employs a local-first architecture that prioritizes local data storage and offline-first functionality.
- Knowledge Management Systems - Provides a system for organizing and structuring data generated by large language models into validated schemas and local files.
- LLM Orchestrators - Connects to large language models and orchestrates the projection of their outputs into structured, schema-validated tables.
- Model API Integrations - Provides connectors to interact with local or remote language model services via standard API protocols.
- Application State Syncing - Synchronizes application configuration and state across devices while allowing for offline edits.
- Application State Synchronization - Uses CRDTs to synchronize account-level preferences and application metadata across multiple devices.
- Local File Storage - Persists application data and documents directly to local disk storage to enable direct ownership and querying.
- Data Portability - Persists application data in human-readable files and portable databases to ensure long-term user ownership and data portability.
- LLM Structured Data Generators - Projects language model outputs into structured, schema-validated tables for advanced knowledge management.
- File-Based Storage Systems - Persists application data in plain text files and portable databases within local directories for direct user ownership.
- Local Data Stores - Provides a local data store for managing persistent information directly on the user device.
- Local-First Persistence - Ensures full user data ownership by storing all application data directly on the local file system.
- Local-First Storage - Employs a local-first storage architecture that prioritizes local persistence for offline access and user data sovereignty.
- Local-First Synchronization - Implements a local-first synchronization architecture that prioritizes offline access with conflict-free merging.
- CRDT State Synchronization Engines - Implements a synchronization engine using conflict-free replicated data types to maintain consistent state across devices.
- File-Based Project Storage - Stores project state as plain-text files and portable databases to ensure long-term data portability.
- LLM Model Integrations - Integrates large language models into a structured data environment for generating and processing text.
- Personal Knowledge Management - Provides a personal knowledge management system for capturing and organizing information in local folders.
- Curated Content Management - Manages user-owned content by separating machine-generated outputs from curated folders for manual versioning.
- LLM Output Projections - Projects large language model outputs into structured tables using validated data definitions for consistent storage.
- Storage Schema Validations - Enforces structured data rules and schema consistency across local storage and synchronized state updates.
- Data Validation Schemas - Allows for the definition of typed data schemas to ensure consistency across local storage and synchronized states.
- Content Separation - Separates machine-generated outputs from user-curated folders to allow manual editing and versioning via external tools.
- Voice Dictation - Multi-provider speech-to-text with AI formatting capabilities.
- Voice To Text - Listed in the “Voice To Text” section of the Awesome Mac awesome list.
- Audio and Video - Speech-to-text transcription with AI processing.
