{"id":28274594,"url":"https://github.com/ngmachado/neucore","last_synced_at":"2025-06-30T20:34:15.051Z","repository":{"id":288906158,"uuid":"964839260","full_name":"ngmachado/neucore","owner":"ngmachado","description":"Modern TypeScript framework for building context-aware AI applications with advanced reasoning, memory management, and provider-agnostic design. NeuCore provides essential building blocks for sophisticated AI systems through modular, extensible architecture","archived":false,"fork":false,"pushed_at":"2025-04-26T13:50:45.000Z","size":1278,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-21T02:11:39.443Z","etag":null,"topics":["ai-framework","chain-of-thought","intent-system","reasoning-systems"],"latest_commit_sha":null,"homepage":"https://publish.obsidian.md/axe/projects/NeuroCore","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ngmachado.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-04-11T21:57:50.000Z","updated_at":"2025-04-21T09:02:55.000Z","dependencies_parsed_at":"2025-04-21T10:48:02.303Z","dependency_job_id":null,"html_url":"https://github.com/ngmachado/neucore","commit_stats":null,"previous_names":["ngmachado/neucore"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ngmachado/neucore","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ngmachado%2Fneucore","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ngmachado%2Fneucore/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ngmachado%2Fneucore/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ngmachado%2Fneucore/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ngmachado","download_url":"https://codeload.github.com/ngmachado/neucore/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ngmachado%2Fneucore/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262846564,"owners_count":23373834,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-framework","chain-of-thought","intent-system","reasoning-systems"],"created_at":"2025-05-21T02:11:33.009Z","updated_at":"2025-06-30T20:34:14.998Z","avatar_url":"https://github.com/ngmachado.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# neucore\n\nModern AI framework for building context-aware AI applications.\n\n\u003e **Early Development Notice**: neucore is currently in early development (v0.0.1). APIs may change significantly between versions. See [Component Status](docs/COMPONENT-STATUS.md) for implementation details.\n\n## Overview\n\nneucore provides the essential building blocks for creating sophisticated AI applications with memory, context management, reasoning capabilities, and plugin-based extensibility. It's designed to be modular, flexible, and performant.\n\n## Key Features\n\n- **Memory Management**: Store and retrieve conversations, documents, and other data with vector embeddings for semantic search\n- **Context Building**: Intelligently select relevant context for LLM prompts\n- **Reasoning System**: Structured approaches to complex reasoning (Chain of Thought, etc.)\n- **Template System**: Dynamic content generation with variable substitution and formatting\n- **Action System**: Define and execute concrete operations with validation\n- **Character Traits System**: Define and apply consistent AI personalities and styles\n- **Model Context Protocol (MCP)**: Structured approach to AI interactions\n- **Provider Adapters**: Support for multiple AI providers (currently Anthropic, with OpenAI planned)\n- **RAG System**: Enhance responses with knowledge retrieval and processing\n- **Goal Management**: Track and manage objectives for agents and users\n\n## Installation\n\n```bash\nnpm install neucore\n```\n\n## Quick Start\n\n```typescript\nimport { \n  createProviderFactory,\n  createContextBuilder,\n  ChainOfThoughtReasoner,\n  ReasoningMethod\n} from 'neucore';\n\n// Initialize provider\nconst providerFactory = createProviderFactory({\n  anthropic: {\n    apiKey: \"your-api-key\",\n    defaultModel: \"claude-3-sonnet-20240229\"\n  }\n});\nconst modelProvider = providerFactory.getProvider();\n\n// Create a reasoning system\nconst reasoner = new ChainOfThoughtReasoner(modelProvider, {\n  method: ReasoningMethod.CHAIN_OF_THOUGHT\n});\n\n// Use reasoning to solve a complex problem\nconst result = await reasoner.reason(\"How can I optimize database queries to improve application performance?\", {\n  methodOptions: {\n    stepCount: 5,\n    enableTaskPlanning: true\n  }\n});\n\nconsole.log(result.conclusion);\n```\n\n## Component Status\n\nSee [Component Status](docs/COMPONENT-STATUS.md) for the current implementation status of each component.\n\n## Model Context Protocol (MCP)\n\nThe Model Context Protocol provides a structured intent-based system for AI interactions, inspired by mature application design patterns.\n\n### Key Features\n\n- **Intent System**: Route requests to appropriate handlers based on actions and categories\n- **Provider Abstraction**: Decouple client code from specific AI provider implementations\n- **Flexible Routing**: Support for targeted intents and broadcasts to multiple handlers\n- **Extensible Design**: Add new handlers and actions without modifying client code\n\n### Example Usage\n\n```typescript\n// Create an intent router\nconst router = new IntentRouter();\n\n// Register handler(s)\nawait router.registerHandler(new AnthropicHandler(apiKey));\n\n// Create and send an intent\nconst intent = new Intent('anthropic:generate', {\n  prompt: 'Write a haiku about programming'\n});\nintent.putExtra('model', 'claude-3-haiku-20240307');\n\n// Send the intent to get results\nconst results = await router.sendIntent(intent, {\n  userId: 'user123'\n});\n```\n\n## Documentation\n\n- [Documentation Index](docs/README.md) - Complete list of all documentation\n- [System Documentation](docs/SYSTEM-DOCUMENTATION.md) - Comprehensive overview of all major subsystems\n- [Reasoning System](docs/REASONING.md) - Documentation for the reasoning system\n- [Validation System](docs/VALIDATION.md) - Utilities for runtime type checking and validation\n- [Future Reasoning Methods](docs/README-future-methods.md) - Planned reasoning implementations\n- [Reasoner Implementation Guide](docs/IMPLEMENTATION-GUIDE.md) - Guide for implementing new reasoners\n- [Mock Migration Guide](docs/MOCK-MIGRATION.md) - Guide for proper dependency injection\n\n## Directory Structure\n\n```\nneucore/\n├── docs/                     # Documentation files\n│   ├── SYSTEM-DOCUMENTATION.md # System overview\n│   ├── COMPONENT-STATUS.md   # Implementation status\n│   ├── REASONING.md          # Reasoning system docs\n│   ├── CHARACTER.md          # Character system docs\n│   └── ...                   # Other documentation\n├── src/\n│   ├── core/                  # Core framework functionality\n│   │   ├── memory/            # Memory management\n│   │   ├── context/           # Context building\n│   │   ├── reasoning/         # Reasoning system\n│   │   ├── character/         # Character traits system \n│   │   ├── actions/           # Action system \n│   │   ├── templates/         # Template system\n│   │   ├── rag/               # Retrieval Augmented Generation\n│   │   ├── goals/             # Goal management\n│   │   ├── providers/         # Model providers\n│   │   ├── relationships/     # Entity relationships\n│   │   ├── database/          # Database abstraction\n│   │   ├── validation/        # Data validation\n│   │   ├── logging/           # Logging system\n│   │   ├── config/            # Configuration\n│   │   └── errors/            # Error handling\n│   ├── mcp/                   # Model Context Protocol\n│   ├── test/                  # Testing utilities and mocks\n│   ├── types/                 # Type definitions\n│   └── index.ts               # Main exports\n```\n\n## Testing\n\n```bash\n# Run tests\nnpm test\n\n# Run tests with coverage\nnpm run test:coverage\n\n# Run linter\nnpm run lint\n```\n\n## Roadmap\n\n- Complete OpenAI provider implementation\n- Implement additional reasoning methods (Tree of Thought, ReAct, etc.)\n- Add comprehensive validation across all components\n- Enhance error handling and reporting\n- Add streaming support to all providers\n- Implement database adapters for popular databases\n- Create higher-level agent abstractions\n\n\n## Research\n\n[NeuroCore](https://publish.obsidian.md/axe/projects/NeuroCore)\n\n## Contributing\n\nAs this project is in early development, please contact the maintainers before making significant contributions.\n\n## License\n\nMIT \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fngmachado%2Fneucore","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fngmachado%2Fneucore","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fngmachado%2Fneucore/lists"}