sarathsp06 sourcesage

WHAT IT CONNECTS

sarathsp06 sourcesage 为 AI Agent 提供什么

• **Language Agnostic**: Works with any programming language the LLM understands
• **Knowledge Graph Storage**: Efficiently stores code entities, relationships, patterns, and style conventions
• **LLM-Driven Analysis**: Relies on the LLM to analyze code and provide insights
• **Token-Efficient Storage**: Optimizes for minimal token usage while maximizing memory capacity
• **Incremental Updates**: Updates knowledge when code changes without redundant storage
• **Fast Retrieval**: Enables quick and accurate retrieval of relevant information
• The LLM analyzes code files (in any language)
• The LLM uses MCP tools to register entities, relationships, patterns, and style conventions
• SourceSage stores this knowledge in a token-efficient graph structure
• The LLM can later query this knowledge when needed
• Open Claude for Desktop
• Go to Settings > Developer > Edit Config
• Add the following to your `claude_desktop_config.json`:
• Restart Claude for Desktop
• **register_entity**: Register a code entity in the knowledge graph
• name: Name of the entity (e.g., class name, function name)
• entity_type: Type of entity (class, function, module, etc.)
• summary: Brief description of the entity
• signature: Entity signature (optional)
• language: Programming language (optional)
• observations: List of observations about the entity (optional)
• metadata: Additional metadata (optional)
• **register_relationship**: Register a relationship between entities
• from_entity: Name of the source entity
• to_entity: Name of the target entity
• relationship_type: Type of relationship (calls, inherits, imports, etc.)
• metadata: Additional metadata (optional)
• **register_pattern**: Register a code pattern
• name: Name of the pattern
• description: Description of the pattern
• language: Programming language (optional)
• example: Example code demonstrating the pattern (optional)
• metadata: Additional metadata (optional)
• **register_style_convention**: Register a coding style convention
• name: Name of the convention
• description: Description of the convention
• language: Programming language (optional)
• examples: Example code snippets demonstrating the convention (optional)
• metadata: Additional metadata (optional)
• **add_entity_observation**: Add an observation to an entity
• entity_name: Name of the entity
• observation: Observation to add
• **query_entities**: Query entities in the knowledge graph
• entity_type: Filter by entity type (optional)
• language: Filter by programming language (optional)
• name_pattern: Filter by name pattern (regex, optional)
• limit: Maximum number of results to return (optional)
• **get_entity_details**: Get detailed information about an entity
• entity_name: Name of the entity
• **query_patterns**: Query code patterns in the knowledge graph
• language: Filter by programming language (optional)
• pattern_name: Filter by pattern name (optional)
• **query_style_conventions**: Query coding style conventions
• language: Filter by programming language (optional)
• convention_name: Filter by convention name (optional)
• **get_knowledge_statistics**: Get statistics about the knowledge graph
• **clear_knowledge**: Clear all knowledge from the graph
• **Analyze Code**: Ask Claude to analyze your code files
• **Register Entities**: Claude will use the register_entity tool to store code entities
• **Register Relationships**: Claude will use the register_relationship tool to store relationships
• **Query Knowledge**: Later, ask Claude about your codebase
• **Get Coding Patterns**: Ask Claude about coding patterns
• **Leverages LLM Understanding**: Uses the LLM's ability to understand code semantics across languages
• **Stores Semantic Knowledge**: Focuses on meaning and relationships, not just syntax
• **Is Language Agnostic**: Works with any programming language the LLM understands
• **Optimizes for Token Efficiency**: Stores knowledge in a way that minimizes token usage
• **Evolves with LLM Capabilities**: As LLMs improve, so does code understanding