Emrea 

Zero-dependency shared types for the Agency AI Toolkit: Dataset and IColumnMetadata used across SQL runners, the RAG formatter, and downstream LLM consumers.

IVectorStore, Query, and SearchHit<T> abstractions for the Agency AI Toolkit. Provider-agnostic contract for nearest-neighbour search across pgvector, SQLite, and future backends.

IEmbeddingGenerator interface and shared embedding abstractions for the Agency AI Toolkit. Implementation-agnostic contract consumed by vector stores, SQL runners, and ingestion pipelines.

IModelProvider interface and shared LLM tool/message types for the Agency AI Toolkit. The single contract that Claude, OpenAI, and any future provider implement.

Anthropic Claude IModelProvider implementation for the Agency AI Toolkit, built on the Stainless Anthropic SDK with full OpenTelemetry traces and token-usage metrics.

OpenAI IModelProvider implementation for the Agency AI Toolkit, built on the official .NET OpenAI SDK with full OpenTelemetry traces and token-usage metrics. Works with Azure OpenAI and OpenAI-compatible... More information

SqlRunnerBase abstract class for the Agency AI Toolkit: shared OpenTelemetry instrumentation and execution skeleton reused by every concrete SQL runner.

Renders an Agency Dataset as a Markdown table for injection into LLM context windows. The minimal RAG formatting step between SQL retrieval and chat completion.

Core agentic loop for the Agency AI Toolkit: Agent, ChatSession, Context composition, ToolRegistry, and StopConditions for multi-turn LLM agents with tool calling.

Common types, interfaces, and options for the Agency long-term memory system.

PostgreSQL raw-SQL runner for the Agency AI Toolkit with a built-in vectorize() macro that inlines pgvector literals from natural-language strings via IEmbeddingGenerator.

SQLite raw-SQL runner for the Agency AI Toolkit with a built-in vectorize() macro that inlines embedding literals from natural-language strings via IEmbeddingGenerator.

Shared configuration layer and ${Section:Key} placeholder resolution for the Agency AI Toolkit.

Ingestion pipeline abstractions and DefaultIngestionPipeline<T> for the Agency AI Toolkit. Compose loaders, chunkers, embedders, and stores into a single load-and-index workflow.

OpenAI-compatible IEmbeddingGenerator implementation with full OpenTelemetry instrumentation. Works with OpenAI, Azure OpenAI, and OpenAI-compatible endpoints such as LM Studio.

Retrieval engine for the Agency long-term memory system. Implements the gated vector search, composite ranking, and context injection for the agent hot path.

PostgreSQL + pgvector implementation of IMemoryStore for the Agency long-term memory system.

Consolidator sub-agent background service for the Agency long-term memory system: merges, updates, and deletes memory records after distillation.

IKVStore, Query, SearchHit<T>, and JSON metadata helpers for the Agency AI Toolkit. Provider-agnostic key-value contract used as the metadata layer alongside vector search.

Semantic Kernel TextChunker-based text splitter for the Agency ingestion pipeline. Token-aware chunking with configurable overlap suitable for embedding-and-retrieval workflows.