Voyage Ai Python Packages

cinematlas

Fuse within a unit, chunk across units: joint-vector search for video, photos, slides and any multimodal records on MongoDB Atlas + Voyage AI. Tested on 4 corpora with pre-stated predictions.

semcode-mcp

Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion

mcp-agent-mongodb

MongoDB Atlas-backed persistent agent memory for mcp-agent (LastMile AI): a drop-in Memory backend with MongoDB Vector Search recall.

agency-swarm-mongodb

MongoDB Atlas-backed thread/session persistence and semantic vector memory for VRSEN Agency Swarm: drop-in load/save_threads callbacks plus MongoDB Vector Search recall with Voyage 3.5.

crewai-mongodb-memory

MongoDB-backed short-term, entity, and contextual memory for CrewAI agents

pydantic-ai-mongodb-memory

MongoDB Atlas-backed memory capability for Pydantic AI: durable cross-session agent memory with Voyage 3.5 embeddings and prefiltered MongoDB Vector Search recall.

voyage-4-nano-mlx

voyage-4-nano text embeddings on Apple silicon via MLX