Build RAG pipelines, AI agents, and graph workflows in Python.
27 providers · 41 tools · 18 loaders · async-native · streaming-first
Why SynapseKit
Built for production Python
Designed for engineers who want full control without writing everything from scratch.
Every API is async/await first. No sync-first retrofit. Sync wrappers included for scripts and notebooks.
Token-level streaming is the default, not an afterthought. Works identically across all 27 LLM providers.
numpy and rank-bm25 only. Every other capability is behind an optional extra. Install what you need.
27 LLM providers and 5 vector stores behind the same API. Swap providers without rewriting a single line.
CostTracker and BudgetGuard give you full cost visibility and circuit-breaker budget limits — no SaaS required.
`synapsekit serve my_app:rag` wraps any RAG pipeline, agent, or graph in a production FastAPI app instantly.
RAG pipelines, agents, and graph nodes are interchangeable. Wrap anything as anything.
No hidden chains, no callbacks, no global state. Every step is plain Python you can read and override.
Explore the docs
Everything you need
From a 3-line quickstart to production graph workflows.
Retrieval-augmented generation with streaming, BM25 reranking, conversation memory, and token tracing.
Read docs →ReAct loop for any LLM. Native function calling for OpenAI, Anthropic, Gemini, and Mistral. 41 built-in tools, fully extensible.
Read docs →DAG-based async pipelines. Parallel execution, conditional routing, typed state, fan-out/fan-in, SSE streaming, event callbacks, human-in-the-loop.
Read docs →OpenAI, Anthropic, Ollama, Gemini, Cohere, Mistral, Bedrock, Azure, Groq, DeepSeek, OpenRouter, Together, Fireworks, SambaNova and more — 27 providers behind one interface.
Read docs →`synapsekit serve` deploys any pipeline in one command. `synapsekit test` runs eval cases with scoring thresholds in CI.
Read docs →CostTracker, BudgetGuard, TokenTracer, OpenTelemetry export, and DistributedTracer — full visibility without a SaaS subscription.
Read docs →InMemory, ChromaDB, FAISS, Qdrant, Pinecone. One interface for all backends. Swap without rewriting.
Read docs →Complete reference for every public class and method in SynapseKit.
Read docs →