synapsekit 0.6.4

Async-native Python framework for building production-grade LLM applications. Streaming-first, 2 dependencies, fully transparent.

Documentation · Quickstart · API Reference · Changelog · Report a Bug

---

SynapseKit is a Python framework for building production-grade LLM applications. Built async-native and streaming-first from day one — not retrofitted. Two hard dependencies. Every abstraction is composable, transparent, and replaceable: plain Python you can read, debug, and extend. No magic. No hidden chains. No lock-in.

---

⚡ Async-native Every API is async/await first. Sync wrappers for scripts and notebooks. No event loop surprises.	🌊 Streaming-first Token-level streaming is the default, not an afterthought. Works across all providers.	🪶 Minimal footprint 2 hard dependencies: numpy + rank-bm25. Everything else is optional. Install only what you use.
🔌 One interface 13 LLM providers and 5 vector stores behind the same API. Swap without rewriting.	🧩 Composable RAG pipelines, agents, and graph nodes are interchangeable. Wrap anything as anything.	🔍 Transparent No hidden chains. Every step is plain Python you can read and override.

---

Who is it for?

SynapseKit is for Python developers who want to ship LLM features without fighting their framework.

• Backend engineers adding AI features to existing Python services
• ML engineers building RAG or agent pipelines who need full control over retrieval, prompting, and tool use
• Researchers and hackers who want a clean, readable codebase they can understand and extend
• Teams who need something they can actually debug and maintain in production

---

What it covers

🗂 RAG Pipelines Retrieval-augmented generation with streaming, BM25 reranking, conversation memory, and token tracing. Load from PDFs, URLs, CSVs, HTML, directories, and more.	🤖 Agents ReAct loop (any LLM) and native function calling (OpenAI / Anthropic / Gemini / Mistral). 16 built-in tools including calculator, Python REPL, web search, SQL, HTTP, summarization, sentiment analysis, and translation. Fully extensible.
🔀 Graph Workflows DAG-based async pipelines. Nodes run in waves — parallel nodes execute concurrently. Conditional routing, typed state with reducers, fan-out/fan-in, SSE streaming, event callbacks, human-in-the-loop, checkpointing, and Mermaid export.	🧠 LLM Providers OpenAI, Anthropic, Ollama, Gemini, Cohere, Mistral, Bedrock, Azure OpenAI, Groq, DeepSeek, OpenRouter, Together, Fireworks — all behind one interface. Auto-detected from the model name. Swap without rewriting.
🗄 Vector Stores InMemory (built-in, .npz persistence), ChromaDB, FAISS, Qdrant, Pinecone. One interface for all backends.	🔧 Utilities Output parsers (JSON, Pydantic, List), prompt templates (standard, chat, few-shot), token tracing with cost estimation.

---

Install

pip

pip install synapsekit[openai]       # OpenAI
pip install synapsekit[anthropic]    # Anthropic
pip install synapsekit[ollama]       # Ollama (local)
pip install synapsekit[all]          # Everything

uv

uv add synapsekit[openai]
uv add synapsekit[all]

Poetry

poetry add synapsekit[openai]
poetry add "synapsekit[all]"

Full installation options → docs

---

Documentation

Everything you need to get started and go deep is in the docs.

🚀 Quickstart	Up and running in 5 minutes
🗂 RAG	Pipelines, loaders, retrieval, vector stores
🤖 Agents	ReAct, function calling, tools, executor
🔀 Graph Workflows	DAG pipelines, conditional routing, parallel execution
🧠 LLM Providers	All 13 providers with examples
📖 API Reference	Full class and method reference

---

Development

git clone https://github.com/SynapseKit/SynapseKit
cd SynapseKit
uv sync --group dev
uv run pytest tests/ -q

---

Contributing

Contributions are welcome — bug reports, documentation fixes, new providers, new features.

Read CONTRIBUTING.md to get started. Look for issues tagged good first issue if you're new.

---

Community

• 💬 Discussions — ask questions, share ideas
• 🐛 Bug reports
• 💡 Feature requests
• 🔒 Security policy

---

License

MIT