Build production LLM apps with 2 dependencies.
Async-native RAG, Agents, and Graph Workflows — no magic, no SaaS, no bloat.
Website · Docs · Quickstart · Discord · Contributing
from synapsekit import RAG
rag = RAG(model="gpt-4o-mini", api_key="sk-...")
rag.add("Your document text here")
async for token in rag.stream("Summarise this."):
print(token, end="", flush=True)Streaming RAG in 4 lines.
Files & Docs
Cloud Storage
Databases
Productivity & CRM
Communication & Social
Web & Research
Media
| Repo | What it is |
|---|---|
| SynapseKit/SynapseKit | The core library — RAG, agents, graph workflows, 33 LLM providers |
| SynapseKit/synapsekit-docs | Documentation site (Docusaurus), live at synapsekit.github.io/synapsekit-docs |
| SynapseKit/synapsekit-ui | Marketing website, live at synapse-kit.com |
| SynapseKit/evalci | Hosted eval runner — run SynapseKit eval suites in CI via GitHub Action |
"LangChain for people who hate LangChain."
| SynapseKit | LangChain | LlamaIndex | |
|---|---|---|---|
| Hard deps | 2 | 50+ | 20+ |
| Install size | ~5 MB | ~200 MB+ | ~100 MB+ |
| Async-native | ✅ Default | ||
| Streaming | ✅ Default | ||
| Cost tracking | ✅ Built-in | ❌ SaaS | ❌ No |
| Evaluation / EvalCI | ✅ CLI + GitHub Action | ❌ SaaS | |
| Graph workflows | ✅ Built-in | ❌ No | |
| Agent federation | ✅ Built-in | ❌ No | ❌ No |
| Reasoning LLMs | ✅ Unified adapter | ||
| Structured output | ✅ Provider-agnostic | ||
| Agent memory | ✅ 4 built-in backends | ||
| Observability | ✅ Prometheus + Grafana | ❌ No | ❌ No |
| Stack traces | Your code | Framework internals | Framework internals |
| License | Apache 2.0 | MIT | MIT |
pip install synapsekit[openai]from synapsekit import RAG
rag = RAG(model="gpt-4o-mini", api_key="sk-...")
rag.add("Your document text here")
print(rag.ask_sync("Summarise this."))Full docs → synapsekit.github.io/synapsekit-docs
Browse good first issues · Read the Contributing Guide · Join Discord
⭐ Star the repo if SynapseKit saves you time.