embedchain-fastdash

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

AI

LangGraph

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• AI
  Conversational RAG agentA conversational RAG agent — LangGraph + OpenRouter
• AI
  Inline citationsanswers with inline citations
• AI
  Local key-free embeddingslocal, key-free embeddings
• AI
  Semantic retrieval toolsemantic retrieval; the agent answers only from the retrieved passages
• AI
  Per-session knowledge basea per-session knowledge base
• AI
  Multi-turn memorygives it multi-turn memory
• AI
  Configurable chat modelKNOWLEDGE_CHAT_MODEL (default anthropic/claude-haiku-4.5)
• AI
  Configurable embed modelEMBED_MODEL (default BAAI/bge-small-en-v1.5)
• Deploy
  Gunicorn single-worker servingServed by gunicorn (gthread, single worker)
• Deploy
  Baked-in embedding modelThe FastEmbed model is baked into the image at build time
• Deploy
  OpenRouter API key secretSet OPENROUTER_API_KEY as a secret on your host
• UI
  Streamed tool call cardsshow up as cards in the transcript

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote; 2 unverifiable items were discarded. A README claim is the maker's description, not something we tested.