agent-service-toolkit

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

Framework

FastAPI, Streamlit

Database / ORM

PostgreSQL (psycopg)

AI

LangChain, LangGraph

API layer

Pydantic, Uvicorn

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

What the README says you get

• AI
  LangGraph agentA customizable agent built using the LangGraph framework
• AI
  Multiple agent supportRun multiple agents in the service and call by URL path
• AI
  Content moderationImplements Safeguard for content moderation
• AI
  RAG agentA basic RAG agent implementation using ChromaDB
• Analytics
  Feedback mechanismstar-based feedback system integrated with LangSmith
• API
  Advanced streamingsupport both token-based and message-based streaming
• API
  AG-UI protocol supportEvery agent is also served over the AG-UI protocol
• API
  AgentClientgeneric `src/client/client.AgentClient` that can be used to interact with the agent service
• Deploy
  Docker supportIncludes Dockerfiles and a docker compose file
• Testing
  Unit and integration testsIncludes robust unit and integration tests for the full repo
• UI
  Streamlit chat interfaceuser-friendly chat interface for interacting with the agent, including voice input and output

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; 3 unverifiable items were discarded. A README claim is the maker's description, not something we tested.