ArchestackGitHub ↗ (opens in a new tab)

AI API backends

Backend service templates (FastAPI, Express, Hono) that expose models or agents over an API.

agent-service-toolkit leads with 70, ahead of fastapi-langgraph-agent-production-ready-template (55) and full-stack-ai-agent-template (55). 6 projects ranked by score.

The ranking

AI API backends: full ranking
RankProjectAdoptionFreshnessMaintenanceEasy to runAgent-readyScore
1agent-service-toolkitLangGraph agents served by FastAPI with a Streamlit chat client Live demo ↗ (opens in a new tab)4.5k stars, MIT, last commit Oct 20267510063505570 out of 100
2fastapi-langgraph-agent-production-ready-templateFastAPI service for a LangGraph agent with auth, memory and tracing2.7k stars, MIT, last commit Sep 20266310046177055 out of 100
3full-stack-ai-agent-templateProject generator for FastAPI and Next.js apps with agents and RAG1.9k stars, MIT, last commit Oct 2026521009607055 out of 100
#4generative-ai-project-templateuv workspace with FastAPI, NiceGUI, LiteLLM and Promptfoo evals118 stars, MIT, last commit Sep 2026131006050051 out of 100
#5nodejs-api-boilerplateExpress TypeScript CRUD API template with an LLM module generator163 stars, MIT, last commit Apr 20262467033031 out of 100
#6genai-apiHono API on Cloudflare Workers proxying Gemini with bearer auth111 stars, Apache-2.0, last commit Apr 20263640333028 out of 100

Momentum, Verified build, Docs and Privacy are not measured yet; their weight goes to the signals shown. A dash means the signal is not scored for that kind of project. Hover a number for its rating in words.

Reviews

170 out of 100

agent-service-toolkit

LangGraph agents served by FastAPI with a Streamlit chat client

Live demo ↗ (opens in a new tab)4.5k stars, MIT, last commit Oct 2026

Python service where LangGraph v1 agents (interrupt, Command, Store) are served by FastAPI with streaming and non-streaming endpoints, AG-UI support, per-agent URL paths, /threads history and a Postgres checkpointer via docker compose. Includes an AgentClient, a Streamlit chat UI with voice, LangSmith feedback, Groq moderation, a ChromaDB RAG agent, unit, integration and smoke tests. Needs at least one LLM API key.

Strengths

  • AG-UI endpoint for CopilotKit-style frontends alongside the REST API
  • docker compose watch runs Postgres, API and Streamlit with live reload
  • Unit and integration tests plus smoke tests for Postgres, Mongo, AG-UI and Langfuse
  • Hosted demo on Streamlit Cloud

Weaknesses

  • Solo maintainer; issues triaged roughly biweekly
  • Streamlit client is a demo UI, not a product frontend
  • Content moderation needs a Groq API key
  • Tests only run outside Docker
  • Python, LangChain providers: OpenAI, Anthropic, Google, Ollama, VertexAI, vLLM/SGLang, AG-UI protocol
  • Needs LLM API key (OpenAI, Anthropic, Google, Groq, Ollama or others), PostgreSQL (compose), LangSmith (optional), ChromaDB (RAG agent)
  • GitHub template
  • Docker
  • env example file
Live demo ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
255 out of 100

fastapi-langgraph-agent-production-ready-template

FastAPI service for a LangGraph agent with auth, memory and tracing

2.7k stars, MIT, last commit Sep 2026

FastAPI backend with a stateful LangGraph agent (Postgres checkpointing, tool calling, human-in-the-loop), mem0 long-term memory on pgvector, JWT auth and sessions, slowapi rate limiting, Alembic migrations, optional Valkey/Redis cache, Langfuse tracing, Prometheus and Grafana, and evals. make docker-up starts the API on port 8000 with PostgreSQL. OpenAI only via ChatOpenAI; any OpenAI-compatible base URL works.

Strengths

  • JWT sessions, rate limiting and structured per-request logging included
  • mem0 long-term memory runs in-process on pgvector; no mem0 cloud
  • Circular model fallback with retries and a total timeout budget
  • Langfuse, Prometheus and Grafana wired; Langfuse can be disabled

Weaknesses

  • OpenAI (or OpenAI-compatible) only; multi-provider is an open issue
  • README leads with a sponsor pitch for Atlas Cloud
  • Needs the pgvector extension and an OpenAI key for memory
  • Not a GitHub template; clone and strip
  • Python, OpenAI via langchain_openai.ChatOpenAI (any OpenAI-compatible base URL)
  • Needs PostgreSQL with pgvector, OpenAI API key, Valkey/Redis (optional), Langfuse (optional)
  • Docker
  • env example file
Repository on GitHub ↗ (opens in a new tab)
355 out of 100

full-stack-ai-agent-template

Project generator for FastAPI and Next.js apps with agents and RAG

1.9k stars, MIT, last commit Oct 2026

CLI (pip install fastapi-fullstack) scaffolding a FastAPI backend and Next.js frontend via a wizard or presets, with Pydantic AI, Pydantic Deep Agents, LangChain, LangGraph or DeepAgents, RAG on Milvus, Qdrant, pgvector or Chroma, WebSocket chat, JWT, OAuth, admin, teams, Stripe billing, Celery, Docker and K8s. make bootstrap starts Postgres, migrations and a seeded admin; projects can pull template upgrades later.

Strengths

  • Wizard and presets pick framework, vector store, auth and billing per project
  • Template upgrades merge into generated projects on a branch
  • Chat UI renders tool calls, plans, subagents, charts and Python execution
  • 100% coverage badge and CI on the generator

Weaknesses

  • Generator, not a repo to fork; output size depends on options chosen
  • Seeds admin@example.com with a fixed password; rotate before exposing
  • Optional services (Milvus, Redis, Celery) raise the local footprint
  • Windows needs GNU Make or WSL2
  • Python, Pydantic AI, Pydantic Deep Agents, LangChain, LangGraph
  • Needs PostgreSQL, Redis (optional), Milvus, Qdrant, pgvector or ChromaDB (RAG), Stripe (billing), LLM provider API key
Documentation ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
#451 out of 100

generative-ai-project-template

uv workspace with FastAPI, NiceGUI, LiteLLM and Promptfoo evals

118 stars, MIT, last commit Sep 2026

Python 3.12 uv workspace with a FastAPI backend (port 8000) and NiceGUI frontend (port 8080) for chat, information extraction and RAG over documents, with models served locally by Ollama or through any LiteLLM provider. Ships Makefiles for install, run, test, Docker (CPU and CUDA compose), pre-commit with ruff and detect-secrets, pytest, Promptfoo and Ragas evals, GitHub Actions, Renovate and an mkdocs site.

Strengths

  • LiteLLM naming lets you switch between Ollama and cloud models by env
  • Promptfoo and Ragas evaluation wired into the template
  • CPU and CUDA docker compose variants
  • CI tests the app against local Ollama models

Weaknesses

  • NiceGUI frontend is unusual for product UIs
  • No auth, database or persistence described
  • Ubuntu 22.04 or macOS only per prerequisites
  • CUDA path installs PyTorch; heavier install
  • Python, LiteLLM (any provider), Ollama
  • Needs Ollama (local models) or an LLM provider key via LiteLLM
  • GitHub template
  • Docker
  • env example file
Repository on GitHub ↗ (opens in a new tab)
#531 out of 100

nodejs-api-boilerplate

Express TypeScript CRUD API template with an LLM module generator

163 stars, MIT, last commit Apr 2026

Express and TypeScript REST API with vertical-slice modules, Zod validation, InversifyJS DI, Knex transactions, ioredis caching, winston trace IDs, node-cron, S3 uploads and Supertest e2e tests, run via docker compose on port 8080. The llm-codegen folder runs three LLM micro-agents (Developer, Troubleshooter, TestsFixer) that generate a new CRUD module, migration, seeds and passing tests from a text description.

Strengths

  • Codegen loop compiles and runs e2e tests until they pass
  • Supports OpenAI, Anthropic, DeepSeek and OpenRouter keys for generation
  • JWT auth routes, Redis cache and cron already in the base API
  • Tests run in Docker or against local SQLite

Weaknesses

  • AI is a dev-time generator; the API itself has no AI features
  • Node badge pins v14 to v20; check against current LTS
  • Generated code still needs manual review and integration
  • Last commit 2026-04
  • TypeScript, OpenAI, Anthropic, DeepSeek, OpenRouter
  • Needs PostgreSQL or SQLite, Redis, AWS S3 (uploads), LLM API key for codegen
  • GitHub template
  • Docker
  • env example file
Repository on GitHub ↗ (opens in a new tab)
#628 out of 100

genai-api

Hono API on Cloudflare Workers proxying Gemini with bearer auth

111 stars, Apache-2.0, last commit Apr 2026

Hono TypeScript worker exposing POST /completion that forwards OpenAI-style messages (text and data-URL images) to Gemini 2.0 and 2.5 Flash models through Cloudflare AI Gateway, validated with Zod and returned as plain text. Secured by a BEARER_TOKEN secret, with an optional X-API-Key header to pass a provider key per request; deployed with make deploy. Built for Apple Shortcuts; local dev on port 8788.

Strengths

  • Bearer-token auth and Zod validation on the single endpoint
  • Requests route through Cloudflare AI Gateway for caching and logs
  • Multimodal input via data-URL images
  • Biome lint and Snyk badge

Weaknesses

  • Google AI Studio provider only; four Gemini Flash models
  • Plain-text responses, no streaming
  • No tests mentioned; last commit 2026-04
  • Needs a Cloudflare account and AI Gateway id
  • TypeScript, Gemini 2.5 Flash, 2.5 Flash Lite, 2.0 Flash, 2.0 Flash Lite via Cloudflare AI Gateway, OpenAI SDK client
  • Needs Cloudflare account with AI Gateway, Google AI Studio API key
  • GitHub template
Repository on GitHub ↗ (opens in a new tab)

Written from each project's README and checked facts. Spot something wrong? Report it on GitHub (opens in a new tab).