Ross ROSS = Recommend OSS · open-source software intelligence for agents

symfony/ai

Symfony AI is a set of components that integrate AI capabilities into PHP applications observed · 2026-09-03

github.com/symfony/ai · homepage · PHP · MIT (permissive) observed · 2026-09-03

Health v2 · maintenance only

87/100

  • Activity 100
  • Release rhythm 100
  • Longevity 35
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 11.0
  • age_days: 503
  • days_rel: 3
  • days_push: 0
  • n_releases_24m: 17

Full methodology

Adoption not part of the score

1191 stars · 269 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Symfony AI is a set of PHP components and Symfony bundles that integrate AI capabilities into PHP applications, including a unified interface to LLM providers (OpenAI, Anthropic, Gemini, Azure), an agent framework with tool calling, vector store abstraction for RAG, and MCP server/client support. It ships as decoupled components (Agent, Chat, Platform, Store, Mate) plus Symfony integration bundles.

Use cases

  • add LLM chat to a PHP application
  • build AI agents with tool calling in Symfony
  • implement RAG with vector stores in PHP
  • expose an MCP server from a Symfony app
  • unify multiple AI providers behind one interface
  • connect coding assistants to a PHP codebase via MCP
  • build multi-agent orchestration in PHP

When to choose

  • you are building a Symfony or PHP application that needs LLM features
  • you want provider-agnostic model inference with streaming, structured output, and multi-modal support
  • you need agents, tool calling, and RAG with Symfony-native YAML configuration and DI
  • you want to build or consume MCP servers/clients in PHP

When to avoid

  • your stack is Python, Node.js, or another non-PHP ecosystem
  • you need a standalone AI product rather than libraries to embed in an app
  • you need production MCP tooling - the Mate component is explicitly development-only
  • you need training or fine-tuning of models - this covers inference and integration only

Facets

framework · maturity active

agent-framework llm-inference rag mcp chatbot sdk vector-database artificial-intelligence large-language-models web-development developer-tools php self-hosted cli symfony php llm openai anthropic tool-calling multi-agent vector-store mcp-server ai-bundle ai-agents retrieval-augmented-generation web-server

6 sources

Member repositories

RepositoryRoleHealth v2
symfony/aimain87

For agents

markdown · JSON · MCP: product_card(name="symfony/ai")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem