Convex Agent

Convex-agent wires up an AI agent or RAG backend on top of @convex-dev/agent, so you get durable threads, message history, tool calls, and vector search without building that plumbing yourself. Reach for it when you want an in-app assistant that remembers conversations and can pull from your own documents. The part I like most is that model calls go through the Convex AI Gateway by default, which means Convex holds the provider credentials and you never have to obtain, store, or rotate an LLM key. The honest caveat is that the gateway doesn't serve embeddings yet, so RAG setups still need an embedding provider key stored in Convex env. It also requires a Convex Cloud deployment on a paid plan, so free-tier or self-hosted projects will need the fallback path.

skills.sh installs: 41.1K
GitHub stars: 69
last updated: Oct 26, 2026

View on GitHub

Install

$ npx -y skills add convex/agent-skills --skill convex-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

Add an AI agent / RAG backend

Install @convex-dev/agent for durable threads, message history, tool-calls, and vector search/RAG — the backend for an in-app AI agent. Call models through the Convex AI Gateway by default: Convex holds the provider credentials, so there is no LLM key to obtain, store, or rotate.

Workflow

Install @convex-dev/agent + @convex-dev/ai-sdk-provider; add the agent component to convex.config.ts.
Define the agent (tools, instructions) with languageModel: convexGateway("provider/model") — no API key needed (needs convex 1.45+ on a Convex Cloud deployment, paid plan).
Create threads + stream messages; persist history in Convex.
For RAG: embed docs into a vector index and retrieve in the tool. The gateway does not serve embeddings yet, so store the embedding provider's key via the env micro power.
Only if the gateway is unavailable (free plan, self-hosted, local backend): call the provider SDK with a key stored via the env micro power.