Ollama Provider V2 for Vercel AI SDK

A Vercel AI SDK provider for Ollama that implements the official Ollama API with minimal dependencies, working in Node.js, browsers and edge environments.

Visit website github.com

Ollama Provider V2 lets the Vercel AI SDK call models served by Ollama, implementing Ollama's own API directly rather than wrapping an OpenAI-compatible shim. It has few dependencies and works the same way in Node.js, in browsers, and in edge runtimes.

It supports the AI SDK's text generation and streaming functions, tool calling (with the SDK's step-based control needed to let a model call a tool and then continue to an answer), embeddings, and a reasoning or thinking mode for models that support chain-of-thought output, exposed either as a top-level SDK option or as an Ollama-specific provider option. Full TypeScript types are included.

It installs from npm alongside the Vercel AI SDK package, and is maintained under the Apache-2.0 license.

More in Agent frameworks

See all 902

Recurse
recurse.run
A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.
- Agent frameworks
ProofForge
shulgin.is-a.dev
An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.
- Agent frameworks
local-coder
github.com
Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.
- Coding agents
- Agent frameworks

More in Agent frameworks

Recurse

ProofForge

local-coder

Cookies