Back to directory

LangChain.dart

LangChain.dart is an unofficial Dart port of the Python LangChain framework, giving Dart and Flutter apps a unified interface to language model providers plus components for retrieval-augmented generation and agents.

LangChain.dart

LangChain.dart is an unofficial Dart port of the LangChain Python framework, for building LLM-powered Dart and Flutter applications. It offers ready-to-use components for working with language models and a standard interface for chaining them together into use cases such as chatbots, question answering, summarization, translation, extraction and recommendation.

A model I/O module gives a unified API across providers such as OpenAI, Google, Mistral and Ollama, along with prompt templates, example selectors and output parsers. A retrieval module covers document loaders, text splitters, embedding models, vector stores and retrievers for retrieval-augmented generation, and an agents module lets a language model decide which available tools, such as web search, a calculator or a database lookup, to use for a task.

Components compose using a LangChain Expression Language, and the project is organized as a set of separate packages.

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.

  • 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.

  • 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.