# tryAGI/LangChain

C# implementation of LangChain. We try to be as close to the original as possible in terms of abstractions, but are open to new entities.

Repository: https://github.com/tryAGI/LangChain
Canonical: https://ross.abutalabs.com/products/tryagi-langchain
Homepage: https://tryagi.github.io/LangChain/
Language: C#
License: MIT
License Family: permissive
Topics: ai, csharp, langchain, llm, langchain-csharp, openai, sdk, langchain-dotnet, dotnet
Last push: 2026-08-31T20:25:19+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 8, longevity 84
- inputs: {"age_days": 1188, "days_push": 2, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1070, forks 139 (observed 2026-09-01T02:14:08.112685+00:00)

## What it is
LangChain .NET is a C#/.NET implementation of the LangChain framework for building LLM-powered applications through composability. It provides abstractions for chat models, embeddings, vector databases, document loaders, and chains, staying close to the original Python LangChain while remaining open to new entities.

## Use cases
- build LLM applications in C#
- create a RAG pipeline over PDF documents
- query a vector database with OpenAI embeddings
- port LangChain abstractions to .NET
- build chatbots and AI agents in .NET
- chain LLM calls with composable abstractions

## When to choose
- you are a .NET/C# developer wanting LangChain-style abstractions
- you want an alternative to Semantic Kernel with more provider flexibility
- you need document loading, embeddings, and vector search in one framework

## When to avoid
- your project is Python or JavaScript based - use official LangChain instead
- you want a Microsoft-backed, production-hardened framework like Semantic Kernel
- you need only a thin OpenAI API client without chain abstractions

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, rag, llm-inference, sdk, chatbot
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: dotnet, cross-platform, cloud
- tags: langchain, csharp, llm, openai, embeddings, vector-database, document-loaders, composability, ai-agents, retrieval-augmented-generation

## Member repositories
- tryAGI/LangChain (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:14:08.112685+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:54:09.540773+00:00, confidence not recorded.
  - readme: https://github.com/tryAGI/LangChain (fetched 2026-09-01T02:14:08.112685+00:00, sha 708d6abfcc2d)
  - homepage: https://tryagi.github.io/LangChain/ (fetched 2026-08-29T12:56:19.143584+00:00, sha e8829648453c)
- Data as of 2026-08-30T08:39:29.467469+00:00.