LangChain

Hybrid (offline or cloud)

The default agent framework. Pipelines, retrievers, tool-calling — works against any local backend.

Editorial verdict: “The default agent framework. Heavy on abstractions, deep ecosystem — pick this if you want defaults.”

Agent framework

Free

MIT

★ 4.0 / 5

GitHub ★ 95,000

↗ Homepage ↗ GitHub ↗ Docs

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported

ollamallama-cppvllmopenai-compat

§ OS / platform

macoslinuxwindows

What it is

LangChain is the most-used agent framework in 2024-2026. Pipelines, retrievers, tool-calling, memory, agents. First-class integration with Ollama, llama.cpp, vLLM, and any OpenAI-compatible endpoint. Strong opinions and lots of abstractions — some love them, some don't.

✓ Strengths

+Biggest ecosystem — examples, integrations, tutorials
+First-class local-runtime support
+Active development

△ Caveats

−Heavy abstraction layers can hide bugs
−API churn has been a long-running complaint

About the Agent framework category

Programming SDK for building agent loops and pipelines.

§ Other agent framework apps

LlamaIndex

Best agent framework for RAG-first workloads. Less abstraction than LangChain.

CrewAI

Best ergonomic multi-agent framework. Picks defaults you'd otherwise have to argue about.

AutoGen

Best for multi-agent role-played workflows. Niche; not the default agent framework.

Where to go from here

Stack Builder →

Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.

Back to /apps →

The full directory — filter by category, runtime, OS, privacy posture, or VRAM.

Runtimes (/tools) →

What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.

Community benchmarks →

Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.