# langchain-ai/langchain

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/langchain-ai-langchain).**

139,458 stars · 23,113 forks · Python · MIT

## Links

- GitHub: https://github.com/langchain-ai/langchain
- Homepage: https://docs.langchain.com/oss/python/langchain/
- awesome-repositories: https://awesome-repositories.com/repository/langchain-ai-langchain.md

## Topics

`agents` `ai` `ai-agents` `anthropic` `chatgpt` `deepagents` `enterprise` `framework` `gemini` `generative-ai` `langchain` `langgraph` `llm` `multiagent` `open-source` `openai` `pydantic` `python` `rag`

## Description

LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution.

The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing for explicit node-to-node routing and state management. Furthermore, it includes a human-in-the-loop control layer that enables developers to pause execution at defined breakpoints, allowing for manual inspection, modification, and approval of agent actions during runtime.

Beyond its core orchestration capabilities, the framework supports a tiered memory architecture that separates short-term conversation context from long-term persistent data. It also provides comprehensive observability tools for tracing and monitoring execution flows, alongside security features for managing authentication and fine-grained access control. The platform is supported by extensive documentation and standardized interfaces for models, embeddings, and data sources to facilitate the development of production-grade agentic systems.

## Tags

### Artificial Intelligence & ML

- [Agent Orchestration Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-orchestration-frameworks.md) — Supplies development abstractions for building, routing, and managing the entire lifecycle of autonomous agents.
- [LLM Integration Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-abstractions/llm-integration-layers.md) — Standardizes connections to diverse language model providers through flexible, swappable integration layers.
- [LLM Application Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations/llm-application-orchestration.md) — Coordinates complex agentic workflows by chaining model calls and managing state across multi-step processes. ([source](https://cdn.jsdelivr.net/gh/langchain-ai/langchain@master/README.md))
- [Human-in-the-Loop Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-orchestration-frameworks/human-in-the-loop-runtimes.md) — Enables manual inspection, modification, and approval of agent actions during runtime via dynamic breakpoints.
- [Graph-Based State Orchestrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/graph-based-state-orchestrations.md) — Models complex agent workflows as directed graphs to manage state transitions and task routing.
- [Human-in-the-loop Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/human-in-the-loop-workflows.md) — Implements oversight mechanisms that pause agent execution for human review, modification, or approval. ([source](https://docs.langchain.com/langsmith/add-human-in-the-loop.md))
- [Autonomous](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/autonomous.md) — Powers multi-step AI workflows that handle autonomous task completion, memory management, and tool execution.
- [Durable Agent Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/runtime-and-ops/durable-agent-runtimes.md) — Deploys execution environments that ensure fault-tolerance and persistent state for long-running agent processes. ([source](https://docs.langchain.com/oss/javascript/concepts/products.md))
- [Agent Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks.md) — Structures the development of language model applications through standardized configuration and execution abstractions. ([source](https://docs.langchain.com/oss/javascript/concepts/products.md))
- [Durable Execution Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/agent-frameworks/agent-runtimes/agent-execution-runtimes/durable-execution-runtimes.md) — Maintains persistent state across long-running processes by automatically checkpointing execution progress to external storage.
- [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Connects multiple language model providers through a consistent API for streamlined configuration and usage. ([source](https://docs.langchain.com/oss/javascript/concepts/providers-and-models.md))
- [Chat Model Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/language-model-interaction-patterns/chat-model-interfaces.md) — Exposes unified interfaces for initializing and interacting with various chat-based language models. ([source](https://cdn.jsdelivr.net/gh/langchain-ai/langchain@master/README.md))
- [Model Management](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-management.md) — Abstracts model interfaces to enable seamless provider swapping and side-by-side comparison without modifying core logic. ([source](https://docs.langchain.com/oss/javascript/concepts/providers-and-models.md))
- [Agent Harnesses](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-harnesses.md) — Bundles pre-built environments and toolsets for planning, executing, and managing complex agent-based workflows. ([source](https://docs.langchain.com/oss/javascript/concepts/products.md))
- [Agent Server APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/integration-deployment/infrastructure-runtime-environments/agent-servers/agent-server-apis.md) — Offers standardized endpoints for provisioning, configuring, and monitoring the operational lifecycle of assistant instances. ([source](https://docs.langchain.com/langsmith/agent-server.md))
- [Composable Memory Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/memory-context-systems/agent-memory-architectures/composable-memory-architectures.md) — Separates short-term context from long-term storage using pluggable backend interfaces for tiered memory architectures.
- [LLM Application Development](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/generative-ai/llm-application-development.md) — Simplifies prompt management, data retrieval, and model interaction through standardized development interfaces.
- [AI Observability and Evaluation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/training-monitoring-and-profiling/ai-observability/ai-observability-and-evaluation.md) — Traces, benchmarks, and monitors the execution performance of language model applications.
- [Agent Communication Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols.md) — Enables seamless data exchange and collaborative task execution between autonomous agents through shared messaging standards. ([source](https://docs.langchain.com/oss/javascript/deepagents/a2a.md))
- [Agent-to-Agent Communication](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols/agent-to-agent-communication.md) — Provides standardized messaging interfaces to facilitate distributed interaction and cross-service observability between agents. ([source](https://docs.langchain.com/oss/javascript/deepagents/a2a.md))
- [Agent Configurations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/autonomous-agents/agent-configurations.md) — Configures agent parameters, behavioral traits, and provider settings through modular, structured definitions. ([source](https://docs.langchain.com/oss/javascript/deepagents/code/configuration.md))
- [Execution Interrupts](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/execution-interrupts.md) — Interrupts active workflows dynamically based on runtime events or manual inputs to facilitate flexible process control. ([source](https://docs.langchain.com/langsmith/add-human-in-the-loop.md))
- [Dynamic Interrupt Mechanisms](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/human-in-the-loop-workflows/dynamic-interrupt-mechanisms.md) — Allows manual intervention by pausing execution graphs at specific breakpoints for real-time state inspection or adjustment.
- [Distributed Agent Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/coordination-and-routing/distributed-agent-systems.md) — Orchestrates multi-agent interactions across distributed environments using unified communication protocols.
- [Deployment Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/deployment-architectures.md) — Scales execution environments by managing task queues across both single-node and distributed infrastructure setups. ([source](https://docs.langchain.com/langsmith/agent-server.md))
- [Subagent Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/subagent-design/subagent-architectures.md) — Organizes task delegation to secondary agents by utilizing asynchronous communication patterns and structured protocol servers. ([source](https://docs.langchain.com/oss/javascript/deepagents/async-subagents.md))
- [State Backends](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/memory-context-systems/persistence-layers/state-backends.md) — Persists session data and historical state across multiple interactions using integrated storage backends. ([source](https://docs.langchain.com/oss/javascript/deepagents/backends.md))
- [Model Routers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/model-orchestration/model-routers.md) — Distributes requests across diverse model providers to optimize costs and balance computational loads. ([source](https://docs.langchain.com/oss/javascript/concepts/providers-and-models.md))
- [Short-term Memory](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/ai-memory-systems/short-term-memory.md) — Retains conversational context within active threads to ensure continuity during immediate interactions. ([source](https://docs.langchain.com/oss/javascript/concepts/memory.md))
- [Conversation Threads](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/conversation-management/conversation-threads.md) — Maintains persistent message history containers to preserve the continuity of user-agent interactions. ([source](https://docs.langchain.com/langsmith/agent-server-api/threads/create-thread.md))
- [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Retains information across long-term intervals by leveraging persistent storage mechanisms for cross-session context. ([source](https://docs.langchain.com/oss/javascript/concepts/memory.md))
- [Assistant Lifecycle Management](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/assistant-management/assistant-lifecycle-management.md) — Facilitates the creation, retrieval, and modification of assistant instances through dedicated management interfaces. ([source](https://docs.langchain.com/langsmith/agent-server-api/assistants/create-assistant.md))
- [Agent Memory Managers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/memory-context-systems/agent-memory-architectures/agent-memory-managers.md) — Centralizes the storage and retrieval of historical interaction data to inform future agent performance. ([source](https://docs.langchain.com/oss/javascript/concepts/memory.md))
- [Context Engineering](https://awesome-repositories.com/f/artificial-intelligence-ml/prompt-engineering/structural-formatting-frameworks/context-engineering.md) — Augments operational context by dynamically injecting relevant data and tool access into agent prompts. ([source](https://docs.langchain.com/oss/javascript/concepts/context.md))
- [Declarative Configuration Schemas](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-management/agent-configuration-management/declarative-configuration-schemas.md) — Applies structured schemas to manage environment variables, model parameters, and deployment settings.
- [Agent Client Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols/agent-client-protocols.md) — Exposes agent interfaces to external development environments and code editors via standardized protocols. ([source](https://docs.langchain.com/oss/javascript/deepagents/acp.md))
- [Event-Driven Agent Communications](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols/event-driven-agent-communications.md) — Coordinates distributed agent interactions through event-driven messaging protocols.
- [Assistant Metadata](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-capabilities-skills-tooling/agent-management/assistant-metadata.md) — Fetches configuration details and versioning data for specific assistant instances. ([source](https://docs.langchain.com/langsmith/agent-server-api/assistants/create-assistant.md))
- [Execution Breakpoints](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/agent-orchestration-multi-agent/control-flow-and-workflows/human-in-the-loop-workflows/execution-breakpoints.md) — Interrupts workflow execution at predefined nodes to allow for manual inspection and debugging. ([source](https://docs.langchain.com/langsmith/add-human-in-the-loop.md))
- [Model Capability Assessment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-and-validation/model-capability-assessment.md) — Benchmarks model performance to assist in selecting appropriate providers for specific requirements. ([source](https://docs.langchain.com/oss/javascript/concepts/providers-and-models.md))

### DevOps & Infrastructure

- [Stateful Workflow Engines](https://awesome-repositories.com/f/devops-infrastructure/cicd-pipeline-automation/workflow-orchestration/stateful-workflow-engines.md) — Supports durable, fault-tolerant execution of complex processes with persistent memory and state management.
- [Agent Deployment Components](https://awesome-repositories.com/f/devops-infrastructure/deployment-management-strategies/agent-deployment-components.md) — Integrates persistence layers and task queues to facilitate the reliable operation of agent servers. ([source](https://docs.langchain.com/langsmith/agent-server.md))

### Programming Languages & Runtimes

- [Execution Contexts](https://awesome-repositories.com/f/programming-languages-runtimes/language-features-paradigms/language-features/function-invocation-mechanics/execution-contexts.md) — Tracks conversation history and intermediate results by managing mutable data throughout an execution lifecycle. ([source](https://docs.langchain.com/oss/javascript/concepts/context.md))
- [Asynchronous Subagents](https://awesome-repositories.com/f/programming-languages-runtimes/language-features-paradigms/concurrency-models/concurrency/task-orchestration-frameworks/asynchronous-subagents.md) — Spawns background subagents to handle concurrent tasks while maintaining the primary user session. ([source](https://docs.langchain.com/oss/javascript/deepagents/async-subagents.md))
- [Run Lifecycle Controls](https://awesome-repositories.com/f/programming-languages-runtimes/runtime-execution-environments/runtime-environments/runtime-management-utilities/run-lifecycle-controls.md) — Terminates active processes to halt execution and prevent further task processing. ([source](https://docs.langchain.com/langsmith/agent-server-api/thread-runs/cancel-run.md))

### Software Engineering & Architecture

- [Agent Graph Configurations](https://awesome-repositories.com/f/software-engineering-architecture/application-lifecycle-management/configuration-management/configuration-scopes/application-configuration/agent-graph-configurations.md) — Defines agent workflows, environment variables, and dependency structures through configurable graph-based schemas. ([source](https://docs.langchain.com/langsmith/agent-server.md))
- [Suites](https://awesome-repositories.com/f/software-engineering-architecture/integration-extensibility/ecosystem-tooling/suites.md) — Aggregates a comprehensive set of development utilities for the entire lifecycle of language model applications. ([source](https://cdn.jsdelivr.net/gh/langchain-ai/langchain@master/README.md))

### System Administration & Monitoring

- [Distributed Tracing Systems](https://awesome-repositories.com/f/system-administration-monitoring/distributed-tracing-systems.md) — Visualizes complex execution paths by aggregating telemetry data from multiple communicating agents into a single thread. ([source](https://docs.langchain.com/oss/javascript/deepagents/a2a.md))
- [Execution Tracing](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/execution-tracing-analysis/execution-tracing.md) — Records granular operation sequences and function calls to provide deep visibility into performance and decision-making.
- [Agent Observability Platforms](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/observability-platforms/distributed-tracing-execution-analysis/agent-observability-platforms.md) — Visualizes execution flows and performance metrics to monitor complex agent-based applications.
- [Execution Tracing and Analysis](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/execution-tracing-analysis.md) — Captures conditional runtime data by attaching dynamic metadata to parent execution spans. ([source](https://docs.langchain.com/langsmith/add-metadata-tags.md))
- [Trace Metadata](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/execution-tracing-analysis/trace-metadata.md) — Annotates execution traces with contextual identifiers to improve observability and data categorization. ([source](https://docs.langchain.com/langsmith/add-metadata-tags.md))
- [Execution Metadata](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/observability-platforms/distributed-tracing-execution-analysis/execution-metadata.md) — Decorates functions with static labels to ensure consistent tracking across execution spans. ([source](https://docs.langchain.com/langsmith/add-metadata-tags.md))
- [Execution Run APIs](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/observability-platforms/distributed-tracing-execution-analysis/execution-run-apis.md) — Queries execution logs and output data to verify the status of specific system runs. ([source](https://docs.langchain.com/langsmith/agent-server-api/thread-runs/cancel-run.md))

### Part of an Awesome List

- [Agent Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/agent-frameworks.md) — Framework for developing applications powered by language models and external data.
- [AI Agent Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/ai-agent-frameworks.md) — Composability framework for building LLM applications.
- [AI Agents](https://awesome-repositories.com/f/awesome-lists/ai/ai-agents.md) — Standard framework for building LLM-powered applications.
- [AI Agents and Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/ai-agents-and-frameworks.md) — Framework for developing applications powered by language models.
- [AI and Agents](https://awesome-repositories.com/f/awesome-lists/ai/ai-and-agents.md) — Building applications with LLMs through composability.
- [AI & Machine Learning](https://awesome-repositories.com/f/awesome-lists/ai/ai-machine-learning.md) — Framework for building applications powered by language models.
- [Application Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/application-frameworks.md) — Comprehensive framework for developing LLM-powered applications.
- [Development Frameworks and Tools](https://awesome-repositories.com/f/awesome-lists/ai/development-frameworks-and-tools.md) — Framework for developing applications powered by language models.
- [Development Platforms](https://awesome-repositories.com/f/awesome-lists/ai/development-platforms.md) — Core framework for building applications with language models.
- [Inference and Serving](https://awesome-repositories.com/f/awesome-lists/ai/inference-and-serving.md) — Framework for building context-aware reasoning applications.
- [Language Model Development](https://awesome-repositories.com/f/awesome-lists/ai/language-model-development.md) — Framework for building composable LLM applications.
- [Large Language Models](https://awesome-repositories.com/f/awesome-lists/ai/large-language-models.md) — Orchestration framework for building LLM-powered applications.
- [LLM Applications](https://awesome-repositories.com/f/awesome-lists/ai/llm-applications.md) — Framework for developing applications powered by language models.
- [LLM Development](https://awesome-repositories.com/f/awesome-lists/ai/llm-development.md) — A framework for developing applications powered by language models.
- [Natural Language Processing](https://awesome-repositories.com/f/awesome-lists/ai/natural-language-processing.md) — Listed in the “Natural Language Processing” section of the FunNLP awesome list.
- [Data Integration Tools](https://awesome-repositories.com/f/awesome-lists/data/data-integration-tools.md) — Framework for developing applications powered by language models.
- [Example Projects](https://awesome-repositories.com/f/awesome-lists/devtools/example-projects.md) — Example code for building applications with LangChain.
- [RAG Frameworks](https://awesome-repositories.com/f/awesome-lists/devtools/rag-frameworks.md) — Modular framework for chaining LLM components and data sources.
- [Agentic AI](https://awesome-repositories.com/f/awesome-lists/more/agentic-ai.md) — Listed in the “Agentic AI” section of the The Incredible Pytorch awesome list.
- [Large Language Models (LLMs)](https://awesome-repositories.com/f/awesome-lists/more/large-language-models-llms.md) — Listed in the “Large Language Models (LLMs)” section of the The Incredible Pytorch awesome list.

### Web Development

- [State Channels](https://awesome-repositories.com/f/web-development/frontend-development-tools/state-data-management/state-channels.md) — Tracks metadata and execution history within dedicated storage channels for auditability and state recovery. ([source](https://docs.langchain.com/oss/javascript/deepagents/async-subagents.md))

### Education & Learning Resources

- [Remote Procedure Calls](https://awesome-repositories.com/f/education-learning-resources/educational-resources/systems-applied-computing/infrastructure-architecture/computer-networks/remote-procedure-calls.md) — Transmits messages and streams real-time responses between distributed agents using standardized communication interfaces. ([source](https://docs.langchain.com/oss/javascript/deepagents/a2a.md))