INVOKE THIS SKILL when setting up a NEW project or when asked about package versions, installation, or dependency management for LangChain, LangGraph, LangSmith, or Deep Agents. Covers required packages, minimum versions, environment requirements, versioning best practices, and common community tool packages for both Python and TypeScript. Not opinionated about which package manager to use.
Key principles:
| Requirement | Python | TypeScript / Node |
|---|
| Runtime minimum | Python 3.10+ | Node.js 20+ |
| LangChain | 1.0+ (LTS) | 1.0+ (LTS) |
| LangSmith SDK | >= 0.1.99 | >= 0.1.99 |
| Framework | When to use | Core extra package |
|---|---|---|
| LangGraph | Need fine-grained graph control, custom workflows, loops, or branching | langgraph / @langchain/langgraph |
| Deep Agents | Want batteries-included planning, memory, file context, and skills out of the box | deepagents (depends on LangGraph; installs it as a transitive dep) |
Both sit on top of langchain + langchain-core + langsmith.
</framework-choice>
| Package | Role | Min version |
|---|---|---|
langchain | Agents, chains, retrieval | 1.0 |
langchain-core | Base types & interfaces (peer dep) | 1.0 |
langsmith | Tracing, evaluation, datasets | 0.1.99 |
| Package | Use when | Min version |
|---|---|---|
langgraph | Building custom graphs directly | 1.0 |
deepagents | Using the Deep Agents framework | latest |
| Package | Provider |
|---|---|
langchain-openai | OpenAI (GPT-4o, o3, …) |
langchain-anthropic | Anthropic (Claude) |
langchain-google-genai | Google (Gemini) |
langchain-mistralai | Mistral |
langchain-groq | Groq (fast inference) |
langchain-cohere | Cohere |
langchain-fireworks | Fireworks AI |
langchain-together | Together AI |
langchain-huggingface | Hugging Face Hub |
langchain-ollama | Ollama (local models) |
langchain-aws | AWS Bedrock |
langchain-azure-ai | Azure AI Foundry |
These packages have tighter compatibility requirements — use the latest available version unless you have a specific reason not to.
| Package | Adds | Notes |
|---|---|---|
langchain-tavily | Tavily web search tool | Dedicated integration package; prefer latest |
langchain-text-splitters | Text chunking utilities | Semver, keep current |
langchain-community | 1000+ integrations (fallback) | NOT semver — pin to minor series |
faiss-cpu | FAISS vector store (local) | Via langchain-community; use latest |
langchain-chroma | Chroma vector store | Dedicated integration package; prefer latest |
langchain-pinecone | Pinecone vector store | Dedicated integration package; prefer latest |
langchain-qdrant | Qdrant vector store | Dedicated integration package; prefer latest |
langchain-weaviate | Weaviate vector store | Dedicated integration package; prefer latest |
langsmith[pytest] | pytest plugin for LangSmith | Requires langsmith >= 0.3.4 |
langchain-community stability note: This package is NOT on semantic versioning. Minor releases can contain breaking changes. Prefer dedicated integration packages (e.g.
langchain-chroma,langchain-tavily) when they exist — they are independently versioned and more stable.
| Package | Role | Min version |
|---|---|---|
@langchain/core | Base types & interfaces (peer dep) | 1.0 |
langchain | Agents, chains, retrieval | 1.0 |
langsmith | Tracing, evaluation, datasets | 0.1.99 |
| Package | Use when | Min version |
|---|---|---|
@langchain/langgraph | Building custom graphs directly | 1.0 |
deepagents | Using the Deep Agents framework | latest |
| Package | Provider |
|---|---|
@langchain/openai | OpenAI (GPT-4o, o3, …) |
@langchain/anthropic | Anthropic (Claude) |
@langchain/google-genai | Google (Gemini) |
@langchain/mistralai | Mistral |
@langchain/groq | Groq (fast inference) |
@langchain/cohere | Cohere |
@langchain/aws | AWS Bedrock |
@langchain/azure-openai | Azure OpenAI |
@langchain/ollama | Ollama (local models) |
| Package | Adds | Notes |
|---|---|---|
@langchain/tavily | Tavily web search tool | Dedicated integration package; prefer latest |
@langchain/community | Broad set of community integrations | Use sparingly; prefer dedicated packages |
@langchain/pinecone | Pinecone vector store | Dedicated integration package; prefer latest |
@langchain/qdrant | Qdrant vector store | Dedicated integration package; prefer latest |
@langchain/weaviate | Weaviate vector store | Dedicated integration package; prefer latest |
@langchain/coremust be installed explicitly in yarn workspaces and monorepos — it is a peer dependency and will not always be hoisted automatically.
</python>
</ex-langgraph-python>
<ex-langgraph-typescript>
<typescript>
Minimal package.json dependencies for a LangGraph project (provider-agnostic).
```json
{
"dependencies": {
"@langchain/core": "^1.0.0",
"langchain": "^1.0.0",
"@langchain/langgraph": "^1.0.0",
"langsmith": "^0.1.99"
}
}
</python>
</ex-deepagents-python>
<ex-deepagents-typescript>
<typescript>
Minimal package.json dependencies for a Deep Agents project (provider-agnostic).
```json
{
"dependencies": {
"deepagents": "latest",
"@langchain/core": "^1.0.0",
"langchain": "^1.0.0",
"langsmith": "^0.1.99"
}
}
langchain-tavily # use latest; partner package, semver
langchain-chroma # use latest; partner package, semver
langchain-text-splitters # use latest; semver
</python>
</ex-with-tools-python>
<ex-with-tools-typescript>
<typescript>
Adding Tavily search and a vector store to a LangGraph project.
```json
{
"dependencies": {
"@langchain/core": "^1.0.0",
"langchain": "^1.0.0",
"@langchain/langgraph": "^1.0.0",
"langsmith": "^0.1.99",
"@langchain/tavily": "latest",
"@langchain/pinecone": "latest"
}
}
| Package group | Versioning | Safe upgrade strategy |
|---|---|---|
langchain, langchain-core | Strict semver (1.0 LTS) | Allow minor: >=1.0,<2.0 |
langgraph / @langchain/langgraph | Strict semver (v1 LTS) | Allow minor: >=1.0,<2.0 |
langsmith | Strict semver | Allow minor: >=0.1.99 |
Dedicated integration packages (e.g. langchain-tavily, langchain-chroma) | Independently versioned | Allow minor updates; use latest |
langchain-community | NOT semver | Pin exact minor: >=0.4.0,<0.5.0 |
deepagents | Follow project releases | Pin to tested version in production |
Breaking changes only happen in major versions (1.x → 2.x) for all semver-compliant packages. Deprecated features remain functional across the entire 1.x series with warnings.
Prefer dedicated integration packages over langchain-community. When a dedicated package exists (e.g. langchain-chroma instead of langchain-community's Chroma integration), use it — dedicated packages are independently versioned and better tested.
Community tool packages (Tavily, vector stores, etc.) should be kept at latest unless your project requires a locked environment. These packages frequently release compatibility fixes alongside LangChain/LangGraph updates.
# LangSmith (always recommended for observability)
LANGSMITH_API_KEY=<your-key>
LANGSMITH_PROJECT=<project-name> # optional, defaults to "default"
# Model provider — set the one(s) you use
OPENAI_API_KEY=<your-key>
ANTHROPIC_API_KEY=<your-key>
GOOGLE_API_KEY=<your-key>
MISTRAL_API_KEY=<your-key>
GROQ_API_KEY=<your-key>
COHERE_API_KEY=<your-key>
FIREWORKS_API_KEY=<your-key>
TOGETHER_API_KEY=<your-key>
HUGGINGFACEHUB_API_TOKEN=<your-key>
# Common tool/retrieval services
TAVILY_API_KEY=<your-key> # for Tavily search
PINECONE_API_KEY=<your-key> # for Pinecone
langchain>=1.0,<2.0
</fix-legacy-version>
<fix-community-unpinned>
`langchain-community` can break on minor version bumps — it does not follow semver.
langchain-community>=0.4
langchain-community>=0.4.0,<0.5.0
Also consider switching to the equivalent dedicated integration package if one exists (e.g. `langchain-chroma` instead of the community Chroma integration).
</fix-community-unpinned>
<fix-community-tool-outdated>
Community tool packages like `langchain-tavily` and vector store integrations release compatibility fixes alongside LangChain updates. Using an old pinned version can cause import errors or broken tool schemas.
langchain-tavily==0.0.1
langchain-tavily>=0.1
</fix-community-tool-outdated>
<fix-core-not-installed>
<typescript>
`@langchain/core` is a peer dependency — it must be in your package.json, especially in monorepos.
```json
// WRONG: missing @langchain/core (breaks in yarn workspaces / strict hoisting)
{
"dependencies": {
"@langchain/langgraph": "^1.0.0"
}
}
// CORRECT: always list @langchain/core explicitly
{
"dependencies": {
"@langchain/core": "^1.0.0",
"@langchain/langgraph": "^1.0.0"
}
}