Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.langchain.com/llms.txt

Use this file to discover all available pages before exploring further.

Use the LangSmith Python and TypeScript SDKs to manage agent repos and skill repos in the Context Hub programmatically. Push new versions from CI, pull the latest or a pinned commit at runtime to inject context into your agent, and use additional methods to check existence, list and search repos, and delete what you no longer need.
Context Hub methods require langsmith>=0.7.35 (Python) and langsmith>=0.5.23 (TypeScript).

​
Setup

  1. Install packages: 
    pip install -U langsmith
  2. Configure environment variables. If you already have LANGSMITH_API_KEY set in your environment, skip this step. Otherwise, create one in Settings > API Keys > Create API Key in LangSmith, then set it as an environment variable: 
    export LANGSMITH_API_KEY="lsv2_..."
Python async: All methods shown on this page are also available on AsyncClient (imported from langsmith) with identical signatures—just await each call. The TypeScript SDK is async by default; there is no separate async client.

​
Push an agent

Create a new agent repo or commit a new version of an existing one. If the repo doesn’t exist yet, it is created with the metadata you provide (description, readme, tags, is_public). If it already exists, those fields are patched only when explicitly passed. The method returns a URL pointing to the new commit in the LangSmith UI: 
from langsmith import Client
from langsmith.schemas import FileEntry

client = Client()

url = client.push_agent(
    "email-assistant",
    files={
        "AGENTS.md": FileEntry(
            content="You are an email triage assistant.",
        ),
        "tools.json": FileEntry(content='{"tools": []}'),
    },
    description="Triages and drafts replies to incoming email.",
    tags=["email", "productivity"],
    is_public=False,
)
print(url)

​
Push a skill

Identical surface to push_agent, but commits to a skill repo. Use this for reusable capabilities that other agents can depend on: 
from langsmith import Client
from langsmith.schemas import FileEntry

client = Client()

url = client.push_skill(
    "deep-research",
    files={
        "SKILL.md": FileEntry(content="Conduct deep multi-step research."),
    },
    description="Multi-step web research with citations.",
    tags=["research"],
)
print(url)
Instead of inlining file content, an entry in files can be a link to another agent or skill repo, which lets you compose contexts without duplicating content across repos. For example, an agent that delegates to a shared skill. If you omit commit_id, LangSmith links to the latest commit of that repo when you push this commit. If the linked repo updates later, LangSmith propagates that update to parent repos that reference it. 
from langsmith import Client
from langsmith.schemas import AgentEntry, FileEntry, SkillEntry

client = Client()

url = client.push_agent(
    "email-assistant",
    files={
        "AGENTS.md": FileEntry(content="You are an email triage assistant."),
        # Link to the deep-research skill repo. Omit commit_id to always
        # resolve to the latest version, or pin it for reproducibility.
        "skills/research": SkillEntry(repo_handle="deep-research"),
        # Link to another agent repo.
        "agents/scheduler": AgentEntry(repo_handle="calendar-agent"),
    },
)
print(url)

​
Push parameters

Both push_agent / pushAgent and push_skill / pushSkill accept the following parameters:
ParameterTypeDescription
identifierstringThe repo’s identifier.
filesdict[str, Entry | None]Map of file path to Entry. Pass None / null to delete a path in this commit.
parent_commit / parentCommitstring (optional)Parent commit hash prefix for optimistic concurrency. Must be 8–64 characters when provided. If it doesn’t match the latest commit, the API returns a 409 conflict.
descriptionstring (optional)Repo description. Set on creation or patched on update.
readmestring (optional)Repo readme content.
tagsstring[] (optional)Repo tags.
is_public / isPublicboolean (optional)Whether the repo is publicly discoverable.

​
Pull an agent

Pull a snapshot of an agent repo. By default the latest commit is returned; pass a commit hash or tag via version (or embed it in the identifier as owner/name:version) to pull a specific version:
Identifier formats: the identifier argument accepts three forms:
  • name: resolves against the current workspace owner.
  • owner/name: fully qualified.
  • owner/name:version: pinned to a specific commit hash or tag.
The optional version argument overrides any version embedded in the identifier. If neither is provided, the latest commit is returned.
from langsmith import Client

client = Client()

agent = client.pull_agent("email-assistant")
print(agent.commit_hash)
print(list(agent.files))

# Pull a specific commit.
pinned = client.pull_agent("email-assistant", version="7ca95573")

# Pull a tagged commit (for example, the production tag).
prod = client.pull_agent("email-assistant:production")

​
Pull a skill

Pull a snapshot of a skill repo. Works identically to pull_agent but returns a SkillContext: 
from langsmith import Client

client = Client()

skill = client.pull_skill("deep-research")
print(skill.files["SKILL.md"].content)

​
Pull parameters

Both pull_agent / pullAgent and pull_skill / pullSkill accept the following parameters:
ParameterTypeDescription
identifierstringThe repo’s identifier. May include an inline version: owner/name:version.
versionstring (optional)Commit hash or tag to pull. Overrides any version embedded in the identifier.
pull_agent returns an AgentContext; pull_skill returns a SkillContext.

​
Check whether a repo exists

Use these methods to check whether an agent or skill repo exists in your workspace before pushing or pulling: 
from langsmith import Client

client = Client()

if client.agent_exists("email-assistant"):
    print("agent already exists")

if not client.skill_exists("deep-research"):
    print("skill not found")

​
List agents and skills

List repos of either type, with optional filters for visibility, archived state, and a search query: 
from langsmith import Client

client = Client()

# Python returns a paginated response.
result = client.list_agents(limit=20, query="email")
for repo in result.repos:
    print(repo.repo_handle)

skills = client.list_skills(is_public=True)
ParameterTypeDescription
limitint (Python only)Maximum number of repos to return per page. Defaults to 100.
offsetint (Python only)Number of repos to skip. Defaults to 0.
is_public / isPublicboolean (optional)Filter to only public (or only private) repos.
is_archived / isArchivedboolean (optional)Filter by archived state. Defaults to False.
querystring (optional)Search query across repo handle, owner handle, description, and tags.
Python’s list_agents / list_skills return a paginated response object with explicit limit and offset for manual pagination. TypeScript’s listAgents / listSkills return an AsyncIterableIterator that handles pagination automatically as you consume it.

​
Delete an agent or skill

This operation is permanent and cannot be undone. Deleting a repo also removes its owned child file repos.
Delete an agent or skill repo from your workspace: 
from langsmith import Client

client = Client()

client.delete_agent("email-assistant")
client.delete_skill("deep-research")
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.