LangGraph Agent Toolkit
Serve LangGraph agents through an authenticated HTTP API. Add streaming, persistent conversation history, managed model connections, and optional tools and observability. Use your own client or the included Streamlit interface.
Python 3.11–3.14. The API image uses Python 3.13. Existing deployments should read the 0.10.0 migration guide and changelog before upgrading.
Quickstart · Integrations · Onboarding · Memory and authentication · Deployment · Documentation · Development
What the toolkit provides
- FastAPI routes for invocation, SSE, JSON Lines, history, and feedback.
- Sync and async
AgentClientinterfaces, including multimodal messages. - SQLite or PostgreSQL checkpoints with conversation ownership and ordered updates across workers.
- Model factories with connection reuse, timeouts, bounded retries, and an optional aiohttp transport for OpenAI and Azure.
- Native LangChain agents, custom LangGraph workflows, human approvals, and optional Deep Agents.
- MCP tools, Langfuse SDK v2/v3/v4 integration, LangSmith, and local or managed prompts.
Install only the integrations that your service needs. LiteLLM, Langfuse, MCP, Deep Agents, and Streamlit are optional.
Quickstart
This local demo uses a deterministic fake model and SQLite. It needs no model key, Docker, or external service. It checks API behavior and persistence. Model quality requires separate evaluation.
Install uv, then use a fresh checkout:
git clone https://github.com/kryvokhyzha/langgraph-agent-toolkit.git
cd langgraph-agent-toolkit
uv sync --frozen --no-install-project --no-dev --extra uvicorn-backend
Create .env in this fresh checkout with these values. Use a shell without
other toolkit or tracing overrides.
USE_FAKE_MODEL=true
AUTH_MODE=trusted
AUTH_SECRET=local-demo-token
AGENT_PATHS=["langgraph_agent_toolkit.agents.blueprints.chatbot.agent:chatbot_agent"]
DEFAULT_AGENT=chatbot-agent
MEMORY_BACKEND=sqlite
SQLITE_DB_PATH=quickstart.sqlite
OBSERVABILITY_BACKEND=empty
MCP_SERVERS={}
MODEL_CONFIGS={}
LANGSMITH_TRACING=false
LANGCHAIN_TRACING_V2=false
Start the API on localhost:
uv run --no-sync python -m langgraph_agent_toolkit.run_api --host 127.0.0.1 --port 8080
In another terminal, check readiness and send a request:
export AUTH_SECRET=local-demo-token
curl --fail http://127.0.0.1:8080/health/ready
curl --fail-with-body http://127.0.0.1:8080/chatbot-agent/invoke \
-H "Authorization: Bearer ${AUTH_SECRET}" \
-H 'Content-Type: application/json' \
-d '{"input":{"message":"Hello"},"user_id":"demo-user","thread_id":"demo-thread"}'
The response content is This is a test response from the fake model. Reuse the
same user_id and thread_id for the next turn. The SQLite file retains
history after the API stops. Use the demo token only for this local example.
Use the quickstart guide for streaming, saved history, the Python client, the UI, and real-model configuration.
Choose an integration
| Need | Start with | Guide |
|---|---|---|
| Chat without tools | chatbot |
Agent patterns |
| A model that selects business tools | Native create_agent |
Usage |
| Structured extraction | create_agent_structured |
Agent patterns |
| A fixed workflow or required approval | Custom StateGraph or human-in-the-loop middleware |
Usage |
| Planning, intermediate files, and delegation | Optional Deep Agents | Deep Agents |
| Tools exposed by another service | MCP, combined with a supported agent | MCP |
| Traces, prompts, and feedback | Langfuse or LangSmith | Langfuse compatibility |
For an existing Python project, select provider and backend extras:
uv add 'langgraph-agent-toolkit[openai,uvicorn-backend,langfuse-v4]'
Follow the application onboarding guide to register agents, set identity and memory contracts, connect a client, and verify the deployment. It also gives the upgrade sequence for existing applications.
langfuse-v2, langfuse-v3, and langfuse-v4 select a Python SDK version
range. Choose one. SDK and server versions are separate. Use the compatibility
guide for supported combinations. mcp, deepagents, ui, and
openai-aiohttp are separate extras. See installation
for all options.
Memory and authentication
thread_id identifies short-term conversation state. A long-term store can use
user_id to identify one user across threads. Passing user_id does not create
a store. SQLite supplies checkpoints but has no long-term store.
The service separates conversation storage by authenticated user, agent, and public thread ID. Keep these values consistent when reading or updating history.
For one deployment per client, use one AUTH_SECRET. With AUTH_MODE=trusted,
your trusted application backend supplies the end user's user_id. That backend
must authenticate the end user. With AUTH_MODE=token, the token identifies the
user. The service rejects a different supplied user ID. See the
authentication and migration guide for curl examples and
existing checkpoint migration.
Deployment
The API can run alone under Uvicorn or Gunicorn. Docker Compose adds the optional frontend, model proxy, and observability services. Configure the full stack through the environment guide.
- The API Docker image installs and selects aiohttp for managed async OpenAI
and Azure calls. Python installations default to HTTPX. Set
LLM_HTTP_ASYNC_TRANSPORT=httpxto override the image default. - Each worker accepts eight active requests by default. Excess work receives
503before an agent run starts. The optional admission queue is bounded. - Use PostgreSQL for replicas across hosts. SQLite workers must share a file on a local filesystem. Configure persistence; the default backend is unset.
- Supervisors replace failed workers. Requests running in a failed worker can fail. The toolkit does not provide durable jobs or exactly-once tool writes.
Read deployment for health probes and worker recovery, and reliability for database pools, connection limits, timeouts, cancellation, and retry boundaries.
Documentation
Read the
documentation site or
the source guides below. The running service exposes its HTTP schema at /docs
and /openapi.json.
| Task | Guide |
|---|---|
| Make the first request | Quickstart |
| Add the toolkit to an application | Onboarding |
| Select extras and configure services | Installation, environment |
| Call the API or register an agent | Usage |
| Choose agents and tools | Integrations, MCP, Deep Agents |
| Upgrade an existing deployment | Migration, dependency review, changelog |
| Deploy and operate the service | Deployment, reliability |
| Configure Langfuse | SDK and server compatibility |
| Verify behavior and capacity | Testing, live model checks, load tests, recorded results |
Development
Install the locked dependencies and run the local tests. The pre-commit hook environments require Python 3.13.
uv sync --frozen --no-install-project --extra all
uv run --no-sync pytest
uv run --no-sync pre-commit run --all-files
Use --extra all because --all-extras selects incompatible Langfuse SDK
versions. Ordinary tests use fake models and local services. Process, Docker,
PostgreSQL, live Langfuse, and real-model checks have separate setup
requirements. Test coverage and local load results do not establish production
capacity or model quality.
See CONTRIBUTING.md for the development workflow. Examples are in scripts/python, including the Deep Agents example.
License
MIT.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file langgraph_agent_toolkit-0.10.0.tar.gz.
File metadata
- Download URL: langgraph_agent_toolkit-0.10.0.tar.gz
- Upload date:
- Size: 1.9 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ba1743cb9b7c9642efc10d1514191cbf82cc0fa480d11c66c3e65c88e5e85d09
|
|
| MD5 |
358efc2979448af48fec779756c9571b
|
|
| BLAKE2b-256 |
2f9ae925d121e2eba022d60f6ed2ab7cdf3b82874f32f13b90851c4a4c2f6b83
|
File details
Details for the file langgraph_agent_toolkit-0.10.0-py3-none-any.whl.
File metadata
- Download URL: langgraph_agent_toolkit-0.10.0-py3-none-any.whl
- Upload date:
- Size: 162.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.12.1 {"installer":{"name":"uv","version":"0.12.1","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
37fa8ec9c6955eb6ce86841426e5176850d40c80d904bf3e1e7fb630b37eaa72
|
|
| MD5 |
5606f384a7d0603e0d1b415144c21770
|
|
| BLAKE2b-256 |
75441544659d69a6847450563e558f9d077db950887ed8d71e909de927cbd041
|
