Python authoring package and CLI launcher for Managed Deep Agents.

[!IMPORTANT] Active development / private beta. Managed Deep Agents is in active development and currently in private beta. The PyPI package API and managed runtime contract may change. Join the waitlist for access and updates.

managed-deepagents is the PyPI package for authoring Managed Deep Agents in Python. It includes:

  • define_deep_agent, the Python authoring contract for managed agents.
  • define_schedule, the Python contract for managed cron schedules.
  • mda, the CLI used to build and deploy your agent to LangSmith.
  • managed_deepagents.runtime, the runtime helper used by generated managed entry modules.

Install

uv tool install managed-deepagents

[!NOTE] Private beta: dev releases only. We currently publish only PEP 440 pre-release (dev) versions and no stable version yet. uv skips pre-releases by default unless they are allowed explicitly:

uv tool install --prerelease allow managed-deepagents

This package requires Python 3.9 or newer. Each platform wheel bundles the prebuilt mda binary for its OS and CPU architecture and exposes it through the mda console script. This PyPI-installed CLI scaffolds and compiles Python projects only and vendors the Python runtime bundled with this wheel.

To start a new project:

mda init my-agent
cd my-agent
uv sync

mda init can shape the project up front — --instructions "..." (or --instructions-file <path>) writes the system prompt, --model <spec> picks the model, --memory agent opts into deployment-shared durable memory, and --no-sandbox leaves out the sandbox. Every new project includes an identity.py that explicitly selects auth.langsmith_api_key() authentication. Managed Deep Agent evals are Harbor tasks under evals/tasks/. Optionally create a minimal source task under evals/scaffold/ with mda evals init <name>, then package the managed agent and scaffolded tasks with mda evals compile .. Nothing prompts, so these commands also work in coding agents and CI scripts.

mda init my-agent --gateway runs the agent on LangSmith Gateway — a model LangSmith hosts, billed to your workspace's Gateway Credits, authenticated with a LangSmith API key instead of a model provider key of your own. It is mutually exclusive with --model, which names a provider you hold the key for.

Define an Agent

Create an agent.py that defines an agent:

from managed_deepagents import define_deep_agent

# The system prompt comes from instructions.md next to this file.
agent = define_deep_agent(
    name="research-assistant",
    model="openai:gpt-5.5",
    tools=[query_db],
)

define_deep_agent requires a static name (LangGraph assistant id and default LangSmith deployment name) and otherwise accepts the create_deep_agent keyword surface minus the managed keys: backend, store, checkpointer, memory, skills, and system_prompt. Those are provided by the managed runtime when your agent is deployed. Write the system prompt in instructions.md next to agent.py; the CLI embeds it at deploy time.

To authenticate SDK and API requests with a LangSmith workspace key while retaining MDA's thread and store authorization, declare it explicitly:

identity = define_identity(auth=auth.langsmith_api_key())

Clients send the key as x-api-key. LangSmith Cloud supplies the verification endpoint and tenant configuration; do not add those platform-owned values to the project .env.

On deploy, Context Hub stores harness files (instructions.md, skills/**). A root memory.py declaring define_memory(scope="agent") additionally mounts one deployment-shared memory tree at /memories/agent/. /memories/agent/AGENTS.md is injected every turn; other files are read on demand. Deploy never overwrites existing memories. Memory is independent of identity, and a project without memory.py mounts no durable memory.

Project Shape

my-agent/
  agent.py              # named `agent` variable
  identity.py           # managed authentication (included by `mda init`)
  instructions.md       # managed system prompt
  pyproject.toml
  .env                  # local deploy secrets, never committed
  schedules/            # optional managed cron schedules
  tools/                # optional custom tools
  middleware/           # optional middleware
  skills/               # optional skills synced to Context Hub
  sandbox/              # LangSmith sandbox (`mda init` includes this; delete to opt out)

The CLI copies your project files into the managed build and generates the entry module that connects your definition to the hosted runtime.

The agent entry must live at the project root as agent.py.

Define a Schedule

Create one file per schedule under schedules/ and define a named schedule:

# schedules/daily_digest.py
from managed_deepagents import define_schedule

schedule = define_schedule(
    cron="0 8 * * 1-5",
    timezone="America/Los_Angeles",
    prompt="Write the daily digest.",
)

mda deploy reconciles schedules as LangSmith cron jobs after the deployment is live. Declarations must be statically serializable literals or top-level constants; prompt schedules become user-message input, and stateless runs clean up their temporary thread after completion.

Sandbox

mda init scaffolds sandbox/__init__.py with a LangSmith sandbox. MDA only enables the sandbox when that declaration is present — delete sandbox/ to opt out:

from managed_deepagents import define_sandbox

sandbox = define_sandbox(
    scope="thread",
    idle_ttl_seconds=600,
)

If sandbox/setup.sh exists, MDA embeds it and runs it once when the sandbox is first provisioned. MDA owns sandbox naming, image/snapshot selection, reuse, and lifecycle.

CLI

Create a new project:

mda init my-agent

Build locally:

mda build ./my-agent

Run on the local LangGraph dev server:

mda dev ./my-agent

mda dev requires uv on PATH, but it resolves the local LangGraph dev server automatically; you do not need to install a global langgraph command.

Deploy to LangSmith:

mda deploy ./my-agent

The generated build is written to <root>/.mda/build by default.

Common deploy options:

mda deploy ./my-agent --name my-agent-dev --deployment-type dev
mda deploy ./my-agent --workspace-id "$LANGSMITH_WORKSPACE_ID"
mda deploy ./my-agent --no-wait

Read the deployed agent's server logs:

mda logs ./my-agent
mda logs ./my-agent --lines 200 --level error
mda logs ./my-agent > agent.log

In a terminal mda logs streams new output until you press Ctrl-C. When the output is piped or redirected it prints the most recent lines (1000 by default) and exits.

Tear it down again:

mda delete ./my-agent

mda delete (alias mda destroy) removes the LangSmith deployment, the tracing project created alongside it, the deployment's Context Hub repo including the per-user memory repos beneath it, and the managed sandboxes the deployment created. It asks for confirmation first; pass --yes to skip the prompt in scripts. Agent memory and thread history are not recoverable afterwards.

Sandboxes are matched by name: the runtime names each one {deployment}--{digest}, which also lets a restarted deployment re-adopt its existing sandbox instead of stranding it. The digest covers the sandbox scope plus how it was provisioned, so editing setup.sh or switching snapshots gives the next run a fresh sandbox instead of one built from the previous recipe. Sandboxes created before this behavior existed are unnamed and are left to LangSmith's idle-stop and retention window.

Before deploying, make sure your model provider key such as OPENAI_API_KEY or ANTHROPIC_API_KEY is available in the project .env, the process environment, or LangSmith workspace secrets. For LangSmith itself, set LANGSMITH_API_KEY the same way, or run interactively and press Enter at the prompt to sign in with your browser (the CLI creates a key and writes it to .env). Use LANGSMITH_WORKSPACE_ID or --workspace-id when your credentials require a workspace selection.

Project links

Data verified by PyPI on
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.5.1)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for langchain from gravatar.com langchain

Credits

Author: LangChain

GitHub Statistics

Data verified by PyPI on 
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT License (MIT)

Requires

Python >=3.10

Provides Extra

test

Tags

langchain langgraph deepagents agents cli

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

managed_deepagents-0.5.0-py3-none-win_arm64.whl (1.8 MB view details)

Uploaded Python 3Windows ARM64

managed_deepagents-0.5.0-py3-none-win_amd64.whl (1.9 MB view details)

Uploaded Python 3Windows x86-64

managed_deepagents-0.5.0-py3-none-manylinux2014_x86_64.whl (2.1 MB view details)

Uploaded Python 3

managed_deepagents-0.5.0-py3-none-manylinux2014_aarch64.whl (2.0 MB view details)

Uploaded Python 3

managed_deepagents-0.5.0-py3-none-macosx_11_0_arm64.whl (1.9 MB view details)

Uploaded Python 3macOS 11.0+ ARM64

managed_deepagents-0.5.0-py3-none-macosx_10_12_x86_64.whl (1.9 MB view details)

Uploaded Python 3macOS 10.12+ x86-64

File details

Details for the file managed_deepagents-0.5.0-py3-none-win_arm64.whl.

File metadata

File hashes

Hashes for managed_deepagents-0.5.0-py3-none-win_arm64.whl
Algorithm Hash digest
SHA256 403d2e30f9e3b3b90522b4da6f785a5c1c9997fa3def32247618b453f9f839e4
MD5 b6ff1c9c4b3495953d2868370ca110e2
BLAKE2b-256 a33ab5ca533c52f7ac807b653947b4b1f7d0577d836f42cf315f67e742c9131e

See more details on using hashes here.

Provenance

The following attestation bundles were made for managed_deepagents-0.5.0-py3-none-win_arm64.whl:

Publisher: release.yml on langchain-ai/managed-deepagents-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file managed_deepagents-0.5.0-py3-none-win_amd64.whl.

File metadata

File hashes

Hashes for managed_deepagents-0.5.0-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 f9b3f9e3ca4b8106cf9b1657b84f16a7d0c179521e99e50a5b55a5ebf96ae798
MD5 0a6bdb5450c8bfd5034d8d51b983e8c5
BLAKE2b-256 a25d1ebb9b0245536e1f39bf1b15cdb054c6b78cafe217d095c568cc328feb19

See more details on using hashes here.

Provenance

The following attestation bundles were made for managed_deepagents-0.5.0-py3-none-win_amd64.whl:

Publisher: release.yml on langchain-ai/managed-deepagents-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file managed_deepagents-0.5.0-py3-none-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for managed_deepagents-0.5.0-py3-none-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 4100f5235b055c640f45985dbf1b272ed6af7e8e8b068f1a1051944f63312afa
MD5 ee77b9402954bacf917d81eb7debb8f3
BLAKE2b-256 c83bfd111c4eea9741ea7bd662d83549731e828f0b80bd41f08e0505ece828a1

See more details on using hashes here.

Provenance

The following attestation bundles were made for managed_deepagents-0.5.0-py3-none-manylinux2014_x86_64.whl:

Publisher: release.yml on langchain-ai/managed-deepagents-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file managed_deepagents-0.5.0-py3-none-manylinux2014_aarch64.whl.

File metadata

File hashes

Hashes for managed_deepagents-0.5.0-py3-none-manylinux2014_aarch64.whl
Algorithm Hash digest
SHA256 87a6a0e224602c76a6cbdb37b4d04cc409a712442c82f05e78328f475903d031
MD5 6b4ae422f2cbf8fe449d5a663f2a80a2
BLAKE2b-256 1b637926da87950b1d417eeb3f3c36af3067bc259c719c7afd599705b7ab1002

See more details on using hashes here.

Provenance

The following attestation bundles were made for managed_deepagents-0.5.0-py3-none-manylinux2014_aarch64.whl:

Publisher: release.yml on langchain-ai/managed-deepagents-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file managed_deepagents-0.5.0-py3-none-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for managed_deepagents-0.5.0-py3-none-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 1968c3380dfe1c03de22e2ca326df060a332b80dc2ac3ccb6e4ada82863ca0cf
MD5 e0536826a3a5b453638fcb2499e2b624
BLAKE2b-256 195f0ce1d2ef83e0357e3ada1ec2b061302ccfb3697c1897796151cca86be9ab

See more details on using hashes here.

Provenance

The following attestation bundles were made for managed_deepagents-0.5.0-py3-none-macosx_11_0_arm64.whl:

Publisher: release.yml on langchain-ai/managed-deepagents-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file managed_deepagents-0.5.0-py3-none-macosx_10_12_x86_64.whl.

File metadata

File hashes

Hashes for managed_deepagents-0.5.0-py3-none-macosx_10_12_x86_64.whl
Algorithm Hash digest
SHA256 dbc61f1165e14bd572601c76069626aad5ceadfbfdb98a8336dc733ca1087bea
MD5 cff23aac5e4724449a53f6dfd8323ac8
BLAKE2b-256 0e6c4307b9a259b049c17b8298cd23f45c528f85fef8b2ce7506ffeb4c8362fb

See more details on using hashes here.

Provenance

The following attestation bundles were made for managed_deepagents-0.5.0-py3-none-macosx_10_12_x86_64.whl:

Publisher: release.yml on langchain-ai/managed-deepagents-sdk

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

0.5.1

0.5.1.dev101 pre-release

This release

0.5.0

0.5.0.dev97 pre-release

0.5.0.dev96 pre-release

0.5.0.dev90 pre-release

0.5.0.dev89 pre-release

0.5.0.dev88 pre-release

0.5.0.dev87 pre-release

0.5.0.dev86 pre-release

0.5.0.dev85 pre-release

0.5.0.dev84 pre-release

0.5.0.dev83 pre-release

0.5.0.dev82 pre-release

0.5.0.dev81 pre-release

0.5.0.dev80 pre-release

0.5.0.dev79 pre-release

0.5.0.dev78 pre-release

0.5.0.dev77 pre-release

0.4.3

0.4.3.dev98 pre-release

0.4.3.dev95 pre-release

0.4.3.dev94 pre-release

0.4.3.dev93 pre-release

0.4.2

0.4.1

0.4.0

0.4.0.dev73 pre-release

0.4.0.dev72 pre-release

0.4.0.dev71 pre-release

0.4.0.dev70 pre-release

0.4.0.dev69 pre-release

0.4.0.dev68 pre-release

0.4.0.dev67 pre-release

0.4.0.dev66 pre-release

0.4.0.dev65 pre-release

0.4.0.dev64 pre-release

0.4.0.dev63 pre-release

0.4.0.dev62 pre-release

0.4.0.dev61 pre-release

0.4.0.dev60 pre-release

0.4.0.dev59 pre-release

0.4.0.dev58 pre-release

0.4.0.dev57 pre-release

0.4.0.dev56 pre-release

0.4.0.dev55 pre-release

0.4.0.dev54 pre-release

0.3.1

0.3.0

0.2.0

0.1.3.dev51 pre-release

0.1.3.dev50 pre-release

0.1.3.dev49 pre-release

0.1.3.dev48 pre-release

0.1.3.dev47 pre-release

0.1.3.dev46 pre-release

0.1.3.dev45 pre-release

0.1.3.dev44 pre-release

0.1.3.dev43 pre-release

0.1.3.dev42 pre-release

0.1.3.dev41 pre-release

0.1.3.dev40 pre-release

0.1.3.dev39 pre-release

0.1.3.dev38 pre-release

0.1.3.dev37 pre-release

0.1.3.dev34 pre-release

0.1.3.dev33 pre-release

0.1.3.dev32 pre-release

0.1.3.dev31 pre-release

0.1.3.dev29 pre-release

0.1.3.dev28 pre-release

0.1.3.dev27 pre-release

0.1.3.dev26 pre-release

0.1.3.dev25 pre-release

0.1.3.dev24 pre-release

0.1.3.dev23 pre-release

0.1.3.dev22 pre-release

0.1.3.dev21 pre-release

0.1.3.dev20 pre-release

0.1.3.dev19 pre-release

0.1.3.dev18 pre-release

0.1.3.dev17 pre-release

0.1.3.dev16 pre-release

0.1.3.dev15 pre-release

0.1.3.dev14 pre-release

0.1.2

0.1.1

0.0.2.dev13 pre-release

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page