feat(cli): deepagents deploy

[Sydney Runkle (sydney-runkle)]

Adds new deepagents deploy command. Documentation

Project layout

src/
  AGENTS.md        # required — system prompt + read-only /memories/AGENTS.md
  skills/          # optional — seeded under /skills/
  mcp.json         # optional — HTTP/SSE MCP servers
  deepagents.toml

deepagents.toml

[agent]
name = "my-agent"
model = "anthropic:claude-sonnet-4-6"

# [sandbox] is optional — omit to run tools in-process.
[sandbox]
provider = "langsmith"   # none | langsmith | daytona | modal | runloop
scope    = "thread"      # thread | assistant
# template = "deepagents-deploy"
# image    = "python:3"

Skills, MCP servers, and model deps are auto-detected.

CLI

deepagents init                         # scaffold deepagents.toml in cwd
deepagents dev    --config src/deepagents.toml [--port 2024]
deepagents deploy --config src/deepagents.toml [--dry-run]

Runtime

• System prompt: src/AGENTS.md verbatim, baked in at build time.
• Memories: /memories/AGENTS.md in the LangGraph store, namespace (assistant_id, "memories"). Read-only at runtime — edit the source file and redeploy.
• Skills: /skills/<skill>/... in the store, namespace (assistant_id, "skills"). Also read-only.
• Sandbox: default backend. Per-thread cache by default; set [sandbox].scope = "assistant" to share one sandbox across all threads of an assistant. Omit [sandbox] entirely to fall back to an in-process StateBackend.
• MCP: HTTP/SSE only. Stdio is rejected at bundle time.

Gotchas

• /memories/ and /skills/ are read-only. Edit source files and redeploy.
• deepagents deploy creates a new revision on every invocation (full cloud rebuild). Use deepagents dev for iteration.
• The in-process sandbox cache does not survive process restarts; thread-scoped sandboxes get re-provisioned if the server recycles.
• Custom Python tools are not supported — use MCP servers.

[hari-dhanushkodi]

thanks for implementing!!

[hari-dhanushkodi]

this command seems to be ignoring colors + interactive input.. if you run langgraph deploy directly you will be prompted for your api key, eg:

❯ langgraph deploy -c /var/folders/sv/n1qqfjs90h73nr_87d7bprwh0000gn/T/deepagents-deploy-2s8d0lqh/langgraph.json --name deepagents-deploy-coding-agent --verbose
Note: 'langgraph deploy' is in beta. Expect frequent updates and improvements.

⚠️  Security Recommendation: Consider switching to Wolfi Linux for enhanced security.
   Wolfi is a security-oriented, minimal Linux distribution designed for containers.
   To switch, add '"image_distro": "wolfi"' to your langgraph.json config file.

No LangSmith API key found. Create one at Settings > API Keys in LangSmith.
Enter LangSmith API key:

I actually do think this is an important part of the experience, but I'm not sure how to fix. I couldn't get it working locally :( Maybe we have to pull in langgraph-cli code and call it directly isntead of subprocess? idk