Skip to main content

Meshagent

MeshAgent Anthropic

The meshagent.anthropic package provides adapters to integrate Anthropic models (Messages API) with MeshAgent tools and agents.

Messages Adapter

  • AnthropicMessagesAdapter: wraps the Anthropic Messages API. It turns Toolkit objects into Anthropic tool definitions, executes tool calls, and returns the final assistant response.
from meshagent.anthropic import AnthropicMessagesAdapter

adapter = AnthropicMessagesAdapter(model="claude-3-5-sonnet-latest")

Compaction can be enabled through Anthropic context management:

adapter = AnthropicMessagesAdapter(
    model="claude-sonnet-4-5",
    context_management="auto",
    compaction_threshold=150000,
)

You can also pass base_url= to AnthropicMessagesAdapter. If omitted, MeshAgent reads ANTHROPIC_BASE_URL from the environment when constructing the provider client.

Tool Response Adapter

AnthropicMessagesToolResponseAdapter converts a tool's structured response into Anthropic tool_result blocks that can be inserted back into the conversation.


Learn more about MeshAgent on our website or check out the docs for additional examples!

Website: www.meshagent.com

Documentation: docs.meshagent.com


Download files

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

Source Distribution

meshagent_anthropic-0.48.0.tar.gz (81.2 kB view details)

Uploaded Source

Built Distribution

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

meshagent_anthropic-0.48.0-py3-none-any.whl (67.9 kB view details)

Uploaded Python 3

File details

Details for the file meshagent_anthropic-0.48.0.tar.gz.

File metadata

  • Download URL: meshagent_anthropic-0.48.0.tar.gz
  • Upload date:
  • Size: 81.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for meshagent_anthropic-0.48.0.tar.gz
Algorithm Hash digest
SHA256 ba1dfbe599c5bca5e9f476d85f289b423c42f3e15d8c8077abda632ef7c40df3
MD5 5765b35c945c3ab63019efa0b3a61ffb
BLAKE2b-256 ce602515798d6e1fc7864a5adfd456eed965e742007ca3b42928b8d4f42f9006

See more details on using hashes here.

File details

Details for the file meshagent_anthropic-0.48.0-py3-none-any.whl.

File metadata

File hashes

Hashes for meshagent_anthropic-0.48.0-py3-none-any.whl
Algorithm Hash digest
SHA256 e39ea02b3466e521c14dcb9959b06642d3a9a4a96271bc2c94ea951ef61c455a
MD5 af40f89e5631248a860390d9e82f450f
BLAKE2b-256 0bee43da40a705a3f97b0ff4962143024234fda41a4af7321d7afcd5718528d4

See more details on using hashes here.

Release history Release notifications | RSS feed

Supported by

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