Skip to main content

No project description provided

Project description

MenschMachine library

Problems / Bugs

Usage matrix:

OpenAI Anthropic DeepSeek Gemini
Direct Y with func Y with func ? ?
OpenRouter ? Y with func Y no func N (errors with funcs)
LiteLLM proxy ? N (errors with funcs) ? N (errors with funcs)

LiteLLM

  • errors when using tools with anthropic and gemini (different errors)

OpenRouter

  • gemini hangs after first tool result

TODO

  • retry failed patch as aider does
  • MM().ask(prompt, max_costs=0.10)
  • add whoosh for local (file) search
  • Change Remove Operation from first line (contents) to last line (content)
  • add a line-numbering agent for callbacks for Remove-Operatin

Project details


Download files

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

Source Distribution

menschmachine-0.1.210.tar.gz (32.1 kB view details)

Uploaded Source

Built Distribution

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

menschmachine-0.1.210-py3-none-any.whl (45.0 kB view details)

Uploaded Python 3

File details

Details for the file menschmachine-0.1.210.tar.gz.

File metadata

  • Download URL: menschmachine-0.1.210.tar.gz
  • Upload date:
  • Size: 32.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.12.8 Darwin/24.3.0

File hashes

Hashes for menschmachine-0.1.210.tar.gz
Algorithm Hash digest
SHA256 45cf0d148abca7374d0d7da82331616cce60315e76d51402ab146c1fd6b89165
MD5 f94526f6ff37bc74dd9e0327fc828837
BLAKE2b-256 b2801cf4eca0ba6be4779aabfcc5c4be206c8735a4d1ea55ca02402c4a9f3023

See more details on using hashes here.

File details

Details for the file menschmachine-0.1.210-py3-none-any.whl.

File metadata

  • Download URL: menschmachine-0.1.210-py3-none-any.whl
  • Upload date:
  • Size: 45.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.12.8 Darwin/24.3.0

File hashes

Hashes for menschmachine-0.1.210-py3-none-any.whl
Algorithm Hash digest
SHA256 380e28b88f9b2bdbb0f36bb627d763eab86a838304504826a2dfbe8c6d49aef6
MD5 a5cb2ebb94d8574104ee21b95821cee4
BLAKE2b-256 79d2a494c4eab3ddfcf0a837b9adbf142280cad08ea9f99ac13f7b4948a3a611

See more details on using hashes here.

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