DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run a production agent with swappable model providers with Octop Harness

Build one deepagents-based agent that can switch between OpenAI, Anthropic, Bedrock, and preset providers.

Credentials. Model provider API keys are read from your environment, so keep them out of source code and shared workspace files.

Who it is forA Python developer who needs an agent in production and wants to change model providers without rewriting the agent.

The problemWiring a model, tools, and checkpoints into a deployable agent takes many decisions, and locking into one provider makes switching costly.

The outcomeA working HarnessAgent that answers prompts through a model chosen by configuration, with failures raised as exceptions for the host to handle.

What you need first

  • Python 3.12 or newer
  • An API key for at least one model provider (OpenAI, Anthropic, AWS Bedrock, or an OpenAI-compatible endpoint)

Steps

  1. Confirm Python 3.12 or newer is installed.
  2. Install the package with pip install octop-harness. (inferred, check the README)
  3. Export your provider API key as an environment variable in your shell.
  4. Run octop-harness init to create an agent workspace. (inferred, check the README)
  5. Create a HarnessAgent through HarnessAgentManager, send a prompt with call(), and wrap the call in exception handling.

Prompt for your agent

In the TencentCloud/octop-harness repo, create a HarnessAgentManager with one agent that uses the model provider <provider>. Send the prompt <prompt> through call() and return the reply. Verify the reply is non-empty and that exceptions from call() are caught.

Caveat. The README does not give the exact pip install command, so the install step above is inferred and should be checked against the project's install docs.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page