Invariant Labs

👀 removing images without user confirmation?

20.02.2025 08:30 — 👍 0    🔁 0    💬 1    📌 0

If you run your tests with the Swarm wrapper, all your runs will automatically be recorded in Explorer.

Of course, you also integrate non-Swarm agents or standard agent logs.

Learn more about it here: explorer.invariantlabs.ai/docs/testing...

20.02.2025 08:29 — 👍 1    🔁 0    💬 0    📌 0

🐝 Have you built an agent with OpenAI's Swarm, but you're unsure about shipping?

Invariant offers a simple wrapper for the Swarm class, making it easy to automatically trace your agent for testing and observability, to ensure your agent _works_.

20.02.2025 08:29 — 👍 2    🔁 0    💬 1    📌 0

🕵️‍♀️‍Check out the documentation to learn about all the ways you can filter traces in Explorer.

Docs: explorer.invariantlabs.ai/docs/explore...

12.02.2025 07:23 — 👍 0    🔁 0    💬 0    📌 0

👀 Trying to find specific details in your agent logs but drowning in the noise?

Explorer allows you to search for either keywords, annotations or other details to quickly identify bugs, security issues and failure modes.

12.02.2025 07:23 — 👍 1    🔁 0    💬 1    📌 0

GitHub - invariantlabs-ai/explorer: A better way of testing, inspecting, and analyzing AI Agent traces. A better way of testing, inspecting, and analyzing AI Agent traces. - invariantlabs-ai/explorer

Explorer Repo: github.com/invariantlab...
Hosted Explorer: explorer.invariantlabs.ai

07.02.2025 14:08 — 👍 0    🔁 0    💬 0    📌 0

Need a quick trace viewing tool for an LLM project that you're building?

1. > pip install invariant-ai
2. > invariant explorer
3. > open localhost

That's it.

Now you can push and inspect your traces in OAI format. Let us know what you think!

Docs: explorer.invariantlabs.ai/docs/explore...

07.02.2025 14:08 — 👍 1    🔁 0    💬 1    📌 0

GitHub - invariantlabs-ai/invariant: A framework-less approach to robust agent development. A framework-less approach to robust agent development. - invariantlabs-ai/invariant

Learn more about Testing here:

Repo: github.com/invariantlab...
Docs: explorer.invariantlabs.ai/docs/testing/

06.02.2025 13:43 — 👍 0    🔁 0    💬 0    📌 0

To make things easier, testing also integrates with Explorer, allowing you to keep track visually of your test runs.

06.02.2025 13:43 — 👍 0    🔁 0    💬 1    📌 0

Struggling to ensure consistency with your agent's reliability, especially with tool calling?

Testing is our lightweight, pytest-based OSS library to write and run agent tests.

It provides helpers and assertions that enable you to write robust tests for your agentic applications.

06.02.2025 13:43 — 👍 2    🔁 1    💬 1    📌 0