update Modus and Apps overview #135
Conversation
There was a problem hiding this comment.
Copilot wasn't able to review any files in this pull request.
Files not reviewed (4)
- apps/overview.mdx: Language not supported
- docs.json: Language not supported
- modus/overview.mdx: Language not supported
- styles/config/vocabularies/general/accept.txt: Language not supported
|
Running Code Quality on PRs by uploading data to Trunk will soon be removed. You can still run checks on your PRs using trunk-action - see the migration guide for more information. |
| @@ -8,50 +8,72 @@ sidebarTitle: "Overview" | |||
|
|
|||
| ## What is Modus? {/* vale Google.Contractions = NO */} | |||
|
|
|||
| Modus is an open source, serverless framework for building functions and APIs, | |||
| powered by WebAssembly. | |||
| Modus is an open source agent framework (including both a runtime and SDK) built | |||
There was a problem hiding this comment.
@johnymontana The fact that we mention WebAssembly so soon in this introduction could give the impression that you need to know WebAssembly to proceed.
I would say something like:
Modus is an open source agent framework (including both a runtime and SDK) built for Go and AssemblyScript, compiled to WebAssembly.
|
|
||
| For more inspiration, check out the | ||
| [Modus recipes](https://github.com/hypermodeinc/modus-recipes). | ||
| ### Language-agnostic logic, safely |
There was a problem hiding this comment.
I wonder if it's worth adding a small demo code block, containing a 'Hello World' function, with Golang and AssemblyScript tabs, so readers can see that we support both runtimes and the different syntax in each implementation.
| For use-cases like multi-day workflows, personal assistants, tutoring, or | ||
| domain-specific agents (for example ticketing systems), long-term context is | ||
| crucial. Modus provides it without requiring a dedicated database layer. Modus' | ||
| built-in short-term memory handles conversational state and context within | ||
| agents. Connect to long-term graph memory for externalized and persisted, but | ||
| serverless-friendly memory. You gain full "recall" - across sessions and | ||
| workflows- without maintaining stateful servers. |
There was a problem hiding this comment.
| For use-cases like multi-day workflows, personal assistants, tutoring, or | |
| domain-specific agents (for example ticketing systems), long-term context is | |
| crucial. Modus provides it without requiring a dedicated database layer. Modus' | |
| built-in short-term memory handles conversational state and context within | |
| agents. Connect to long-term graph memory for externalized and persisted, but | |
| serverless-friendly memory. You gain full "recall" - across sessions and | |
| workflows- without maintaining stateful servers. | |
| For use-cases like multi-day workflows, personal assistants, tutoring, or | |
| domain-specific agents (for example ticketing systems), long-term context is | |
| crucial. Modus provides it without requiring a dedicated database layer. Modus' | |
| built-in short-term memory handles conversational state and context within | |
| agents. You gain full "recall" - across sessions and | |
| workflows- without maintaining stateful servers. | |
| <Note> | |
| Connect to long-term graph memory, such as Dgraph, for externalised and persisted, serverless-friendly storage. | |
| </Note> |
Here the note about connecting to long term storage felt a bit odd, wdyt about putting it in a note?
|
|
||
| A few of the core Modus features include: | ||
| When you need clarity on _why_ the agent did something, no just _what_ the model |
There was a problem hiding this comment.
| When you need clarity on _why_ the agent did something, no just _what_ the model | |
| When you need clarity on _why_ the agent did something, not just _what_ the model |
No description provided.