agency
gollum
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
agency
-
Agency: Pure Go LangChain Alternative
I would, at the very least, wrap the errors being returned inside the process function https://github.com/neurocult/agency/blob/14b14e50a7570189388...
Or, I suppose the user must handle exception behavior in their custom `OperationHandler`
-
🕵 Agency: The Go Way to AI. Part 1
Recognizing the need for a Go-friendly tool that’s simple yet powerful, we developed Agency. This Go library, designed with a clean approach, matches Go's strengths in a static type system and high performance. It's our answer to bringing easy-to-use, efficient AI capabilities to Go developers.
gollum
-
From slow to SIMD: A Go optimization story
I did a similar optimization via https://github.com/viterin/vek as the SIMD version. Some somewhat unscientific calculations showed a 10x improvement staying in float32: https://github.com/stillmatic/gollum/blob/07a9aa35d2517af8cf...
TBH my takeaway was that it was more useful to use smaller vectors as a representation
-
Agency: Pure Go LangChain Alternative
I like Go a lot for working with OpenAI etc, it's 'just' API calls and Go is great at that. I've opensourced some bits here: https://github.com/stillmatic/gollum -- in particular, function dispatch (given a prompt, return an arbitrary Go struct) is really nice, as is a very fast in-memory KNN index.
-
Introducing TypeChat from Microsoft
I've written a version of this in Golang: https://github.com/stillmatic/gollum/blob/main/dispatch.go
```go
-
FANN: Vector Search in 200 Lines of Rust
I have gotten 10x speedups with SIMD on modern hardware. Goroutines make this actually fairly tricky, as you essentially have to process all the events and then sort the entire array, which is usually the bottleneck. The heap adds a small amount of complexity but is significantly more efficient, feels like good ROI.
https://github.com/stillmatic/gollum/blob/main/vectorstore.g...
What are some alternatives?
langroid - Harness LLMs with Multi-Agent Programming
CopilotKit - Build in-app AI chatbots 🤖, and AI-powered Textareas ✨, into react web apps. [Moved to: https://github.com/CopilotKit/CopilotKit]
langchain - 🦜🔗 Build context-aware reasoning applications
ts-patch - Augment the TypeScript compiler to support extended functionality
go-openai - OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go
ai-agents-laravel - Build AI Agents for popular LLMs quick and easy in Laravel
humanscript - A truly natural scripting language
voy - 🕸️🦀 A WASM vector similarity search written in Rust
yay - 🐹 interact with openai api from command line
TypeChat - TypeChat is a library that makes it easy to build natural language interfaces using types.
langchaingo - LangChain for Go, the easiest way to write LLM-based programs in Go
Weaviate - Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.