llm_agents
leaptable
llm_agents | leaptable | |
---|---|---|
6 | 3 | |
884 | 162 | |
- | - | |
3.5 | 10.0 | |
about 2 months ago | 7 months ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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.
llm_agents
- Build your own agents which are controlled by LLMs
-
LangChain Announces 10M Seed Round
In case anyone misses it buried in the readme, the accompanying blog post looks like the solid introduction to the subject that I've been looking for: https://www.paepper.com/blog/posts/intelligent-agents-guided...
leaptable
-
AI and the End of Programming
As the parent comment says, LLMs are very good at giving plausible answers. Without checking each cell, then the data you eventually output becomes suspect.
We've been trying to solve this problem at Leaptable (https://leaptable.co/). The crux is that while LLMs are still a black box, transparency in the way AI Agents interact with LLMs is key. For instance, seeing the outputs of each step in a chain-of-thought sequence helps debug common fallacies in the way the LLMs reason and built trust.
-
Textual Adds a Command Palette
This is very cool and I can see how it'd be helpful for users. How did you arrive at this feature? Slash command's discoverability is key. The commands serve as documentation and hints. Additionally, love the fact that users can create customized commands as shortcuts for frequent workflows or other logic. Reduces repetitive clicking/navigating.
As the builder of LeapTable (https://github.com/peterwnjenga/leaptable), an open-source low-code database powered by AI agents, one of the first pieces of feedback I received from early users was the desire for slash commands similar to Notion.
After evaluating different options, I settled on incorporating PlateJS (https://platejs.org/docs/mention) to enable @mention-style slash commands in LeapTable's React-based interface.
PlateJS proved to be a great fit for easily bringing robust slash command capabilities into our webapp. The @mention commands allow for convenient execution of actions, integration with external services, and automation workflows.
For any other React developers looking to incorporate flexible, Notion-style slash commands into their webapps, I highly recommend checking out PlateJS. It provided the perfect building block for enabling rich slash command interactions in LeapTable.
-
Unicorn Startup Airtable Lays Off 27% of Firm, Shifts Focus to Big Clients
Baserow is cool. We evaluated it within our company a few months ago and eventually settled for Nocodb (https://nocodb.com/) - easy to run, more mature.
Leaptable is another Open Source framework like Airtable I saw recently with support for AI Agents. https://github.com/peterwnjenga/leaptable
What are some alternatives?
llm_osint - LLM OSINT is a proof-of-concept method of using LLMs to gather information from the internet and then perform a task with this information.
nocodb - 🔥 🔥 🔥 Open Source Airtable Alternative
langchain - âš¡ Building applications with LLMs through composability âš¡ [Moved to: https://github.com/langchain-ai/langchain]
vektor - a mini vector database implementation that intends to be educational and interpretable
langchain-tutorials - Overview and tutorial of the LangChain Library
refinery - The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.
bot - GPT-powered bot that can automate complex online tasks using both the web browser and API calls.
grist-core - Grist is the evolution of spreadsheets.
gptroles - Interact with ChatGPT and let it interact with your computer
LinkedInGPT - Skynet
yolov5 - YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
docarray - Represent, send, store and search multimodal data