hash
axflow
hash | axflow | |
---|---|---|
7 | 3 | |
951 | 1,085 | |
1.4% | 1.3% | |
9.9 | 9.2 | |
7 days ago | 2 months ago | |
TypeScript | TypeScript | |
GNU General Public License v3.0 or later | MIT License |
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.
hash
-
GAMA Platform: building spatially explicit agent-based simulations
The founders of stackoverflow also founded a similar project
https://github.com/hashintel/hash/tree/main/apps/engine
- Released error-stack v0.3.0
- Top OpenAI Tools, Examples & Use Cases
-
How should I propagate my errors to include a custom message, an exit code, and the original error?
Check out error_stack, which allows attaching custom messages, preserves the original error, and allows exit codes
-
Error Handling with error-stack
Feel free to ask me any questions on error-stack, either here or over at our repository!
-
Announcing error-stack: a context-aware error library that supports arbitrary attached user data!
hashintel/hash#602
axflow
- Axflow: A TypeScript Framework for AI
- We built a framework to build AI applications with TypeScript
-
Show HN: Zero-dependency, TypeScript SDK for building robust NLP applications
Hey HN!
We just released a new library for building LLM-powered applications: @axflow/models. It is part of a larger suite of libraries we're developing for TypeScript developers working with generative AI.
This library provides the simplest APIs for 1) invoking the most popular LLM and embedding models (openai, anthropic, cohere, huggingface, etc.) 2) streaming LLM responses to clients, including augmenting the streams with additional arbitrary data and 3) building client-side applications with React hooks.
@axflow/models has zero dependencies and is built using only the JavaScript standard library. As such, it works in all environments including edge environments like the Next.js edge runtime.
We'd love any feedback you may have. You can check out the code and more on our GitHub (https://github.com/axflow/axflow)
What are some alternatives?
moon - A task runner and repo management tool for the web ecosystem, written in Rust.
rivet - The open-source visual AI programming environment and TypeScript library
hashes - Collection of cryptographic hash functions written in pure Rust
chatgpt-plugin - Powered by AI Playgrounds by E2B. Code interpreter on steroids for ChatGPT. Run any language, any terminal process, use filesystem freely. All with access to the internet. [Moved to: https://github.com/e2b-dev/llm-code-interpreter]
semantic-source - Parsing, analyzing, and comparing source code across many languages
llm-client - LLMClient - JS/TS Use prompt signatures, Agents, Reasoning, Function calling, RAG and more. Based on the Stanford DSP Paper
simuwaerm - A simple heat simulation in pure Rust.
E2B - Secure cloud runtime for AI apps & AI agents. Fully open-source.
text - Haskell library for space- and time-efficient operations over Unicode text.
llm-code-interpreter - [DEPRECATED] Powered by AI Playgrounds by E2B. Code interpreter on steroids for ChatGPT. Run any language, any terminal process, use filesystem freely. All with access to the internet.
unordered-containers - Efficient hashing-based container types
chatflow - Leveraging LLM to build Conversational UIs