Highlights
Stars
- All languages
- Arduino
- Assembly
- Astro
- Awk
- Batchfile
- Bikeshed
- Blade
- C
- C#
- C++
- CSS
- Clojure
- CoffeeScript
- Cuda
- Dart
- Dockerfile
- Eagle
- Elixir
- Elm
- Emacs Lisp
- Erlang
- Gherkin
- Go
- Groff
- HCL
- HTML
- Haml
- Handlebars
- Haskell
- JSON
- Java
- JavaScript
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lean
- Less
- LiveScript
- Lua
- MATLAB
- MDX
- Makefile
- Markdown
- Mermaid
- Mustache
- Nim
- Nunjucks
- OCaml
- Objective-C
- Objective-C++
- PHP
- PLpgSQL
- Perl
- PostScript
- Processing
- Pug
- Python
- R
- ReScript
- Reason
- Rich Text Format
- Ruby
- Rust
- SCSS
- SVG
- Scala
- Shell
- Smarty
- Starlark
- Stylus
- Svelte
- Swift
- TeX
- TypeScript
- V
- Vim Script
- Vue
- WebAssembly
- Zig
🚀🚀🚀A faster, better and more stable Redis desktop manager [GUI client], compatible with Linux, Windows, Mac.
Open Source TypeScript AI Agent Framework with built-in LLM Observability
A service that monitors API specification changes from AI providers
Universal skills loader for AI coding agents - npm i -g openskills
CLI to migrate TypeScript projects away from `baseUrl` and `rootDir` usage
The OpenRouter provider for the Vercel AI SDK contains support for hundreds of models through the OpenRouter chat and completion APIs.
Load node modules according to tsconfig paths, in run-time or via API.
Replace alias paths with relative paths after typescript compilation
Add long-term memory to any AI in minutes. Self-hosted, open, and framework-free.
A faster than tiktoken tokenizer with first-class support for Vercel's AI SDK.
dqbd / tiktoken
Forked from openai/tiktokenJS port and JS/WASM bindings for openai/tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
TypeScript's 1:1 validator, optimized from editor to runtime
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)
We propose a pioneering benchmark to evaluate LLM agents' ability to improve over time in streaming scenarios
Open-source search and retrieval database for AI applications.
"Context engineering is the delicate art and science of filling the context window with just the right information for the next step." — Andrej Karpathy. A frontier, first-principles handbook inspi…
HTML processor powered by plugins part of the @unifiedjs collective
τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment
Visual testing tool for MCP servers
🦔 PostHog provides open-source web & product analytics, session recording, feature flagging and A/B testing that you can self-host. Get started - free.