- All languages
- Assembly
- Astro
- Awk
- C
- C#
- C++
- CSS
- Cuda
- Dart
- Dockerfile
- Go
- HTML
- Haskell
- Java
- JavaScript
- Jupyter Notebook
- Just
- Kotlin
- Lua
- MDX
- Makefile
- Markdown
- Max
- Metal
- Mojo
- Nim
- Nunjucks
- OCaml
- Objective-C
- Odin
- PHP
- Pascal
- Perl
- PowerShell
- Python
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Svelte
- Swift
- TypeScript
- Vim Script
- Vue
- YAML
- YARA
- Zig
Starred repositories
PII mask/unmask reverse-proxy for Claude Code — hybrid proxy + hooks, unmask-on-wire
[ICML 2026] Coloring the Noise: Adversarial Sobolev Alignment for Faithful Image Super Resolution (Official Implementation)
Archives information on Reckless Ben vs BAM
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.
Code for Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers
Grafeo is a pure-Rust, high-performance graph database that can be embedded as a library or run as a standalone database, with optional in-memory or persistent storage. Grafeo supports both LPG and…
Turn any collection of documents into a knowledge graph. Extract entities and relationships via LLM, deduplicate with your approval. Map domains, find hidden connections, spot patterns across docum…
[IEEE Intelligent Systems] Awesome-Graph-augmented-LLM-Agent (GLA)
ICML 2026 · Plug-and-play long-term memory for LLM agents
Survey and paper list on efficiency-guided LLM agents (memory, tool learning, planning).
CLI tool and Go library for parsing and analyzing Burp Suite project files
Journaling that remembers and reasons in context. Synapse is a memory-first reflection agent built for the London LangChain x SurrealDB Hackathon. It turns unstructured reflections into a persisten…
Cyber-Zero: Training Cybersecurity Agents Without Runtime
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
Steering Llama 2 with Contrastive Activation Addition
A tiny web app comparing human and AI values on the Ingelhart–Welzel Cultural Map
LLaDA2.0-Uni: Understanding and Generation the World.
First mechanistic interpretability library for Apple's MLX framework. Train sparse autoencoders (BatchTopK, Matryoshka) on Apple Silicon.