- All languages
- Assembly
- Astro
- AutoIt
- Ballerina
- Batchfile
- Bikeshed
- C
- C#
- C++
- C3
- CMake
- CSS
- Chapel
- Clojure
- Common Lisp
- Crystal
- Cuda
- Cython
- D
- Dart
- Dockerfile
- Elixir
- Elm
- Emacs Lisp
- Erlang
- F#
- Fluent
- Fortran
- FreeMarker
- GAP
- GDScript
- GLSL
- Go
- Groovy
- HCL
- HLSL
- HTML
- Hack
- Haml
- Handlebars
- Haskell
- Haxe
- Inno Setup
- Java
- JavaScript
- JetBrains MPS
- Jinja
- Julia
- Jupyter Notebook
- Kotlin
- LLVM
- Lua
- MATLAB
- MDX
- MLIR
- Makefile
- Markdown
- 8000 Mercury
- Mojo
- Mustache
- NSIS
- Nim
- Nix
- Nushell
- OCaml
- Objective-C
- PDDL
- PHP
- PLSQL
- PLpgSQL
- Pascal
- Perl
- Pony
- PowerShell
- Processing
- Python
- QML
- R
- Racket
- Red
- Riot
- Roff
- Ruby
- Rust
- SCSS
- Scala
- ShaderLab
- Shell
- Standard ML
- Starlark
- Svelte
- Swift
- TeX
- Text
- TypeScript
- V
- Vala
- Vim Script
- Visual Basic .NET
- Vue
- WebAssembly
- Xtend
- YAML
- ZAP
- ZIL
- Zig
Starred repositories
A minimal LLM-powered zero-day vulnerability scanner by AISLE.
Git for the intent behind agent-written code. Records what your coding agent decided and why, and links every commit to it.
Fast, accurate OCR with correctness assessment.
Saving your tokens 🔥! SparseRead enables AI agents to selectively read what matters across diverse information sources.
An inference framework that adapt to diverse and dynamic agent workloads
A persistent, file-based memory layer for coding agents — give Claude Code, Codex & others a project brain (durable decisions, requirements, constraints) via a zero-dependency CLI.
A curated list of foundational blueprints, functional frameworks, and technical guides for building compounding, AI-compiled knowledge bases.
Claude Code plugin that turns the podcasts you listen to on Spotify into a cited LLM wiki: one page per topic, every claim linked to its episode.
🦍 Memorilla: Latent Semantic Memory for LLMs
Lot Map for Claude Code: a live map beside the chat that shows what the agent is doing. Tool calls, model steps, hooks, skills and subagents light up as they happen. Local only, in 7 languages.
Monitors your RAM and reports any "quite terrible" unused capacity directly to the CEO of OpenAI.
Object-storage native graph database with branching and typed ontology
The open, self-hostable alternative to closed AI bots. Production-ready, fully customizable, and plugs into every stack: any agent, any model, any tool.
One VM for every project. An isolated sandbox with your project’s toolchain, ready for you or a coding agent to start coding
Complete logs of the experiments in the blog post 'LLMs can understand and write neural network weights'
Next Generation Agentic Proxy for AI Agents and MCP servers
The Quality Playbook is an open-source skill that turns AI coding agents into rigorous quality engineers. Point it at your code, in any language. Feed it whatever docs you have: READMEs, GitHub iss…
A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM model/KV-cache insights for NVIDIA, AMD, and Intel GPUs (plus Huawei Ascend on Linux).
Any model. Any hardware. Zero compromise. Built with @ziglang / @openxla / MLIR / @bazelbuild
NVIDIA Kubernetes Engine (NVKE). A management plane for GPU Kubernetes on bare metal.
A Spec-Driven Multi-Agent Framework for AI-Assisted Software Engineering
Plan, apply and roll back changes to a production ontology, with a blast radius report and a proof an auditor can re-check.
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
Route to the cheapest model in claude code for your task using jev-router
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfa…
HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, …