AI channel
LLM apps

Open-source LLM apps and frameworks

Most-starred projects

3,769–3,792 of 5,866
SimWorld-AI

SimWorld

★ 815

SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds

Python
trailofbits

coop

★ 815

Isolated VM environment for running Claude Code and Codex

Rust
suboss87

FDEOps

★ 814

Forward deployed engineering skills for AI coding agents.

JavaScript
MicrosoftDocs

Agent-Skills

★ 813

Curated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.

★ 813

Pre-publish review for Douyin, Xiaohongshu and WeChat Channels: have AI check your post before you publish it, flagging which line crosses the line, which official rule it violates, and giving a ready-to-use fix. Calibrated against 38 real samples with 72 verifiable official rule citations, backed by a local rule base that gets more accurate the more you use it. Does not guarantee approval and does not teach how to evade review.

Python
jmuncor

tokentap

★ 812

Intercept LLM API traffic and visualize token usage in a real-time terminal dashboard. Track costs, debug prompts, and monitor context window usage across your AI development sessions.

Python
krakenfx

kraken-cli

★ 812

The first AI-native CLI for trading crypto, stocks, forex, and derivatives.

Rust
SanDiegoMachineLearning

bookclub

★ 812

Notes and links from the book club meetings

Jupyter Notebook
★ 812

Payments are broken for AI agents. Snaplii unlocks real-world commerce with a safe, tokenized payment layer — giving AI agents access to merchant-native payment credits across 500+ brands — while saving users up to 10% per transaction on top of existing deals and promotions.

Python
sstklen

trump-code

★ 812

AI decoding Trump's posts versus the stock market — 31.5M models, 61.3% hit rate, open source.

Python
★ 811

Agents Office v3 (Beta) — a headless office where AI agents do real work

JavaScript
nealbridges

VulnHunter

★ 811

Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebuilt for any agent harness.

Python

Evidence-constrained commercialization assessment with deterministic retrieval, six LLM stages, auditable scoring and checkpoint recovery.

Python
warpfront

hipfire

★ 811

RDNA-native LLM inference engine in Rust.

Rust
mybigday

whisper.rn

★ 810

React Native binding of whisper.cpp.

TypeScript
remorses

holocron

★ 810

Open source drop-in replacement for Mintlify as a Vite plugin

TypeScript
★ 810

An native MCP server extension for Ghidra

Java
christopherkarani

Wax

★ 809

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple Silicon.. No Server. No API. One File. Pure Swift

Swift
dragon1086

prism-insight

★ 808

AI-based stock analysis and trading system

Python
★ 808

Scaling Deep Research via Reinforcement Learning in Real-world Environments.

Python
inference-sh

skills

★ 808

inference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agents

Shell
regent-vcs

re_gent

★ 808

Version control for AI agents — track what your agent did, blame any line to a prompt, inspect any step.

Go
tight-studio

OpenBrand

★ 808

Extract brand assets (logos, colors, backdrops) from any website; open source alternative to Brand.dev

TypeScript