AI channel
LLM apps

Open-source LLM apps and frameworks

Most-starred projects

2,761–2,784 of 5,866
Ataraxy-Labs

opensessions

★ 1,238

tmux sidebar for coding agents — Amp, Claude Code, Codex, OpenCode. Per-thread markers, local HTTP API, live session state.

Rust
mem9-ai

mem9

★ 1,237

Unlimited memory for OpenClaw

TypeScript
NomaDamas

slides-grab

★ 1,237

Best harness + editor + linter for generating slides in Claude Code / Codex - Claude Design Open Source Alternative

HTML
★ 1,237

A fully open-source API service for fetching WeChat official-account articles and RSS subscriptions, supporting one-click export of an entire account's articles in 7 formats (Markdown/HTML/Word/PDF/EPUB/Excel/JSON), an IP proxy pool for anti-blocking, and MCP integration with various AI Agent tools.

Python
EvolvingLMMs-Lab

LLaVA-OneVision-2

★ 1,235

Fully Open Framework for Democratized Multimodal Training

Python
mescon

Muximux

★ 1,235

A self-hosted homelab dashboard with an optional built-in reverse proxy that makes stubborn apps work in iframes

JavaScript
★ 1,234

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

JavaScript
basetenlabs

truss

★ 1,233

The simplest way to serve AI/ML models in production

Python
InternScience

GraphGen

★ 1,233

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Python
★ 1,232

Agent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants

ant-research

AntOmniEvo

★ 1,230

An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.

Python

A Claude Code skill that designs and builds high-converting questionnaire-style app onboarding flows — modelled on proven conversion patterns from top subscription apps like Mob, Headspace and Noom

Chorus-AIDLC

Chorus

★ 1,229

The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

TypeScript
★ 1,229

Agentic SOC Platform: A powerful, flexible, open-source, and agent-centric automated security operations platform (AI SOC)

Python
★ 1,229

Independently authored prompt templates for AI coding agents — system prompts, tool prompts, agent delegation, memory management, and multi-agent coordination. Informed by studying Claude Code.

ASCIT31

Dark-Moon

★ 1,227

Autonomous AI pentesting engine across web, cloud, identity, CI/CD, IaC, databases, Active Directory, Kubernetes, IoT firmware and AI/LLM endpoints (OWASP LLM Top 10). Real exploits with proof for every finding. Privacy gateway: the LLM never sees your real IPs, hosts or creds; nothing leaves your perimeter.

Python
larlarua

AutoCVE

★ 1,226

Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

Python
moltlaunch

cashclaw

★ 1,224

An autonomous agent that takes work, does work, gets paid, and gets better at it.

TypeScript
yeyupiaoling

Whisper-Finetune

★ 1,223

Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment

C
Zefan-Cai

R-KV

★ 1,223

[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

Python
zjunlp

LightMem

★ 1,222

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Python