Open-source LLM apps and frameworks

brontoguana

krasis

★ 529

Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware

proffesor-for-testing

agentic-qe

★ 529

Agentic QE Fleet is an open-source AI-powered QA/QE platform designed for use with Coding Agents (works best with Claude Code) featuring specialized agents and skills to support testing activities for a product at any stage of the SDLC. Free to use, fork, build, and contribute. Based on the Agentic QE Framework created by Dragan Spiridonov.

zolotukhin

zinc

★ 529

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

adshao

flounder

★ 528

Autonomous white-hat security auditor for AI-driven code review, bug bounty research, exploit construction, and execution-grounded verification.

agencyenterprise

PromptInject

★ 528

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

badchars

darknet-mcp-server

★ 528

66-tool MCP server for dark web intelligence — breach data, ransomware tracking, Tor .onion access, malware analysis, blockchain intel, exploit search, stealer logs

microsoft

vattention

★ 528

Dynamic Memory Management for Serving LLMs without PagedAttention

my-claude-utils

clsh

★ 528

Access your terminal and your AI agent from any device — phone, tablet, desktop.

actions

ai-inference

★ 527

An action for calling AI models with GitHub Models

AThevon

TokenEater

★ 527

Native macOS app to monitor Claude AI usage limits and watch your coding sessions live

datawhalechina

easy-langent

★ 527

A tutorial series on "langent", a portmanteau of "lang" and "agent".

jerryjliu

liteparse_samples

★ 527

Interactive samples/demos for LiteParse: a fast, local, model-free document parser

lucasjinreal

Crane

★ 527

A Pure Rust based LLM, VLM, VLA, TTS, OCR Inference Engine, powering by Candle & Rust. Alternate to your llama.cpp but much more simpler and cleaner..

ZaxbyHub

opencode-swarm

★ 527

Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.

CerebriumAI

examples

★ 526

Examples for Cerebrium Serverless GPUs

concierge-hq

concierge

★ 526

🚀 Universal SDK for building next-gen MCP servers

jatechan

ai-data-extractor

★ 526

Free open-source extractor for AI coding assistant chat histories. Supports Claude Code, Cursor, Windsurf, Aider, Cline/Roo Code and more

vanzan01

claude-code-sub-agent-collective

★ 526

🧠 Context Engineering Research - Not just another agent collection, but using research and context engineering to function as a collective. Hub-and-spoke coordination through Claude Code.

farlume

termish

★ 525

Open-source mobile SSH/Mosh terminal and native AI workspace for Android and iOS.

microsoft

PowerAppsCodeApps

★ 525

Create custom web applications to run within Power Apps!

ome-projects

ome

★ 525

Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton

pab1it0

prometheus-mcp-server

★ 525

A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.

unbody-io

unbody

★ 525

The Supabase of AI era. A modular, open-source backend for building AI-native software — designed for knowledge, not static data.

Muvon

octocode

★ 524

Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in one Rust binary. Give Claude, Cursor, and any MCP client a deep understanding of your codebase.