#Apache 2.0

ByteDance-Seed

EdgeBench

★ 466

EdgeBench: Unveiling scaling laws of learning from real-world environments

qdrant

qdrant-js

★ 465

JavaScript/Typescript SDK for Qdrant Vector Database

josstei

maestro-orchestrate

★ 465

Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools

eval-sys

mcpmark

★ 465

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

neuml

rag

★ 464

🚀 Retrieval Augmented Generation (RAG) with txtai. Combine search and LLMs to find insights with your own data.

simonw

llm-gemini

★ 463

LLM plugin to access Google's Gemini family of models

opensolon

solon-ai

★ 463

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

superserve-ai

superserve

★ 462

Sandbox infrastructure for AI Agents

trotsky1997

OpenFugu

★ 462

Open reimplementation of Sakana Fugu — the 'one model to command them all' LLM orchestrator. Read → run → train → serve.

google-ai-edge

litert-samples

★ 462

LiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.

paradigmxyz

evmbench

★ 460

Collab with OpenAI. A benchmark and harness for finding and exploiting smart contract bugs

ApodexAI

AgentHarness

★ 459

Evaluation harness for Apodex-1.0 on public deep-research benchmarks.

hashgraph-online

registry-broker-skills

★ 459

AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.

jacbz

Lofi

★ 458

ML-supported lo-fi music generator

leyten

shard

★ 458

Pipeline-parallel LLM inference across GPUs on separate machines.

guidewire-oss

fern-platform

★ 457

Unified test intelligence platform with multi-format ingestion, real-time analytics, and AI-powered insights via LLM integration

MTSWebServices

RecTools

★ 457

RecTools - library to build Recommendation Systems easier and faster than ever before

EvolvingAgentsLabs

evolving-agents

★ 455

Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined guardrails.

awslabs

graphstorm

★ 455

Enterprise graph machine learning framework for billion-scale graphs for ML scientists and data scientists.

galdawave

pickle-rick-extension

★ 454

This extension transforms the Gemini CLI into "Pickle Rick," a hyper-intelligent, arrogant, yet extremely competent engineering persona. It enforces a rigid, iterative software development lifecycle through continuous AI agent loops. Emphasizing "God Mode" coding practices and a disdain for