#Apache 2.0

NVIDIA

TensorRT-Edge-LLM

★ 585

High-performance, light-weight C++ LLM and VLM Inference Software for Physical AI

InfinitiBit

graphbit

★ 584

GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a Python wrapper for unmatched speed, security, and scalability. It enables reliable multi-agent workflows with minimal CPU and memory usage, making it production-ready for real-world enterprise environments.

ScalaConsultants

Aspect-Based-Sentiment-Analysis

★ 584

💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)

argoproj-labs

mcp-for-argocd

★ 582

An implementation of Model Context Protocol (MCP) server for Argo CD.

agentpit-io

hunter-community

★ 582

Hunter Community Edition: your private financial AI team combining AI agents and AI quant trading, open-source and self-hosted, powered by opencode, Claude Code, MCP and multi-agent orchestration, with a 15-minute Docker start.

secureagentics

Adrian

★ 581

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

MaxFreedomPollard

Compartment

★ 580

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

rtk-ai

icm

★ 580

Permanent memory for AI agents. Single binary, zero dependencies, MCP native.

SigmanticAI

apex-inference-chip

★ 579

An inference chip design that runs a real LLM (Qwen2.5-0.5B) on FPGA — one transformer decoder layer in RTL, every silicon value bit-exact against a golden model. 0.56 tok/s measured, a 140× climb, full evidence trail.

google-deepmind

simply

★ 579

Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.

v-modal

vmodal_sdk_android

★ 576

Video Search SDK for Android Kotlin. Integrate in any video app

neo4j-labs

agent-memory

★ 574

A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j.

mira-wm

mira

★ 574

Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

raids-lab

crater

★ 574

Crater is a cloud-native AI training & inference platform.

codelion

adaptive-classifier

★ 573

A flexible, adaptive classification system for dynamic text classification

talesofai

cohub

★ 572

A living space where people and agents create, play, and build together.

smg-project

smg

★ 572

Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.

Sidiora-Labs

LayerX-Network

★ 571

LayerX Network is a deterministic execution and accounting network for autonomous agents.

SouthBridgeAI

offmute

★ 570

An experiment in meeting transcription and diarization with just an LLM. Maybe I went a little overboard though

Diyago

Tabular-data-generation

★ 570

We well know GANs for success in the realistic image generation. However, they can be applied in tabular data generation. We will review and examine some recent papers about tabular GANs in action.