AI ओपन सोर्स प्रोजेक्ट

AgentsMesh

The AI Agent Workforce Platform. Run a hundred AI coding agents across your own machines — schedule, isolate, and steer them all from one console.

Vearch

Distributed vector search for AI-native applications

VDP

🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications

Fairlearn

A Python package to assess and improve fairness of machine learning models.

777genius/agent-teams-ai

You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/Git

dstack

A unified orchestration layer for heterogeneous AI compute. It standardizes how to manage compute and run training and inference on GPU clouds, Kubernetes, VMs, or bare-metal clusters.

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Envoy AI Gateway

Based on Envoy’s AI gateway, manages LLM traffic in cloud native environments.

VeOmni (ByteDance)

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

envd

🏕️ Reproducible development environment for humans and agents

any-llm

Mozilla's unified library of interfaces for multiple LLM providers.

Helios (PKU-YuanGroup)

Helios: Real Real-Time Long Video Generation Model

Future AGI

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

llama.vim

Vim plugin for LLM-assisted code/text completion

FastSD CPU

The Stable Diffusion implementation can also quickly generate images on the CPU.

SIA

SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task.

Neuron AI

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that interact with your data and UI.

DeepSpeed-Mii

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

Diffrax

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Agentset

The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.

NeMo-RL

Scalable toolkit for efficient model reinforcement

transcribe.cpp

ggml speech-to-text inference for 16+ model families

ADR (Uber)

ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.

DeePMD-kit

Build molecular dynamic learning functions with deep learning.