Skillget

awesome-ai-agent-stack

mcp
Security Audit
Pass
Health Pass
  • License — License: CC-BY-4.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 28 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Curated map of 3,000+ open-source AI agent tools: coding agents, agent frameworks, MCP servers, RAG, memory and local LLMs, sorted by layer and ranked by GitHub stars.

README.md

Awesome AI Agent Stack

Awesome Website Stars Last commit

A curated, layer-by-layer map of the tools I actually use to build AI agents — from the coding agent in your terminal down to the model serving the tokens.

Browse the website · Suggest a tool

The Awesome AI Agent Stack website: 3,000+ tools in 29 categories, ranked by GitHub stars

3,000+ tools across 29 categories, ranked by GitHub stars. Each section is split into sub-groups by what the tools do. Every entry passes a mechanical bar: real, public, not archived, and actively maintained (pushed in the last 12 months); new additions also need 1,000+ stars. Every link is re-checked against the GitHub API, and projects under 10,000 stars that stop being maintained are pruned. Organized as a stack so you can find the right tool for each layer of an agent system.

On the website you can search every tool, sort any category by stars, and see the most-starred projects in each layer. It rebuilds from this README on every change.

If this list saves you time, give it a star — it helps other builders find it.

┌──────────────────────────────────────────────────────────────┐
│  Coding Agents & Harnesses  →  Skills & Context Engineering  │  ← how you build
├──────────────────────────────────────────────────────────────┤
│  Agent Frameworks  →  Memory  →  RAG  →  MCP / Tools         │  ← what you build with
├──────────────────────────────────────────────────────────────┤
│  Sandboxes & Browsers  →  Document Ingestion  →  Workflows   │  ← what agents act on
├──────────────────────────────────────────────────────────────┤
│  Gateways & Routing  →  Free LLM APIs  →  Local Inference    │  ← where tokens come from
├──────────────────────────────────────────────────────────────┤
│  Evaluation, Observability & Review  →  Reference Systems    │  ← how you ship
└──────────────────────────────────────────────────────────────┘

Contents

Coding Agents & Harnesses

The agent that writes the code. Pick one, learn it deeply.

Terminal coding agents

IDE, editor & desktop agents

Autonomous software engineers

General-purpose agent harnesses

  • NousResearch/hermes-agent - Self-improving general-purpose agent with a large skills ecosystem.
  • openclaw/openclaw - Cross-platform agent that operates the OS, not just the editor.
  • agentlas-ai/Agentlas-OS - Local-first OS staffing specialist agent teams per task.
  • truefoundry/trueforge - Open-source agent harness that turns an LLM into a working agent runtime.
  • autonomous-ai/openharness - Harness to run all your coding agents across all your machines.
  • androoAGI/starnet - Local-first desktop agent harness where agents work in a pixel-art station.
  • InsForge/InsForge - The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting,.
  • XiaoDuoYa/codex-with-chatgpt - ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
  • teaql/teaql-agent-kit - A model-mediated harness for reliable agentic software development.
  • maxritter/pilot-shell - Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software with spec-driven development,.
  • badlogic/pi-mono - AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI.
  • All-Hands-AI/OpenHands - 🙌 OpenHands: AI-Driven Development.
  • dohooo/helmor - Open-source local workbench for multi-agent software development.

Multi-agent orchestration on top of coding agents

Remote control & session monitoring

  • amantus-ai/vibetunnel - Share terminal agent sessions over the web.
  • Dimillian/CodexMonitor - macOS menu-bar monitor for Codex CLI sessions.
  • kbwo/ccmanager - Session manager for Claude Code with usage tracking.
  • omnara-ai/omnara - Remote monitoring and control for coding agents.
  • rustykuntz/clideck - Phone-friendly dashboard for CLI coding agents.
  • slopus/happy - Mobile client for monitoring Claude Code sessions.
  • soul-sol/agent-watch - Stall detection for background Claude Code and Codex jobs.
  • pacifio/atlas - Source control for agents that tracks and queries changes from multiple coding agents.
  • tiann/hapi - App for driving Codex, Claude Code and OpenCode sessions from anywhere.
  • backnotprop/plannotator - Visually annotate and review coding agent plans and diffs, and share them.
  • siteboon/claudecodeui - Use Claude Code on mobile and web via CloudCLI.
  • stefanprodan/cctop - Live top-style monitor for Claude Code sessions.
  • tomasz-tomczyk/crit - A feedback loop between you and your agent: review plans and diffs fast.
  • ewsun22/codex-manager - Desktop control center for OpenAI Codex sessions.
  • pingdotgg/t3code - Mobile, web and desktop control surface for the coding agents on your machine.
  • Louis-CFM/coucou - Notch companion that watches your coding agents and alerts you.
  • chenhg5/cc-connect - Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Feishu/Lark, DingTalk, Slack, Telegram, Disco.
  • eneskirca/nodeterm - Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/z.
  • happier-dev/happier - Web, Desktop & Mobile client and orchestrator for Codex, Claude Code, OpenCode, Pi, Cursor, Grok, Antigravity, Kimi, Augment Code, Qwen, ful.
  • AltanS/collie - Herdr mobile client for iPhone and Android. A self-hosted PWA to drive Claude Code, Pi, Codex and OpenCode in Herdr, tmux or zellij from you.
  • Ataraxy-Labs/opensessions - tmux sidebar for coding agents — Amp, Claude Code, Codex, OpenCode. Per-thread markers, local HTTP API, live session state.

Account, session & proxy managers

CI & GitHub Actions

App builders

Protocols & standards

Skills, Plugins & Context Engineering

What you put in front of the agent matters more than which agent. Skills, CLAUDE.md files, methodology.

Skill frameworks & methodology

Autonomous loops (Ralph)

Behavior-shaping skills (single-file, high leverage)

Official skill collections

Security skills

Domain & workflow skills

Hooks, status lines & usage tracking

Context compression & management

Prompt engineering

System prompt collections

Guides & best practices

Plugin & skill directories

Spec-driven development

Codebase context & packing

Skill tooling & rules sync

Agent Frameworks & Orchestration

Build your own agents and multi-agent systems.

Core frameworks

TypeScript & JavaScript frameworks

Go, Java, Rust, Ruby & other languages

Multi-agent systems

  • bytedance/deer-flow - An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the.
  • OpenBMB/ChatDev - ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration.
  • FoundationAgents/MetaGPT - The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming.
  • 2FastLabs/agent-squad - Flexible framework for managing multiple AI agents and complex conversations.
  • camel-ai/camel - Pioneering multi-agent framework for role-playing autonomous agents.
  • camel-ai/owl - Optimized workforce learning for general multi-agent assistance.
  • FoundationAgents/OpenManus - Open-source generalist multi-agent framework.
  • HKUDS/ClawTeam - Agent swarm intelligence with one-command full automation.
  • kyegomez/swarms - Enterprise-grade multi-agent orchestration framework.
  • openai/swarm - Educational framework for ergonomic, lightweight multi-agent orchestration.
  • VRSEN/agency-swarm - Reliable multi-agent orchestration framework.
  • OpenBMB/IoA - Open framework for collaborative AI agents across organizations.
  • openagents-org/openagents - The collaboration OS for AI agents.
  • multica-ai/multica - Make humans and AI agents work as one team; open-source and self-hostable.
  • MervinPraison/PraisonAI - Multi-agent framework for building always-on AI workforces.
  • yyyy231209/ai-company-framework - Open-source multi-agent orchestration for running an AI company.
  • Zerone-Laboratories/RIGEL - Multi-agentic AI assistant and builder.
  • NeuroLift-Technologies/nlt-otoi - Multi-agent orchestration with user-defined terms of interaction.
  • sipyourdrink-ltd/bernstein - Declarative governance and orchestration framework for AI agents.
  • GammaLabTechnologies/harmonist - Portable agent orchestration with mechanical protocol enforcement.
  • block/buzz - Hive-mind communication platform for coordinating agent swarms.
  • aden-hive/hive - Multi-agent harness for production AI workloads.
  • ruvnet/ruflo - Agent harness for deploying multi-player swarms and autonomous workflows.
  • cft0808/edict - OpenClaw multi-agent orchestration with nine specialized agents and dashboard.
  • CelestoAI/agentor - Open-source Claude managed-agents platform for building agent teams.
  • compozy/compozy - Operating system for AI agents that plugs into your existing agent CLIs.
  • GoogleCloudPlatform/scion - Open orchestration platform for teams of AI agents and their people.
  • Runfusion/Fusion - Software factory: multi-node agents building software around the clock.
  • phodal/routa - Workspace-first multi-agent coordination with shared specs and Kanban.
  • hfadhlullah/kaizen - Agents show the plan first, then a second agent reviews the work.
  • paperclipai/paperclip - The open-source app everyone uses to manage agents at work.
  • zhayujie/CowAgent - Open-source super AI assistant and self-evolving agent harness.
  • openakita/openakita - Open-source AI assistant framework with skills and agent architecture.
  • TokenRhythm/opensquilla - Token-efficient AI agent with higher intelligence density per budget.
  • OrchestratorInc/agent-orchestrator - Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud.
  • RunMaestro/Maestro - Agent Orchestration Command Center.
  • stellarlinkco/myclaude - Multi-agent orchestration workflow (Claude Code Codex Gemini OpenCode).
  • Kocoro-lab/Shannon - A production-oriented multi-agent orchestration framework.
  • rcortx/kiwiq - Production-grade multi-agent orchestration platform - JSON-defined agents, multi-tier memory, and built-in observability. Battle-tested on 2.
  • Mininglamp-OSS/octo-server - 🐙 The Go backend powering OCTO — an open workplace built for humans × AI agents. REST & WebSocket APIs, Lobster (AI agent) orchestration, an.
  • crestalnetwork/intentkit - IntentKit is an open-source, self-hosted cloud agent cluster that manages a collaborative team of AI agents for you.
  • nextlevelbuilder/goclaw - GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at.
  • MaxMiksa/Auto-Company - AI company framework for continuous autonomous work: 14 AI agent role definitions that research, decide, and code within human-configured goals.
  • jnMetaCode/agency-orchestrator - 🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id.
  • 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.
  • nrslib/takt - TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML.

Visual & low-code builders

  • langgenius/dify - Visual builder for agentic workflows and RAG pipelines with a rich tool ecosystem.
  • langflow-ai/langflow - Drag-and-drop builder for LangChain flows and agents.
  • inkeep/agents - Build agents in a visual builder or TypeScript SDK with two-way sync.
  • botpress/botpress - Open-source hub to build and deploy GPT/LLM agents.
  • dust-tt/dust - Custom AI agent platform to speed up knowledge work.
  • i-am-bee/agentstack - Deploy and share agents on open infrastructure, free from vendor lock-in.
  • paradigmxyz/centaur - Frontier agentic infrastructure you own; open-source agent cloud.
  • coze-dev/coze-studio - An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze.
  • melih-unsal/DemoGPT - 🤖 Create agentic apps in a second with your prompts. Everything you need to create an LLM Agent - tools, prompts, frameworks, and models - a.

Agent protocols & interoperability

Durable execution & background agents

  • temporalio/temporal - Durable workflow engine; the right way to run long-lived agents that must survive crashes.
  • inngest/inngest - Event-driven durable functions with first-class AI step support.
  • conductor-oss/conductor - Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents.
  • julep-ai/julep - Durable, composable AI agents with crash-and-resume flows.
  • loopx-project/loopx - Control plane with durable state kernel for long-horizon agents.
  • restatedev/restate - Resilient applications with durable workflows that tolerate any failure.
  • ThousandBirdsInc/chidori - Agent framework where every run is durable, replayable and resumable.

Azure AI Foundry

Memory & Persistent Context

Agents forget between sessions unless you give them somewhere to remember.

Memory layers & frameworks

Memory for coding agents

Memory MCP servers

Knowledge & code graphs

Benchmarks & papers

Graph databases

Storage backends

RAG & Retrieval

Vector databases, search engines, embeddings and the frameworks that ground answers in your own data.

Vector databases

  • chroma-core/chroma - Embedded, zero-config vector store; the right default for prototypes.
  • qdrant/qdrant - Rust vector database with filtering and hybrid search; production-ready.
  • pgvector/pgvector - Vector similarity search inside Postgres; skip a new database if you already run Postgres.
  • lancedb/lancedb - Serverless, file-based vector database on Lance columnar format.
  • milvus-io/milvus - Distributed vector database for billion-scale workloads.
  • weaviate/weaviate - Vector database with built-in vectorizers and hybrid search.
  • alibaba/zvec - A lightweight, lightning-fast, in-process vector database.
  • VexDB-THU/VexDB-Lite - A cross-platform vector database integrable into existing applications.
  • vearch/vearch - Distributed vector search for AI-native applications.
  • vdaas/vald - Vald: a highly scalable distributed vector search engine.
  • dingodb/dingo - A multi-modal vector database supporting upserts and vector queries.
  • endee-io/endee - A high-performance vector database built for billions of vectors.
  • philippgille/chromem-go - Embeddable vector database for Go with a Chroma-like interface.
  • oceanbase/seekdb - The AI-native search database for agent storage, unifying vector search.
  • Stevenic/vectra - Local vector database for Node.js, Pinecone-like but file-based.
  • epsilla-cloud/vectordb - A high-performance vector database leveraging parallel graph computing.
  • sdan/vlite - A fast vector database built in numpy.
  • Semafind/semadb - No-fuss multi-index hybrid vector database and search engine.
  • nuclia/nucliadb - NucliaDB, the AI search database for RAG.
  • infiniflow/infinity - AI-native database for LLM applications with vector and full-text search.
  • objectbox/objectbox-java - On-device database for Android and JVM with vector search.

Vector search libraries

  • eminsk/nanovector - The SQLite of vector search and episodic memory for AI agents in ~120KB.
  • spotify/annoy - Approximate nearest neighbors for static vectors.
  • facebookresearch/faiss - A library for efficient similarity search and clustering of dense vectors.
  • unum-cloud/USearch - Fast open-source search and clustering engine for vectors and more.
  • nmslib/hnswlib - Header-only C++/Python library for fast approximate nearest neighbors.
  • microsoft/DiskANN - Vector indexing library for fast, fresh, and filtered search at scale.
  • sqliteai/sqlite-vector - SQLite-Vector: cross-platform, ultra-efficient SQLite extension.
  • StarTrail-org/LEANN - Storage-efficient vector index for running RAG over personal data on a laptop.
  • RyanCodrai/turbovec - Rust vector index with Python bindings built on TurboQuant compression.

Search engines

Embeddings, rerankers & search

RAG frameworks & techniques

Graph RAG

Semantic caching

RAG evaluation & benchmarks

MCP Servers & Tool Integration

The Model Context Protocol is the USB-C of agent tooling.

Protocol & SDKs

Inspectors & dev tools

Gateways, proxies & hosting

Tool integration platforms

  • ComposioHQ/composio - 250+ pre-built tool integrations with auth handled for you.
  • Klavis-AI/klavis - MCP integration platform for connecting agents to tools at scale.
  • cporter202/agentic-ai-apis - 2,000+ production APIs across agents, models and MCP servers.
  • superdesigndev/treg - Hub for agent tools and API credentials, OpenRouter-style.
  • oomol-lab/open-connector - Open-source auth gateway connecting 1500+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.
  • aipotheosis-labs/aci - ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function ca.

Clients & directories

Servers

Database & data servers

Cloud & DevOps servers

Browser, search & scraping servers

Productivity, files & business servers

Creative & app-control servers

Sandboxes, Browsers & Computer Use

Isolated places to run agent-written code, and the browsers and scrapers agents drive.

Sandboxes

Isolation runtimes & dev environments

Browser automation

Stealth & anti-detection

Scraping & crawling

HTTP & HTML parsing

  • aio-libs/aiohttp - Asynchronous HTTP client/server framework for asyncio in Python.
  • encode/httpx - Next-generation HTTP client for Python with sync/async and HTTP/2.
  • psf/requests - Simple, elegant HTTP library for Python scraping and automation.
  • cheeriojs/cheerio - Fast jQuery-like library for parsing and manipulating HTML and XML.
  • jhy/jsoup - Java HTML parser for editing, cleaning, scraping, and XSS safety.
  • AngleSharp/AngleSharp - C# library parsing HTML5, SVG, and CSS into a W3C DOM.
  • PuerkitoBio/goquery - jQuery-style HTML parsing and traversal library for Go.
  • servo/html5ever - High-performance browser-grade HTML5 parser in Rust.
  • Nykakin/chompjs - Parses JavaScript objects from scraped pages into Python structures.
  • gawel/pyquery - jQuery-like HTML parsing library for Python scraping pipelines.
  • jsdom/jsdom - JavaScript implementation of web standards for headless DOM scraping.
  • lxml/lxml - The lxml XML toolkit for Python.
  • rushter/selectolax - Python binding to Modest and Lexbor engines. Fast HTML5 parser with CSS selectors for Python.
  • scrapy/parsel - Parsel lets you extract data from XML/HTML documents using XPath or CSS selectors.

Browser testing frameworks

Document Processing & Data Ingestion

Getting real-world files into a form agents can use.

Document parsing & conversion

OCR

PDF libraries

Structured extraction

Chunking & data pipelines

Media ingestion

Web content extraction

Web archiving

Workflow Automation

No-code and code-first automation with AI steps — the glue between your agents and everything else.

AI workflow platforms

n8n templates & tooling

Durable workflow engines

Data pipeline orchestration

Task queues & schedulers

BPM & process engines

CI/CD & event automation

  • nektos/act - Run your GitHub Actions workflows locally for fast testing.
  • harness/harness - Open-source end-to-end developer platform with CI/CD pipelines.
  • jenkinsci/jenkins - Extensible automation server for building and deploying software.
  • dagger/dagger - Automation engine to build, test, and ship any codebase anywhere.
  • tektoncd/pipeline - Cloud-native CI/CD pipeline framework for Kubernetes.
  • StackStorm/st2 - Event-driven automation for auto-remediation and ChatOps.
  • argoproj/argo-events - Event-driven automation framework for Kubernetes.
  • knative/eventing - Event-driven application platform for Kubernetes.
  • FellouAI/eko - Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai.

Model Gateways & Routing

One endpoint, many providers, automatic fallback.

AI gateways

Smart model routers

Coding-agent & API translation proxies

Privacy & security gateways

Router research & benchmarks

Free LLM APIs & Free Tiers

Build and learn without a credit card.

Free LLM API directories

Free-tier routers & gateways

Free developer resources & hosting

Local Models, Inference & Hardware

Run, fine-tune and quantize open models on your own hardware.

Serving

Apple Silicon & MLX

  • ml-explore/mlx - Array framework for machine learning on Apple silicon.
  • jundot/omlx - LLM inference server for Apple Silicon with continuous batching and SSD caching.
  • ml-explore/mlx-lm - Run large language models on Apple silicon using MLX.
  • Arthur-Ficial/apfel - Free on-device AI for Mac: CLI, OpenAI-compatible server, and chat.
  • Blaizzy/mlx-vlm - Inference and fine-tuning of vision-language models on Mac with MLX.
  • raullenchai/Rapid-MLX - Fast local AI engine for Apple Silicon with tool calling and prompt caching.
  • vllm-project/vllm-metal - Community hardware plugin that enables vLLM on Apple Silicon.
  • waybarrios/vllm-mlx - OpenAI-compatible LLM inference server for Apple Silicon built on MLX.
  • ddalcu/mlx-serve - Native Apple Silicon LLM inference server, OpenAI and Anthropic API compatible.
  • ml-explore/mlx-swift-lm - Run LLMs and VLMs on Apple silicon from Swift with MLX.
  • SharpAI/SwiftLM - Native MLX Swift inference server for Apple Silicon with SSD streaming.
  • ARahim3/mlx-dspark - Up to 4x faster lossless LLM decoding on Apple Silicon via speculative decoding.
  • Trans-N-ai/swama - High-performance MLX-based LLM inference engine for macOS in native Swift.
  • carloslfu/slotstream - Stream a 105GB mixture-of-experts model from SSD on Macs with 16 to 64GB RAM.
  • Epistates/pmetal - High-performance Apple Silicon framework for local LLM inference and serving.
  • youssofal/MTPLX - Fast local inference of Qwen models on Apple Silicon Macs using multi-token prediction.
  • incoai/splash - Local inference engine for Apple silicon built around the specific model.
  • drumih/turbo-fieldfare - Runs Gemma 4 26B-A4B in about 2 GB of RAM on M-series MacBooks.

On-device, mobile & browser

KV cache, kernels & speculative decoding

Quantization & compression

Training & fine-tuning

Hardware fit & benchmarks

Evaluation, Observability & Code Review

Trace, test and red-team agents, and review the code they write.

Tracing & observability

Evaluation

Benchmarks

Security & red-teaming

Fairness & governance

Code review

Production Architectures & Reference Systems

Complete, opinionated systems worth reading end to end.

Reference architectures

Templates & starter kits

Production RAG systems

Example apps & use cases

UI & Application Layer

Frontends, chat components, and app frameworks for putting agents in front of users.

Chat & agent UI components

Python app frameworks

Starter templates

Web frameworks

Backend frameworks

Component libraries & styling

Low-code & CMS

Learning Path

Ordered roughly from beginner to advanced.

Foundations

Agents & AI engineering

Cookbooks

Build it from scratch

Reinforcement learning

Must-read essays & guides

Research

Interview prep

Voice, Speech & Audio

Speech-to-text, text-to-speech and voice agents.

Speech-to-text

Text-to-speech & voice cloning

Voice agents

Audio processing & analysis

Telephony & SIP

Vision & Multimodal

Image/video understanding and vision-language models.

Vision-language models

  • QwenLM/Qwen3-VL - Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  • haotian-liu/LLaVA - Large Language-and-Vision Assistant; open GPT-4V-style model.
  • OpenGVLab/InternVL - Open-source multimodal model family rivaling proprietary vision-language models.
  • LLaVA-VL/LLaVA-NeXT - Open-source large multimodal models for image and video understanding.
  • OpenBMB/MiniCPM-V - Pocket-sized multimodal LLM for efficient image and video understanding on phones.
  • NVlabs/Eagle - Frontier vision-language models trained with data-centric strategies.
  • NVlabs/VILA - Vision-language models for multimodal AI across edge, data center, and cloud.
  • OpenSenseNova/SenseNova-U1 - Native unified multimodal model for understanding, reasoning, and generation.
  • m87-labs/moondream - Tiny vision-language model for fast image understanding on any device.
  • ATH-MaaS/Ovis - Multimodal LLM architecture structurally aligning visual and textual embeddings.
  • om-ai-lab/VLM-R1 - Reinforcement learning framework for visual understanding with VLMs.
  • eulogik/TinyDoc-VLM - 256M-parameter document VLM that runs on CPU with ONNX export.
  • andreagemelli/baguettotron-vlm - Fully reproducible sub-1B vision-language model with open training.
  • microsoft/Magma - Foundation model for multimodal AI agents acting in digital worlds.
  • apple-aiml-research/ml-ferret - Apple's region-aware VLM for referring expression grounding.
  • jingyaogong/minimind-v - Train a small vision-language model from scratch in a couple of hours.

Detection, segmentation & tracking

Vision libraries & backbones

Face analysis

Video understanding & agents

Depth & 3D reconstruction

Image, Video & Creative Generation

Diffusion, image and video generation tooling.

Image generation UIs

Image models & inference

ComfyUI extensions

Video generation

Avatars & lip-sync

Image editing, upscaling & restoration

Training & fine-tuning

Audio & music generation

3D generation

Computer Use & GUI Agents

Agents that operate desktops, phones and apps.

Browser & desktop agents

GUI grounding models & research

Mobile agents

Benchmarks & environments

RPA

Desktop automation libraries

Mobile device automation

VMs & remote desktop

Structured Output, Guardrails & Safety

Validation, constrained decoding, jailbreak and injection defense.

Structured output

Guardrails

Prompt injection defense

Red-teaming & security scanners

Model supply-chain security

Chat UIs & Application Layer

Front-ends, chat interfaces and app scaffolds.

Chat apps

Desktop & terminal clients

Mobile clients

AI search & research

Character & roleplay

Bots & support platforms

AI workspaces

  • u14app/neo-chat - Local-first AI chat workspace with agents, plugins, search and RAG.

  • AppFlowy-IO/AppFlowy - AI collaborative workspace; open Notion alternative.

  • toeverything/AFFiNE - Next-gen knowledge base with an AI copilot.

  • odysseus-dev/odysseus - Self-hosted AI workspace.

  • cloudflare/cloudflare-os - Agent workspace on Cloudflare Workers for documents, apps and agents.

  • tutti-os/tutti - Multi-user, multi-agent, real-time collaboration space where people and agents build together.

  • preset-io/agor - Multiplayer AI: Bring your team and agents together.

  • Team-Commonly/commonly - Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infr.

  • alookai/alook - Rooms for people and agents.

  • yincongcyincong/MuseBot - Multi-platform LLM bot for Telegram, Discord, Slack, Lark, DingTalk, WeChat and more; works with OpenAI, Gemini, DeepSeek, Doubao and others.

Deployment, Serving & MLOps

Ship and operate models and agents in production.

Model serving

  • microsoft/onnxruntime - Cross-platform inference engine for serving ML models in production.
  • onnx/onnx - Open standard format for portable, interoperable ML models.
  • kserve/kserve - Standardized serverless inference platform on Kubernetes for predictive and generative AI.
  • triton-inference-server/server - NVIDIA's multi-framework inference server with dynamic batching and ensembles.
  • SeldonIO/seldon-core - MLOps framework to package, deploy, monitor, and manage production ML models.
  • bentoml/BentoML - Build and serve model inference APIs, job queues, and multi-model pipelines.
  • SeldonIO/MLServer - Multi-framework ML inference server with multi-model serving support.
  • basetenlabs/truss - The simplest way to package and serve AI/ML models in production.
  • tensorflow/serving - Flexible, high-performance serving system for machine learning models.
  • replicate/cog - Containers for machine learning: package models reproducibly behind an API.
  • vllm-project/production-stack - Reference system for Kubernetes-native, cluster-wide vLLM deployment.
  • vllm-project/aibrix - Cost-efficient, pluggable infrastructure components for GenAI inference.
  • llm-d/llm-d - Kubernetes-native distributed LLM inference with state-of-the-art performance.
  • ogx-ai/ogx - OpenAI-compatible agentic API server; run any model on any infrastructure.
  • ai-dynamo/dynamo - Datacenter-scale distributed inference serving framework from NVIDIA.
  • xorbitsai/inference - Unified production API to serve LLMs, embeddings, and multimodal models.
  • InternLM/lmdeploy - Toolkit for compressing, deploying, and serving LLMs at high throughput.
  • lm-sys/FastChat - Open platform for training, serving, and evaluating large language models.
  • dphnAI/sonar - Large-scale LLM inference engine, successor of the Aphrodite Engine fork.
  • ServerlessLLM/ServerlessLLM - Serverless LLM serving with fast cold starts for everyone.
  • predibase/lorax - Multi-LoRA inference server scaling to thousands of fine-tuned adapters.
  • ModelTC/LightLLM - Lightweight, easy-to-scale, high-speed Python LLM serving framework.
  • OpenNMT/CTranslate2 - Fast inference engine for Transformer models in C++ and Python.
  • beam-cloud/beta9 - Ultrafast serverless GPU inference, sandboxes, and background jobs.
  • vllm-project/vllm-ascend - Community hardware plugin running vLLM on Huawei Ascend NPUs.
  • alibaba/rtp-llm - Alibaba's high-performance LLM inference engine.

MLOps platforms & pipelines

Experiment tracking

  • mlflow/mlflow - The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of.
  • clearml/clearml - ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data.
  • wandb/wandb - The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
  • marimo-team/marimo - A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a.
  • kubeflow/katib - Automated hyperparameter tuning and neural architecture search on K8s.
  • optuna/optuna - Automatic hyperparameter optimization framework for ML.
  • aimhubio/aim - Self-hostable experiment tracker built for high-volume run comparison.
  • treeverse/dvclive - Log and track ML metrics, parameters, and models with Git/DVC.
  • iterative/gto - Turn any Git repository into an artifact and model registry.
  • kubeflow/hub - Central model registry UI for the Kubeflow MLOps lifecycle.
  • DagsHub/client - Client libraries for the DagsHub ML experiment tracking platform.
  • SwanHubX/SwanLab - Experiment tracking and visualization for AI training.

Kubernetes for AI workloads

Edge & lightweight Kubernetes

Serverless

  • knative/serving - Scale-to-zero, request-driven serverless compute on Kubernetes.
  • openfaas/faas - Serverless functions made simple, on Kubernetes or faasd.
  • nuclio/nuclio - High-performance serverless event and data processing platform.
  • fission/fission - Fast and simple serverless functions for Kubernetes.

GitOps, CI & dev environments

Data, Datasets & Synthetic Data

Data curation, labeling, synthetic generation and datasets.

Datasets

Labeling & annotation

Synthetic data

Data quality & validation

Data processing

Data versioning, catalogs & feature stores

NLP libraries

BI & analytics

Graph analysis libraries

Domain Agents: Finance, Healthcare, Research & More

Vertical agents and assistants for specific industries.

Finance

Healthcare & life sciences

Research & science

Deep research agents

Data analysis agents

  • sinaptik-ai/pandas-ai - Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
  • eosphoros-ai/DB-GPT - Open-source agentic AI data assistant for the next generation of AI + Data products.
  • business-science/ai-data-science-team - Team of AI agents that performs data science and analytics tasks.
  • WecoAI/aideml - AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.

Legal

  • dnzengou/legal-ai-agent - Contract review API with server-validated citations.
  • lowtidebuild/contract-review - Contract review agent pipeline producing redlined DOCX.
  • nexu-io/open-design - 🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes t.
  • Armur-Ai/Pentest-Swarm-AI - Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with.
  • aiming-lab/AutoResearchClaw - Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞.
  • OpenNSWM-Lab/FAROS - A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and pe.
  • beenuar/AiSOC - Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for.
  • Lumiwealth/lumibot - AI agents that actually place the trade. 12 brokers, real backtests, stocks options futures forex crypto and prediction markets.
  • kyky2347/ALTA - Autonomous LLM Trading Asterism — a research-only multi-agent trading platform with evidence-first research, an auditable console, Shadow si.
  • GH05TCREW/pentestagent - PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
  • samugit83/redamon - Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandb.
  • espressif/esp-claw - ESP-Claw, a "Chat Coding" AI agent framework for IoT devices.
  • SanMuzZzZz/LuaN1aoAgent - LuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning.

Assistants, Copilots & Personal Agents

General-purpose assistants you run yourself.

Personal agents

  • Fosowl/agenticSeek - Fully local autonomous AI agent; no APIs, runs on your machine.
  • HKUDS/nanobot - Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI.
  • leon-ai/leon - Open-source personal assistant you self-host.
  • agent0ai/agent-zero - Personal agentic framework with computer-use and multi-agent support.
  • agentscope-ai/QwenPaw - Personal AI assistant workstation deployable locally or in the cloud.
  • damianvtran/local-operator - Local AI agent CLI that runs tasks on your machine.
  • dcSpark/shinkai-local-ai-agents - Local-first AI agent operating system with encrypted data.
  • kortix-ai/suna - Open-source generalist AI agent for complex tasks.
  • felinics/Memoh - Multi-agent platform giving every agent its own computer and memory.
  • MarlBurroW/hivekeep - Self-hosted platform running a team of persistent personal AI agents.
  • Panniantong/Agent-Reach - Agent internet capability layer connecting AI agents to live web services.
  • tinyhumansai/openhuman - Local-first personal AI agent harness with persistent memory.
  • RightNow-AI/openfang - Rust-built open-source Agent OS with autonomous scheduled Hands.
  • rootazero/Aleph - Self-hosted personal AI assistant with a native desktop app and messaging channels.
  • CharlesHAO77/EveryBuddy - Local-first desktop personal agent with personas, cron schedules, and MCP skills.
  • utopusc/livinity-io - Self-hostable "Cloud AI Computer" with an AI assistant managing apps and files.
  • vaenyxai/core - Self-hosted home AI agent with local memory, tasks, and your choice of model backend.
  • BugraAkdemir/memo - Local-first assistant with real memory, agent tool use, and proactive habits (Go + Flutter).
  • missarii/Web-Pilot - Local-first AI browser agent that browses, extracts, and downloads on your machine.
  • ownpilot/OwnPilot - Privacy-first personal AI assistant platform with autonomous agents and multi-provider support.
  • NeOMakinG/desktop-ai-dashboard - Open-source Tauri personal AI workspace with persistent chats and schedules.
  • 0x-copilot-dev/0x-copilot - Local BYOK AI copilot; Electron desktop runs the whole stack on your machine.
  • ItsNotAILABS/pocket - Host-local co-pilot runtime that opens desktop apps and the web on your PC.
  • nolanmak/Jarvis - Self-hosted assistant daemon triaging email and DMs with human-approval before sending.
  • opencrew-ai/oncellclaw - Personal Claude assistant in durable cloud cells; isolated, crash-proof, wakes on message.
  • PeterGreenAppliedAI/Invarail - Local-model-first agent framework with router/specialist architecture and web console.
  • abacusai/abacusai-bot - Open-source personal agents for WhatsApp, Telegram, Discord, with scheduled routines.
  • Vexillon-ai/MIRA - Self-hosted personal AI agent with channels, voice, cron automations, and memory (Rust core).
  • netease-youdao/LobsterAI - Desktop AI agent for everyday work such as data analysis and documents.
  • ThinkInAIXYZ/deepchat - Desktop AI assistant connecting multiple models and tools to personal workflows.
  • jayamitkatariya/personacli - Local-first personal workspace with an AI that knows your files.
  • Graphene-Lab/AgentBridge - Autonomous personal AI assistant for delegating everyday tasks.
  • NickMonrad/kernel-ai-assistant - Local-first Android assistant with on-device inference and semantic memory.
  • samosa-ai-com/Gotcha - Fully on-device Android AI copilot turning natural language into device actions.
  • spinabot/brigade - Personal AI agent runtime with enterprise-grade controls.
  • TencentCloud/Octop - Self-hosted multi-user, multi-agent AI assistant.
  • CopilotKit/OpenDots - Always-on AI coworkers that work across text, calls and Slack.
  • eigent-ai/eigent - Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex.
  • holaboss-ai/holaOS - Open-source agentic workspace enterprises can make their own. Connect the systems you already run — 100+ integrations, MCP, chat tools, apps.
  • the-open-agent/openagent - ⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: ht.
  • nanbingxyz/5ire - 5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and t.
  • OpenCoworkAI/open-cowork - Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-m.
  • YaoApp/yao - ✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or.
  • najmuzzaman-mohammad/gawkbot - open source grok bot. gawk bots automate your menial work via AI models and build you microapps to manage the outcome, so that you have a fa.
  • ghostwright/phantom - An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on.
  • vellum-ai/vellum-assistant - An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.

Second brain & knowledge

  • khoj-ai/khoj - Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents.
  • logancyang/obsidian-copilot - THE Copilot in Obsidian.
  • mindsdb/mindshub - Unified workspace where open-source AI models automate real work.
  • mateaix/mateclaw - 🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spr.

CLI assistants

  • simonw/llm - CLI and Python library for talking to any LLM, with plugins.
  • sigoden/aichat - All-in-one LLM CLI: shell assistant, RAG, agents.
  • TheR1D/shell_gpt - Command-line productivity tool powered by LLMs.
  • kriserickson/ai-cli - CLI that converts natural-language requests into shell commands via LLMs.

Voice assistants & companions

Task-specific assistants

  • career-ops-hq/career-ops - AI job-search agent that scores listings, tailors CVs, tracks applications.
  • hugohe3/ppt-master - Agentic workflow that generates fully editable PowerPoint presentations.
  • Mail-0/Zero - Open-source AI-driven email client with AI agents.
  • mikeljc-dev/docsera - Self-hosted docs AI chat widget with citations, works with local models via Ollama.
  • yikart/AiToEarn - AI content creation and auto-publishing across social platforms.
  • KKKKhazix/AIHOT - Framework for a site that finds trending topics and writes daily AI reports.
  • melgarafael/DeskcommCRM - Self-hosted CRM with built-in AI sales agents and WhatsApp.

Interpretability, Alignment & Research

Understanding and steering model behaviour.

Interpretability

Steering & model editing

RL & post-training

Alignment

Research

  • deepseek-ai/Engram - Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models.
  • ShishirPatil/gorilla - Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls).
  • dair-ai/AI-Papers-of-the-Week - Highlighting the top ML papers every week.
  • karpathy/nanoGPT - Minimal, hackable GPT training codebase for LLM training research.
  • state-spaces/mamba - Selective state-space sequence models; the leading Transformer alternative.
  • google-research/google-research - Code for Google Research papers.
  • NVIDIA/cosmos - NVIDIA's open world models, datasets and tools for physical AI.
  • camel-ai/oasis - 🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
  • mll-lab-nu/RAGEN - Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics.
  • ray-r-ren/agent-apprenticeship - The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor age.
  • Human-Agent-Society/CORAL - Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi.

Developer Tools & Utilities

Useful things that don't fit a layer.

Developer utilities

  • CapSoftware/Cap - Open-source screen recording for demos and bug reports.
  • OtterMind/Chat2DB - Chat2DB is a free, cross-platform, local-first database client and SQL workspace for developers.
  • astral-sh/uv - Extremely fast Python package and project manager written in Rust.
  • jdx/mise - Dev-tool version manager, env vars, and task runner in one binary.
  • pydantic/pydantic - Data validation in Python using type hints; core of most agent frameworks.
  • jd/tenacity - Python retry library with exponential backoff for flaky LLM API calls.
  • hynek/stamina - Production-grade retry library for Python async and sync workloads.
  • hoppscotch/hoppscotch - Open-source API development and testing ecosystem for web, desktop, and CLI.
  • usebruno/bruno - Open-source API IDE for exploring and testing APIs, a Postman alternative.
  • rocketride-org/rocketride-server - High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model pr.
  • microsoft/foundry-dev-tools - Microsoft Foundry developer tools: build AI applications and agents with the Foundry CLI, SDKs, and VS Code toolkit.

Git & commit tools

LLM SDKs & tokenizers

Prompt playgrounds & versioning

Usage metering & cost tracking

Tunnels & networking

Self-hosting & PaaS

Package registries & runtimes

Other Awesome Lists

Sibling lists worth mining when you need to go deeper on a niche.

Agent & coding-agent lists

Skills, MCP & Claude lists

AI & ML lists

Research, security & evaluation lists

General lists

Contributing

Contributions welcome — read CONTRIBUTING.md first. The bar: you have used it, it is maintained, and it fits a layer of the stack. The quickest way in is to edit this README and open a pull request; the website updates itself once it is merged.

Contributors

Star history

Star history chart

Footnotes

Maintained by Tayyab Imam. If you reuse this list, please credit it:

Based on Awesome AI Agent Stack by Tayyab Imam.

Reviews (0)

No results found