# iac

Autonomous scientific discovery via agentic tree search

AI Scientist v2 is Sakana AI's open-source system for fully autonomous scientific research using LLM-powered agentic tree search. It generates hypotheses, designs experiments, writes and executes code, analyzes results, and produces publishable manuscripts without human intervention. The system uses progressive exploration with backtracking to navigate the research space efficiently.

Lightweight C++ inference for Google Gemma models

gemma.cpp is Google's standalone C++ inference engine built specifically for running Gemma language models without Python or CUDA dependencies. It provides optimized CPU inference using SIMD instructions and Highway library, supports Gemma 2 and Gemma 3 models, and runs on x86 and ARM architectures. Designed for embedded systems, edge devices, and server deployments needing minimal overhead.

Unified Python/.NET framework for multi-agent AI

Microsoft Agent Framework is Microsoft's official unified SDK for building multi-agent AI workflows in Python and .NET. It consolidates Semantic Kernel and AutoGen into a single framework with MCP tool integration, graph-based workflows, human-in-the-loop patterns, and multi-agent orchestration. The framework reached Release Candidate status in February 2026 and is Microsoft's recommended path for production agent development.

State-of-the-art open-source code language models

DeepSeek Coder is a family of open-source code language models trained from scratch on 2 trillion tokens of code and natural language data. Available in sizes from 1B to 33B parameters, these models support 80+ programming languages with 16K context windows and fill-in-the-blank capabilities. DeepSeek Coder outperforms CodeLlama-34B on HumanEval and MBPP benchmarks while being commercially licensable under MIT.

Context retrieval layer for AI agents and RAG

Airweave is an open-source context retrieval platform that connects AI agents and RAG systems to 50+ apps and databases through a unified search interface. It continuously syncs data from sources like Notion, Slack, GitHub, and databases, making it searchable through LLM-friendly APIs. Airweave includes Python and TypeScript SDKs, MCP support, and a CLI for managing data connections.

Modern data pipeline orchestration with built-in AI

Mage AI is an open-source data pipeline orchestration tool positioned as a modern alternative to Apache Airflow. It provides a visual pipeline editor, native AI integrations for generating pipeline code, real-time streaming support, and built-in data quality checks. Mage handles batch and streaming workloads with a developer-friendly notebook-style interface and deploys to any cloud provider.

Fine-grained authorization engine by Okta

OpenFGA is an open-source authorization engine inspired by Google Zanzibar, built and maintained by Okta (Auth0). It provides relationship-based access control with a flexible modeling language, sub-millisecond permission checks, and SDKs for major languages. OpenFGA is used by companies including Grafana Labs, Canonical, and Docker for fine-grained access control in multi-tenant applications.

Google Zanzibar-inspired authorization database

SpiceDB is an open-source authorization database inspired by Google's Zanzibar system, providing relationship-based access control (ReBAC) at scale. It defines permissions through a schema language that models relationships between users, resources, and roles, then evaluates authorization checks in single-digit milliseconds. Used by companies like Netflix and GitHub, SpiceDB handles millions of permission checks per second.

Open-source AIOps alert management platform

Keep is an open-source AIOps platform that provides a single pane of glass for all alerts from monitoring tools like Datadog, PagerDuty, Grafana, and 50+ integrations. It uses AI to correlate, deduplicate, and enrich alerts, reducing noise and helping on-call teams focus on real incidents. Keep includes workflow automation, bidirectional sync with ticketing systems, and a modern web dashboard.

Open-source feature flags and A/B testing platform

GrowthBook is an open-source platform for feature flags, A/B testing, and product experimentation. It includes Bayesian and frequentist statistics engines, warehouse-native analytics connecting to BigQuery, Snowflake, and Databricks, and SDKs for 15+ languages. GrowthBook supports targeting rules, gradual rollouts, and an MCP server for AI agent integration. Self-hostable via Docker.

Open-source platform for building API integrations

Nango is an open-source API integration platform that handles OAuth authentication, data synchronization, and proxying for 700+ APIs in a single self-hostable package. It manages token refresh, rate limiting, field mapping, and webhook syncing so developer teams can connect AI agents and products to external services in hours instead of weeks. Backed by Y Combinator W23 with $7.5M in funding.

Voice AI APIs for speech-to-text and text-to-speech

Deepgram is a voice AI infrastructure platform providing low-latency speech-to-text, text-to-speech, and conversational AI APIs. Its Nova-3 model delivers industry-leading accuracy for real-time transcription with streaming support, interruption handling, and multi-language capabilities. Used by 1,300+ organizations including Twilio and Vapi, Deepgram powers voice features in applications ranging from call centers to AI agent voice interfaces.

Full-stack monitoring with session replay and tracing

Highlight.io is an open-source full-stack monitoring platform that combines session replay, error monitoring, logging, and distributed tracing in a single tool. It captures user sessions as replayable videos alongside frontend errors, backend logs, and traces, letting teams see exactly what users experienced when issues occur. Self-hostable via Docker with a generous free tier on their managed cloud service.

High-performance WebAssembly runtime for cloud and AI

WasmEdge is a CNCF sandbox WebAssembly runtime optimized for cloud-native, edge, and AI workloads. It provides a lightweight, secure, and portable execution environment that is faster than containers and safer than native processes. WasmEdge supports LLM inference via LlamaEdge, serverless functions, microservices, and plugin extensions for networking, AI, and cryptography across Linux, macOS, and Windows.

In-page AI browser agent via a single script tag

Page Agent is Alibaba's open-source JavaScript library that embeds an AI GUI agent directly into any web page through a single script tag injection. Unlike headless browser tools that operate externally, Page Agent works inside the DOM using text-based manipulation for natural language QA testing, enterprise copilots, and making legacy web apps AI-native. It supports BYOLLM with any model provider and requires no backend changes.

Headless browsers in Docker for automation at scale

Browserless is a headless browser-as-a-service platform that deploys Chrome, Firefox, and WebKit in Docker containers for web scraping, testing, and AI agent automation. It provides Puppeteer and Playwright-compatible APIs, a built-in MCP server for connecting AI assistants to browser automation, screenshot and PDF generation, and connection pooling for high-concurrency workloads. Available as self-hosted open source or managed cloud.

On-device ML solutions for mobile and edge AI

MediaPipe is Google's open-source framework for building on-device machine learning pipelines across mobile, web, desktop, and edge platforms. It provides pre-built solutions for face detection, hand tracking, pose estimation, object detection, image classification, text classification, and on-device LLM inference. MediaPipe runs entirely locally without cloud dependencies, supporting Android, iOS, Python, and web browsers.

Reusable computer vision tools for developers

Supervision is an open-source Python toolkit by Roboflow providing reusable CV utilities for detection, tracking, annotation, and dataset management. It works with any model including YOLO and Hugging Face via a standardized Detections class. Features include 20+ annotators, ByteTrack object tracking, zone counting, speed estimation, and dataset conversion between COCO, YOLO, and Pascal VOC formats.

Deep learning optimization for distributed training

DeepSpeed is Microsoft's open-source deep learning optimization library that makes distributed training and inference easy, efficient, and effective. Its ZeRO optimizer eliminates memory redundancies across data-parallel processes, enabling training of models with trillions of parameters. DeepSpeed supports 3D parallelism combining data, pipeline, and tensor parallelism, along with mixed precision training, gradient checkpointing, and CPU/NVMe offloading for memory-constrained environments.

Open-source microVMs for secure serverless and AI agent sandboxing

Firecracker is an open-source virtual machine monitor that creates lightweight microVMs with sub-150ms cold starts, originally built by AWS for Lambda and Fargate. With 28,000+ GitHub stars, it provides kernel-level isolation for running untrusted code safely and powers the sandboxing infrastructure behind AI coding agents like Devin and E2B.

Kubernetes-native cloud infrastructure control plane

Crossplane is a CNCF Graduated open-source project that extends Kubernetes to manage cloud infrastructure through declarative APIs. Platform teams compose custom infrastructure abstractions as Compositions and publish them as self-service APIs. It provisions resources across AWS, Azure, GCP, and 200+ providers directly from kubectl. Used by 450+ organizations with 11,000+ GitHub stars.

AWS's fully managed machine learning service for building, training, and deploying ML models.

Amazon SageMaker is AWS's comprehensive ML platform covering data labeling, notebook environments, model training, hyperparameter tuning, model hosting, and MLOps pipelines. Supports all major ML frameworks. Offers SageMaker Studio as an integrated IDE. Used by enterprises for production-scale ML workloads.

Open-source Terraform fork — community-driven Infrastructure as Code.

OpenTofu is an open-source fork of Terraform created by the Linux Foundation after HashiCorp switched Terraform to the BSL license. Fully compatible with Terraform 1.5.x, it offers state encryption, early variable evaluation, and a community-driven development model. Backed by major cloud providers and companies.

Infrastructure as Code using real programming languages — TypeScript, Python, Go, C#, Java.

Pulumi is a modern Infrastructure as Code platform that lets you define cloud infrastructure using familiar programming languages instead of DSLs. Supports TypeScript, Python, Go, C#, Java, and YAML across AWS, Azure, GCP, Kubernetes, and 150+ providers. Offers testing, IDE autocomplete, and reuse patterns.