Catalog

ADK-Rust is a community-built Rust framework for constructing LLM-powered AI agents. It is inspired by Google's offic...

The Agent Harness pattern describes the architectural approach where all non-model code, configuration, and execution...

Agent Memory as Infrastructure is an emerging architectural pattern that treats AI agent memory not as a feature or s...

Agent Runtime Security is an emerging architectural pattern for protecting autonomous AI agents that execute actions ...

Agent Skill Supply Chain Risk is an emerging security threat pattern specific to the AI agent skills ecosystem. It de...

The Agent Skills specification is an open standard for packaging procedural knowledge, instructions, scripts, and res...

The Agent2Agent (A2A) protocol is an open communication standard for AI agent interoperability, originally introduced...

AgentField is an open-source control plane (written in Go, backed by PostgreSQL) that turns AI agents into independen...

The Agentic AI Foundation (AAIF) is a Linux Foundation project announced on December 9, 2025, that provides neutral, ...

AI Safety Evaluation (Pre-Deployment) is an emerging pattern where frontier AI models are assessed by independent thi...

AIO Sandbox is an all-in-one Docker container that bundles Browser (Chromium with VNC and CDP), Shell (Bash), File sy...

Alibaba Cloud is the cloud computing division of Alibaba Group, providing a full-stack cloud platform with compute, s...

All Hands AI is the venture-backed company behind OpenHands, the open-source platform for autonomous AI coding agents...

Anomaly Innovations (trading as "Anomaly") is a venture-backed developer tools company that builds OpenCode (open-sou...

AnythingLLM is an open-source, self-hosted AI chat application built by Mintplex Labs that emphasizes document-centri...

ArcKit is an open-source toolkit that provides 67 AI-assisted slash commands for enterprise architecture governance, ...

Beads is a Go CLI tool (`bd`) that provides AI coding agents with persistent, structured memory across sessions. It r...

Benchmark saturation is the recurring pattern in AI evaluation where models approach or exceed the maximum meaningful...

Block Inc. (formerly Square, NYSE: SQ) is a publicly traded American fintech company founded by Jack Dorsey in 2009. ...

BMAD (Breakthrough Method for Agile AI-Driven Development) is an open-source framework that structures AI-assisted so...

ByteDance is the world's most valuable private technology company ($550B valuation as of early 2026, $186B projected ...

Cedar is a declarative authorization policy language created by Amazon and open-sourced under Apache 2.0. It lets you...

Claude Code is Anthropic's official CLI-based AI coding agent that operates directly in the developer's terminal. It ...

ClawKeeper is a three-layer real-time security framework designed specifically for OpenClaw autonomous agents. It add...

Clerk is a managed authentication and user-management platform focused on developer experience. It provides drop-in U...

ClickHouse is an open-source columnar OLAP (Online Analytical Processing) database designed for real-time analytics o...

CodeSandbox SDK is a programmatic API for creating and running VM sandboxes, originally built by CodeSandbox and now ...

Composio Agent Orchestrator is an open-source system for managing fleets of AI coding agents working in parallel on a...

ComputeSDK is a unified TypeScript abstraction layer for executing code in sandboxed environments across multiple clo...

Contentful is a headless CMS platform that provides content infrastructure via APIs. It separates content modeling an...

Daytona is an open-source AI code sandbox infrastructure platform offering the fastest creation times in the market (...

Deep Agents is an open-source, MIT-licensed agent harness framework built on LangChain and LangGraph. It packages the...

DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source "SuperAgent harness" by ByteDance that orch...

Dify is an open-source platform for building LLM-powered applications through a visual drag-and-drop workflow builder...

Dolt is a SQL database with git-style version control built in. You can fork, clone, branch, merge, push, and pull da...

> Updated 2026-04-03: Cross-referenced with Ry Walker's AI Agent Sandboxes Compared survey (2026-03-27). Added compet...

each::labs is a pre-seed AI infrastructure startup that provides two main products: (1) an LLM router that aggregates...

Fission AI is a YC-backed startup that builds OpenSpec, an open-source spec-driven development framework for AI codin...

Flowise is an open-source visual builder for constructing AI agents and LLM workflows using a drag-and-drop node-base...

Gemini CLI is Google's open-source terminal-based AI coding agent that brings Gemini models directly into the develop...

Google Agent Development Kit (ADK) is an open-source, code-first Python framework for building, evaluating, and deplo...

Goose is an open-source, on-machine AI agent built primarily in Rust (58%) and TypeScript (34%) by Block Inc. It goes...

Graphite is a developer productivity platform centered on stacked pull requests for GitHub. It provides a CLI, VS Cod...

HCAST (Human-Calibrated Autonomy Software Tasks) is METR's primary benchmark for measuring frontier AI model capacity...

Hermes Agent is an open-source (MIT) self-improving AI agent built by Nous Research. Its core differentiator is auton...

Honcho is an open-source memory library (with managed service) for building stateful AI agents that maintain persiste...

Humanity's Last Exam (HLE) is a multi-modal benchmark consisting of 2,500 expert-level academic questions designed to...

Inspect AI is an open-source framework for large language model evaluations created by the UK AI Safety Institute (AI...

Jujutsu (jj) is a Git-compatible version control system written in Rust, originally developed at Google. It uses Git'...

Kinde is a managed developer platform that bundles authentication, access management (RBAC, organizations/multi-tenan...

klaw.sh is a Go-based CLI tool that applies Kubernetes-style orchestration patterns to AI agent fleet management. It ...

Kubernetes Agent Sandbox (agent-sandbox) is an official Kubernetes SIG Apps project providing a declarative CRD-based...

LangChain is an AI infrastructure company that provides open-source frameworks and commercial services for building L...

Langflow is a visual IDE for building AI agents and RAG applications, supporting both LangChain and LangGraph under t...

LangGenius Inc. is a venture-backed AI infrastructure startup headquartered in Sunnyvale, California. It is the comme...

LangGraph is a graph-based runtime for building stateful, multi-step AI agent workflows. It models agent logic as a d...

LangSmith is a commercial observability, evaluation, and deployment platform for LLM applications, built and operated...

Leash wraps AI coding agents (Claude, Codex, Gemini, Qwen, OpenCode) in containers and monitors every syscall — file ...

LibreChat is an open-source, self-hosted AI chat platform that provides a unified ChatGPT-like interface for interact...

LiteLLM is an open-source Python SDK and proxy server (AI Gateway) that provides a unified OpenAI-compatible API for ...

The LLM Gateway pattern interposes a proxy layer between applications and LLM providers, creating a centralized contr...

Lubeno is an early-stage code hosting and collaboration platform built from the ground up to support Jujutsu (jj), th...

METR (Model Evaluation & Threat Research) is a Berkeley-based 501(c)(3) nonprofit research organization that evaluate...

The METR Task Standard is a portable specification for defining AI agent evaluation tasks. It provides a standardized...

Microsandbox is a local-first sandbox platform that runs lightweight microVMs on the developer's own machine using li...

MMLU (Massive Multitask Language Understanding) is a benchmark for evaluating large language model knowledge and reas...

Modal is a serverless Python infrastructure platform that provides cloud compute (CPU and GPU) with sub-second cold s...

The Model Context Protocol (MCP) is an open standard introduced by Anthropic in November 2024 that defines how AI ass...

Models.dev is an open-source, community-contributed database of AI model specifications. It aggregates metadata (pric...

Northflank is an enterprise-grade developer platform that provides secure microVM sandboxes for AI agent workloads wi...

Nous Research is a venture-backed AI research lab focused on open-source language models, fine-tuning, and autonomous...

Ollama is an open-source local LLM inference engine that simplifies downloading, running, and managing large language...

Open WebUI (formerly Ollama WebUI) is a self-hosted, provider-agnostic web interface for interacting with large langu...

OpenClaw is an open-source (MIT licensed), self-hosted AI agent gateway built in Node.js. It connects chat platforms ...

OpenCode is an open-source, MIT-licensed AI coding agent that operates primarily through a terminal user interface (T...

OpenHands is an open-source platform for building and running autonomous AI coding agents. Agents interact with codeb...

OpenRouter is a unified API gateway that provides access to 300+ large language models from 60+ providers (OpenAI, An...

OpenSandbox is an open-source, self-hosted sandbox platform for executing untrusted code from AI agents. It provides ...

OpenSpec is an open-source TypeScript CLI framework that adds a specification layer to AI-assisted development. Creat...

OpenViking is an open-source context database by ByteDance's Volcano Engine team, designed specifically for AI agents...

Optio is a workflow orchestration system for AI coding agents that automates the lifecycle from task intake to merged...

Pi is an open-source, terminal-based AI coding agent that takes a deliberately minimal approach. Created by Mario Zec...

Portkey is an enterprise-grade AI gateway and control plane for managing LLM access in production. It provides a unif...

Quilt is an open-source, Rust-based container infrastructure for AI agents that provides instant parallel container c...

The Ralph Loop (originally "Ralph Wiggum Loop") is an autonomous agent pattern for AI-assisted software development. ...

Runloop provides "Devboxes" -- persistent, sandboxed development environments for AI agents with git-style state mana...

Skills.sh is Vercel's directory and leaderboard for AI agent skill packages built on the open Agent Skills Specificat...

> Updated 2026-04-05: Added OpenSpec catalog cross-reference following dedicated review.

Sprites is Fly.io's persistent VM product built on Firecracker microVMs, designed for AI agent workloads that need st...

Stacked diffs (also called stacked PRs or stacked changes) is a code review workflow pattern where large changes are ...

SWE-bench is a benchmark for evaluating whether AI systems can resolve real-world GitHub issues. It presents an AI ag...

Vercel AI Gateway is a unified API proxy for accessing 100+ AI models from multiple providers (OpenAI, Anthropic, Goo...

Vivaria is METR's open-source platform for running AI agent evaluations and conducting elicitation research. It provi...

Volcano Engine is ByteDance's enterprise cloud services platform, providing infrastructure, AI/ML services, and appli...

W3C DID Agent Identity is an emerging pattern that applies W3C Decentralized Identifiers (DIDs) and Verifiable Creden...

Warp Oz is a commercial orchestration platform for cloud AI coding agents, built by Warp (the terminal/IDE company). ...

Weaviate is an open-source (BSL-1.1 licensed) vector database designed for AI-native applications. It stores data obj...

Weaviate Engram is a memory and context management layer for AI agents, built on top of Weaviate's vector search tech...

Zavora AI is the company (or personal brand) behind ADK-Rust, a Rust-based AI agent framework. Founded by James Karan...

Zeroboot provides sub-millisecond VM sandboxes for AI agents using copy-on-write (CoW) forking of Firecracker microVM...

Zerobox is a lightweight CLI tool and TypeScript SDK that sandboxes arbitrary processes using OS-level isolation prim...