The Framework for Building Agents

The agent that grows with you

The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

The `npx serve` of Apple Simulators.

SimDeck is a developer tool built for streamlining mobile app development using agents. Drive iOS Simulators and Android emulators from your favorite IDE & CLI.

Review code. Patch bugs. Land PRs.

🪩 Mirror git refs from a source remote to a target remote without a local checkout. Packfiles stream directly over Smart HTTP and an in-memory object store.

Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built.

Basecamp CLI and Agent Skills

Atomic and non-atomic counters and rate limiting tools. Limit resource access at any scale.

⤵️ A GitHub Action for syncing current repository with remote

Browser automation CLI for AI agents

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

Chrome extension & CLI to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP

Auto synchronization of remote Git repositories. Auto conflict solving. Network fail resilience. Linux & Windows support. And more.

Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite

CLI agent to explore file system, powered by Gemini 3 Flash

UX-oriented React tools

The filesystem for agents.

A SQL database in Rust: SQLite-compatible, now also speaking Postgres (experimental). The LLVM of databases.

Open source local sandboxing for running AI generated code.

Capture screenshots, console errors, network issues, and user actions, giving developers full context instantly.

The absolute trainer to light up AI agents.

Embeddable Postgres with real-time, reactive bindings.

Beautiful, Modern & Opinionated Linux

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

Kimi K2 is the large language model series developed by Moonshot AI team

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.