Claude Agent SDK
The Claude Agent SDK is a developer toolkit that enables the creation of autonomous AI agents powered by Claude, allowing them to perform real-world tasks beyond simple text generation by interacting directly with files, systems, and tools. It provides the same underlying infrastructure used by Claude Code, including an agent loop, context management, and built-in tool execution, and is available for use in Python and TypeScript. With this SDK, developers can build agents that read and write files, execute shell commands, search the web, edit code, and automate complex workflows without needing to implement these capabilities from scratch. It maintains persistent context and state across interactions, enabling agents to operate continuously, reason through multi-step problems, take actions, verify results, and iterate until tasks are completed.
Learn more
ToolSDK.ai
ToolSDK.ai is a free TypeScript SDK and marketplace that accelerates building agentic AI applications by providing instant access to over 5,300+ MCP (Model Context Protocol) servers and composable tools with one line of code, enabling developers to wire up real-world workflows combining language models with external systems. The platform exposes a unified client for loading packaged MCP servers (e.g., search, email, CRM, task management, storage, analytics) and converting them into OpenAI-compatible tools, handling authentication, invocation, and result orchestration so assistants can call, compare, and act on live data from services like Gmail, Salesforce, Google Drive, ClickUp, Notion, Slack, GitHub, analytics platforms, and custom web search or automation endpoints. It includes example quick-start integrations, supports metadata and conditional logic in multi-step orchestrations, and makes scaling to parallel agents and complex pipelines straightforward.
Learn more
VibeKit
VibeKit is a simple, open source SDK for safely running Codex and Claude Code agents in secure, customizable sandboxes. It enables you to embed coding agents directly in your app or workflow via a drop‑in SDK. import VibeKit and VibeKitConfig, and call generateCode with prompts, modes, and streaming callbacks for live output handling. VibeKit runs code in fully isolated private sandboxes, supports customizable environments where you can install packages, and is model‑agnostic, letting you choose any compatible Codex or Claude model. It streams agent output efficiently, maintains full prompt and code history, provides async run handling, integrates with GitHub for commits, branches, and pull requests, and supports telemetry and tracing (via OpenTelemetry). Compatible sandbox providers include E2B (today), with Daytona, Modal, Fly.io, and others coming soon, plus support for any runtime that meets your security needs.
Learn more
Convo
Kanvo provides a drop‑in JavaScript SDK that adds built‑in memory, observability, and resiliency to LangGraph‑based AI agents with zero infrastructure overhead. Without requiring databases or migrations, it lets you plug in a few lines of code to enable persistent memory (storing facts, preferences, and goals), threaded conversations for multi‑user interactions, and real‑time agent observability that logs every message, tool call, and LLM output. Its time‑travel debugging features let you checkpoint, rewind, and restore any agent run state instantly, making workflows reproducible and errors easy to trace. Designed for speed and simplicity, Convo’s lightweight interface and MIT‑licensed SDK deliver production‑ready, debuggable agents out of the box while keeping full control of your data.
Learn more
