SDK Tools

PenguinHarness is an open-source self-improving harness built by the team behind LlamaFactory. Its AI-native SDK enables agents to build, evaluate, and optimize other agents. It supports 1,000+ models, reusable skills, tool and context management, automatic data generation, multi-agent evaluation, and closed-loop harness evolution. With one prompt and about $0.02, an agent can build a complete RAG application.

Effects SDK helps developers add production-ready AI video and audio effects to web, desktop, and mobile apps. Add background blur, virtual backgrounds, smart framing, lighting correction, beautification, overlays, avatars, and real-time noise suppression — all running client-side, without sending video or audio to our servers.

Native SDK is the complete toolkit for building beautiful native desktop applications: declarative markup, a predictable message-based state model, a modern component library, and its own native renderer — no browser, no WebView, no compromise.

Mozaik enables autonomous agent teams to work concurrently, react to events, communicate intelligently, and decide how collaboration should unfold during execution.

Agent 37 is managed hosting for persistent agents like Hermes, OpenClaw and ClaudeCode. So you don't need to run them on Mac minis or VPS yourself. One API call gives each of your customers their own always-on agent, from $3.44/mo. Founders use it to ship vertical agents to their own clients without babysitting servers.

Agent 37 is managed hosting for persistent agents like Hermes, OpenClaw and ClaudeCode. So you don't need to run them on Mac minis or VPS yourself. One API call gives each of your customers their own always-on agent, from $3.44/mo. Founders use it to ship vertical agents to their own clients without babysitting servers.

A macOS workbench where Claude, Codex, and Hermes run on your specs, research, and Figma files.

AEVS (Agent Execution Verification System) is a drop-in SDK that records every AI agent tool call and gives agents verifiable execution receipts. It captures the tool, inputs, outputs, status, and timing as tamper-evident proof, so teams can verify what an agent actually executed without relying on chat history or fragile logs.

A unified storage SDK for object and blob backends. One small, honest API. Web-standards I/O. An escape hatch when you need the native client.

Open Browser Use connects local AI agents to your real Chrome profile through an open-source MV3 extension, native host, CLI, MCP server, and JS/Python/Go SDKs. It can open and claim tabs, run CDP commands, inspect page state, watch downloads, handle file choosers, and keep agent tabs organized without a hosted automation service.

Build safer, smarter chat with CometChat Moderation, the all-in-one safety layer for conversations. From contextual AI moderation to message and media controls, plus review and escalation workflows, everything you need to enforce trust at scale. Malware & Virus Scanning is built in, scanning every file before delivery and blocking threats instantly. Turn it on from the Dashboard in minutes, no extra code required.

Replyke is the complete infrastructure layer for how users interact and create content in your app. Comments, reactions, spaces, feeds, notifications, chat, follows — every system your users need, already modeled, moderation-ready, and production-ready. Stop rebuilding the same user interaction systems. Install an SDK, wrap your app in a provider, and ship your first feature in under an hour. Multi-platform: React, React Native, Expo, and Node.js.

CometChat's Compact Message Composer, part of the CometChat UI Kits, brings rich text formatting to your chat app - bold, italic, strikethrough, underline, links, bullet points, blockquotes and more. Enabled with a single prop. Comes with a floating toolbar, keyboard shortcuts, and full control over how messages are sent. Drop it into any framework and ship a richer chat experience in minutes.

Twenty 2.0 turns our open-source CRM into a platform you can build on. Define your data model, custom objects, workflows, layouts, and widgets in code with our new SDK, shipped through your normal dev flow with the AI tools you already use. AI built in, custom agents, serverless functions, and full layout and navigation customization. Self-hostable. Fully yours.

Android CLI is a new agent-first toolkit that lets developers build Android apps directly from the terminal—faster and with less guesswork. It combines CLI commands, modular “skills,” and a live knowledge base to guide AI agents with best practices, enabling rapid setup, project creation, testing, and deployment while reducing token usage and speeding workflows up to 3x.

Every QA debug loop looks the same — CI fails, you open logs, Slack, Jira, Grafana. 45 minutes later, still no root cause. Ask AI fixes that. Type a question, get a rendered artifact — dashboards, sprint reports, test plans, stakeholder slides — built from your live Playwright data. No queries. No config. Just answers. Free 14-day trial. No credit card. Built by the founding team behind LambdaTest Test Insights.

21st Agents SDK is the fastest way to add an AI agent to your app. Define your agent in TypeScript, deploy in one command, and embed a production-ready chat UI with Built-in streaming, session management, usage billing, and observability — so you can focus on what makes your agent unique, not infrastructure. Backed by Y Combinator (W26).

NexaSDK for Mobile lets developers use the latest multimodal AI models fully on-device on iOS & Android apps with Apple Neural Engine and Snapdragon NPU acceleration. In just 3 lines of code, build chat, multimodal, search, and audio features with no cloud cost, complete privacy, 2x faster speed and 9× better energy efficiency.

LLMs are great at writing code but struggle with writing tool calls. Code Mode solves this by giving your model ONE powerful tool: a TypeScript execution sandbox with access to your entire toolkit. Complex, multi-step workflows thereby become a single batched execution. Independent studies show massive gains: 60% faster execution, 68% fewer tokens, 88% fewer round-trips, while Anthropic's research team found a massive reduction of 98.7% in token usage using CodeMode.

Hopx lets you spin up fully isolated Linux micro-VMs in ~100 ms — perfect for running AI agents, notebooks, or untrusted code safely at scale. Each sandbox runs in its own Firecracker microVM, with full state persistence, SDKs for Python, JS, Go, and more. No cold-start lag. No runtime limits. Just raw performance and security.

Start with an API spec. Generate SDKs in multiple languages and interactive API documentation tailored to your brand.