App Launches
AI & developer apps — the latest launches, ranked, and browsable by category.
Today's Top Launches
-
1
MiniMax H3232
Unified video generation for motion design and branding
-
2
Miniback9
Bug reports that come with the context to actually fix them
-
3
Threehub8
Complex Product Quoting made easy
-
4
Numa5
Private AI accountant that runs 100% locally
-
5
StayOps AI4
The World's First AI Workforce™
More applications 3313
-
Claude DevTools—
The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.
-
PostHog: Self-Driving Product Analytics Platform—
:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. S...
-
MLX Serve - Native Apple Silicon LLM Server—
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
-
Amazon Q to API Bridge—
Amazon Q to API Bridge：一个使用 FastAPI 实现的桥接服务，将 Amazon Q Developer 变成兼容 OpenAI Chat Completions 和 Claude Messages 的 API，支持多账号管理、随机负载均衡和流式响应。
-
LLM Knowledge Base System—
LLM-powered personal knowledge base — raw articles → compiled wiki → Q&A + outputs. Claude writes, you curate.
-
Natively: Open-Source AI Meeting Assistant—
Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Interview Coder. Real-time transcription, AI meeting notes, lecture recording, local RAG, BYOK, and stealth mode. Runs locally. No su...
-
Refly: Open-Source Agent Skills Builder—
The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.
-
Claude Code Usage Dashboard—
A local dashboard for tracking your Claude Code token usage, costs, and session history. Pro and Max subscribers get a progress bar. This gives you the full picture.
-
Raptor: AI Security Research Agent—
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
-
IM4Codes: Instant Messaging for Agents—
The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.
-
Skill Store - AI Agent Skills Directory—
收录最全、更新最快的技能Skills 商店，涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流等多个领域的 72 个精选技能包。所有技能已打包完成，可直接安装使用！ 该商店中自动抓取了 Github 上的所有的 Skills 项目，并按照分类、更新时间、Star 数量等标签进行整理。
-
Tiger CoWork: Self-Hosted AI Workspace—
A self-hosted AI workspace unifying chat, code execution, parallel multi-agent orchestration, and project management. Each agent runs on a distinct provider — OpenAI-compatible APIs, Claude Code, or Codex CLI. MCP servers extend the toolbox. Built for 100+ tool-call sessions with context compress...
-
OpenCode Fusion: Multi-Model Team for Coding—
Main agent plans and reviews; cheaper sidekick edits. Devin Fusion pattern for OpenCode
-
Tabularis: SQL Workspace with AI Integration—
Open-source desktop SQL workspace for PostgreSQL, MySQL/MariaDB, SQLite and 13+ more databases like DuckDB, ClickHouse, Redis and Firestore. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN.
-
Plexus: Universal LLM API Gateway—
Unified API gateway for multiple AI providers (OpenAI, Anthropic, Gemini, etc.). Switch models and providers without changing client code. Features OAuth authentication, quota tracking, embeddings, transcriptions, and OpenAI-compatible endpoints.
-
Frago: Operating System for AI Agents—
Multi-runtime automation infrastructure for AI agents. Native CDP browser control, metadata-driven Recipe system, and persistent Run context management.
-
Forge: Open Agent Skills Runtime—
Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already operate. Write a SKILL.md. Compile to a portable, hardened agent. Deploy it anywhere containers run: Kubernetes, on-prem, ai...
-
Agent Flow—
Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.
-
WhyBuddy: Product Rehearsal Engine—
A Simple and Universal Product Rehearsal Engine, Speccing Anything. 简洁通用的产品推演引擎，推演万物。
-
vllm-mlx: Apple Silicon LLM Server—
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.
-
Tabbit2API: OpenAI & Claude Adapter—
Convert Tabbit browser’s internal API into OpenAI and Anthropic Claude-compatible interfaces for seamless multi-account AI service integration.
-
Adnify: AI Agent Code Editor—
Adnify—A lightweight, highly customizable AI Agent Editor.It delivers a superior experience beyond mainstream AI coding tools, featuring instant startup and lag-free performance.
-
OpenUsage — Track AI Coding Subscriptions—
Burning through your subscriptions too fast? Paying for stuff you never use? Stop guessing. OpenUsage is free and open source.
-
GraphJin: Governed Graph for AI Agents—
One governed graph for AI agents — GraphQL + MCP over your databases, files, APIs, and code