CRG indexes your repository into a persistent local graph of functions, calls, imports and blast radius — then serves that context to Claude Code, Cursor, Copilot, Codex and any MCP-compatible client.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Headroom compresses everything your AI agent reads — tool outputs, logs, RAG chunks, files, and conversation history — before it reaches the LLM. Same answers, fraction of the tokens.

URL to markdown for agents.

Turn websites into optimized, low token output to supercharge your context. Save money on tokens

agent multiplexer that lives in your terminal.

workspaces, tabs, panes. mouse-native: click, drag, split. every agent at a glance: blocked, working, done. detach and reattach, agents keep running. no gui app, no electron, no mac-only native wrapper. you see the agent's own terminal, not someone's interpretation of it.

Semble is a code search library built for agents. It returns the exact code snippets they need instantly, using ~98% fewer tokens than grep+read. Indexing and searching a full codebase end-to-end takes under a second, with ~200x faster indexing and ~10x faster queries than a code-specialized transformer, at 99% of its retrieval quality (see benchmarks). Everything runs on CPU with no API keys, GPU, or external services.

Local-first, open-source alternative to Anthropic's Claude Design

Multi-agent orchestration system for Claude Code, GitHub Copilot, and other AI agents with persistent work tracking

Scan your website to see how ready it is for AI agents. We check multiple emerging standards — from robots.txt and Markdown negotiation to MCP, OAuth, Agent Skills and agentic commerce.

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.

A Claude Cowork skill that builds your entire PM operating system in under 5 minutes.

Agent harness

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf, Antigravity, Augment, Trae, Qwen Code, Cline, and CodeBuddy.

An open source toolkit that allows you to focus on product scenarios and predictable outcomes instead of vibe coding every piece from scratch.

Typst is a new markup-based typesetting system that is designed to be as powerful as LaTeX while being much easier to learn and use. Typst has:

• Built-in markup for the most common formatting tasks
• Flexible functions for everything else
• A tightly integrated scripting system
• Math typesetting, bibliography management, and more
• Fast compile times thanks to incremental compilation
• Friendly error messages in case something goes wrong

Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.

Maestro is an open-source framework that makes UI and end-to-end testing for Android, iOS, and web apps simple and fast.
Write your first test in under five minutes using YAML flows and run them on any emulator, simulator, or browser.

openDAW is a next-generation web-based Digital Audio Workstation (DAW) designed to democratize music production and to resurface the process of making music by making high-quality creation tools accessible to everyone, with a strong focus on education and hands-on learning.

openDAW is designed with a strong focus on separation of concerns:

The studio runs independently of any specific service infrastructure.
There is no required login, no vendor lock-in.
Users can work immediately in the browser without creating an account.

The Fluid Corpus Manipulation project (FluCoMa) instigates new musical ways of exploiting ever-growing banks of sound and gestures within the digital composition process, by bringing breakthroughs of signal decomposition DSP and machine learning to the toolset of techno-fluent computer composers, creative coders and digital artists.

Hurl is a command line tool that runs HTTP requests defined in a simple plain text format.

It can chain requests, capture values and evaluate queries on headers and body response. Hurl is very versatile: it can be used for both fetching data and testing HTTP sessions.

Hurl makes it easy to work with HTML content, REST / SOAP / GraphQL APIs, or any other XML / JSON based APIs.