SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

Skeptical ship/no-ship adversarial code review of a git diff or branch — runs against any LLM (API or local CLI agent)

The agent that grows with you

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

✂️ Find unused files, dependencies and exports in your JavaScript and TypeScript projects. Knip it before you ship it!

Aspire is the tool for code-first, extensible, observable dev and deploy.

better agentic engineering

CF-Hero is a reconnaissance tool that uses multiple data sources to discover the origin IP addresses of Cloudflare-protected web applications

Build Real-Time Knowledge Graphs for AI Agents

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Production-grade engineering skills for AI coding agents.

Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

CLI for common Playwright actions. Record and generate Playwright code, inspect selectors and take screenshots.

Agent Skills for Google products and technologies

Raster to Vector Graphics Converter

SQL implementation TypeIDs: type-safe, K-sortable, and globally unique identifiers inspired by Stripe IDs

Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities bef…

A vault for securely storing and accessing AWS credentials in development environments

Wraps your package manager, preventing installation of malicious packages.

AI agents running research on single-GPU nanochat training automatically

Sub-millisecond VM sandboxes for AI agents via copy-on-write forking

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

OpenShell is the safe, private runtime for autonomous AI agents.

A github action for waiting for the vercel preview

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

Autonomous experiment loop extension for pi