Recently updated open-source projects

Think Better installs scenario-triggered skills that help Claude, Copilot, and similar assistants break down problems, compare options, review architecture, and make more explicit decisions. Skills can activate automatically or through named commands, while the CLI manages installation and checks. Running the skills requires Python 3; building or installing the CLI from source also requires Go 1.25+.

Peace Equalizer APO is a community-maintained graphical interface for Equalizer APO on Windows 10 and 11. It applies system-wide parametric equalization to games, music, video, and calls, with preamp and bass controls, headphone calibration, presets, VST support, and a real-time response graph. It is not an official release from the original Peace or Equalizer APO developers, and Equalizer APO must be installed first from a trusted source.

Startup Founder Skills packages common company-building tasks into agent workflows for pitch decks, investor research, outreach, product requirements, recruiting, engineering reviews, legal operations, finance, and marketing. A shared startup-context skill supplies the company's stage, product, market, team, metrics, and goals so each task can produce output tailored to the same business.

This library packages repeatable agent workflows for research, intelligence gathering, design, and content creation. Its catalog includes Hacker News and Product Hunt research, app-store intelligence, trademark checks, motion patterns, design tokens, creative direction, and visual QA. Users can install the entire collection or a selected skill through npx, with support for Claude Code, OpenClaw, Codex, Cursor, and similar tools; some integrations are keyless, while others require service-specific API credentials.

ScreenCaptureKit-rs gives Rust developers an idiomatic interface to Apple’s ScreenCaptureKit for capturing displays, windows, applications, system audio, and microphones. It supports runtime-agnostic async workflows and low-copy frame delivery for recording, transcription, and remote-desktop software. Features are gated by macOS versions, the base crate requires macOS 12.3 or later, and every app must obtain the user’s Screen Recording permission.

NetPad is a cross-platform C# playground for trying snippets, learning language features, and keeping reusable utility or administration scripts without managing full projects. Users can inspect complex output, visualize data, query databases with LINQ or SQL, and add NuGet packages or local assembly references to individual scripts. It runs as a desktop application or in a browser and is positioned as an open-source LINQPad alternative. A .NET SDK version 6 or later is required, with EF Core tools additionally needed for database connections.

Remote Sensing Research Radar is a Codex skill for daily or weekly monitoring of geospatial AI, optical remote sensing, large-scale Earth-observation data, and computer-vision methods that may transfer into the field. It discovers and ranks papers, repositories, datasets, benchmarks, and trends by novelty, evidence, reproducibility, and research fit, then produces reading queues, related-work tables, reproduction plans, or publishable directions. SAR, PolSAR, InSAR, microwave-only, and SAR-optical fusion work are excluded by default unless explicitly requested.

This skill turns a working prototype into a structured Figma review artifact. It creates a frame for each meaningful interaction state, maps elements to available design-system components, and adds flow arrows, conditions, edge cases, annotations, and optional Code Connect links. It requires Figma MCP tooling, and clients with limited tool support may produce a specification document instead of building the file directly.

Saga Reader is a desktop reading application that gathers online information from user-defined interests through search and RSS. It can pass collected articles to a local or cloud LLM for summarization, translation, guidance, and an interactive reading conversation. Interest prompts, source articles, and processed content are stored on the user's computer rather than in a hosted account. Retrieval still depends on available search providers, while AI processing depends on the model backend the user configures.

xgrok provides a management interface for proxy access and network tunneling across HTTP(S), TCP, and UDP. It is available as a Windows or macOS desktop application, while a Docker deployment exposes a web management interface. The project also covers reverse proxying, tunnel status, startup behavior, and proxy-based access. On macOS, the application may trigger system verification or “damaged app” warnings and require the manual quarantine-removal step described by the project.

Pile is a desktop journaling app for macOS and Windows that keeps journal data local and organizes reflection in separate “piles.” Optional AI tools can respond to an individual entry or answer questions across the entire journal. Users can connect an OpenAI API key or use Ollama for local AI instead. The project is described as experimental, and cloud-based reflections incur the user’s own API costs.

Railway Skills packages an installable `use-railway` skill for Claude Code, Codex, Cursor, Grok Build, and compatible environments. The Railway CLI setup can install the skill, configure the local MCP server where supported, and check whether the user is authenticated. The skill routes requests to action-oriented guidance for Railway tasks, while actual use requires a Railway account and an authenticated CLI session.

These skills let coding agents use context captured by Entire, including sessions, Checkpoints, prompts, and git history. Ask an agent to find earlier work, explain why code changed, review a branch, or prepare a session handoff without memorizing CLI commands. They are most useful in repositories with substantial captured history, and some indexed searches require the Entire CLI and login.

Readwise Skills turns Readwise and Reader data into reusable agent workflows. An installed agent can triage inbox articles, catch up on feeds in batches, quiz you on recently read material, draft book reviews, or build personalized reading pages, with an optional reader persona guiding later outputs. The skills require either the Readwise MCP server or the Readwise CLI to be installed and connected first.

Demystify observes API traffic and generates OpenAPI 3.1 specifications from what it sees, including inferred path parameters and request or response details across status codes and MIME types. The desktop app captures traffic through a built-in proxy, the browser extension watches requests in a tab, and the CLI converts HAR files; a library is available for programmatic integration. It is useful for documenting APIs whose behavior is easier to observe than to describe manually.

Skrun is a self-hostable, multi-model agent runtime that turns SKILL.md, AGENTS.md, or another instruction format into a POST /run endpoint. Its CLI initializes, versions, verifies, and invokes agents, while the runtime adds streaming events, asynchronous webhooks, tool calling, persistent state, an operator dashboard, and generated API documentation. Users bring their own model credentials, and the current self-hosted setup requires Node 20 or later with SQLite or Postgres.

This Figma Desktop plugin reads local colors, typography, spacing, radii, effects, grids, variables, and component-family signals from the active file. It generates editable DESIGN.md and SKILL.md files that Claude Code, Codex, Cursor, and similar tools can use as a design-system blueprint. The repository currently documents building it locally and importing its manifest as a Figma development plugin.

Install it in a project to generate agent instructions, reusable skills, a dependency graph, and Git hooks for tools such as Claude Code, Cursor, and Gemini. The setup helps agents answer structural questions and enforces rules around commits, file headers, and complexity; in-agent skills need no separate API key, while standalone CLI features may require one.