Find the open-source solution that fits.

Project overview

Clawith gives each agent a persistent identity, long-term memory, private workspace, and autonomous triggers, then connects agents through an organization chart, messaging channels, and a shared knowledge feed. Teams also get role-based access, approvals, quotas, and audit logs. The platform can be self-hosted or used as a cloud service, but local deployment does not run models and still requires external LLM APIs.

Project overview

SkillHub gives organizations a self-hosted place to publish, discover, install, and manage reusable agent skills. Packages can use semantic versions and release tags, while team namespaces define membership, roles, visibility, and publishing policies. Review gates and audit logs support governed internal sharing behind an organization's firewall.

Project overview

MetaCubeXD provides a visual control surface for Mihomo, with live traffic statistics, latency testing for proxy groups, connection management, searchable rules, and streaming logs. It can run as a browser panel connected to an existing remote kernel, a desktop app that supervises a bundled Mihomo, or an all-in-one server for a router, NAS, or VPS. Bundled modes also add profile editing, validation, and activation. Desktop TUN routing requires a privileged helper, and a server exposed beyond a trusted LAN needs separate network controls or an authenticated reverse proxy.

Project overview

gophernotes adds a Go kernel to Jupyter Notebook and nteract, allowing live Go code to sit alongside equations, visualizations, and explanatory text in shareable documents. It evaluates code through the gomacro interpreter. On Windows, gomacro cannot use the required plugin support for third-party packages, so those notebooks should be run through the documented Docker setup.

Project overview

Scrcpy GUI wraps scrcpy in a desktop interface for displaying and controlling Android devices over USB or TCP/IP. It can use the computer’s keyboard and mouse, share clipboard content, capture screenshots or recordings, adjust streaming settings, and show multiple connected devices. The Android device must run at least Android 5.0 with ADB debugging enabled, and scrcpy itself must be installed and available in the environment. Some devices require an additional setting before input control works.

Project overview

Triangula uses an iterative evolutionary algorithm to approximate an image with triangles or other polygons. Users can work through the separate graphical application or the companion CLI, which generates an intermediate JSON result and later renders it to SVG or PNG. The number of points and optimization settings can be adjusted for different styles and detail levels. Unlike instant geometric filters, the algorithm improves over repeated iterations and may need meaningful processing time before the result reaches the desired fitness.

Project overview

Pennywise opens web pages and media in a small always-on-top window that can be resized, repositioned, and made partially transparent. A detached mode lets pointer interactions pass through to the window underneath, which is useful for tutorials, dashboards, reference pages, or videos while working. Builds are available for macOS, Windows, and Linux, but the project is no longer maintained, so users should verify compatibility with current operating systems and websites before relying on it.

Project overview

Add focused skills for App Store release notes, GitHub operations, iOS debugging, macOS packaging, SwiftUI and React improvements, and multi-agent review or bug-hunt workflows. Each skill is self-contained and installed under the Codex skills directory, so developers can invoke only the workflow relevant to the current project. The collection is especially useful for recurring Apple-platform and code-quality tasks.

Project overview

Every Code is a community fork of OpenAI Codex for local terminal development. It extends the upstream tool with browser actions and multi-agent workflows, while Auto Drive and background Auto Review support longer execution and non-blocking checks. It supports ChatGPT sign-in or API-key use, can orchestrate external CLIs such as Claude and Gemini, and is not an official OpenAI product.

Project overview

Cinny is a web client for the Matrix communication network. Users can open the hosted application or self-host the static build on a web server, Docker container, or container registry image. Administrators can configure default homeservers and explore pages, and must set up routing so direct application URLs resolve correctly. This repository focuses on the browser application; downloadable native desktop builds are maintained in the separate cinny-desktop project.

Project overview

Ever Gauzy combines ERP, CRM, HR management, applicant tracking, project work, time and activity tracking, sales, invoicing, and related business operations in one business management platform. Users can run an all-in-one desktop app with the interface, API, and a local database, or deploy the server edition with PostgreSQL; Docker Compose and Kubernetes options are also documented for self-hosting. The hosted SaaS is marked as alpha/testing, so it should be evaluated cautiously before operational use.

Project overview

Golutra turns existing coding CLIs such as Claude Code, Codex, Gemini, and OpenCode into a shared multi-agent workspace. Users can run agents in parallel, orchestrate longer workflows, import or export templates, inspect individual logs, inject prompts during execution, and track handoffs in a visual interface. It keeps the underlying CLI tools and project layout intact, making it useful for developers who want centralized oversight without migrating their work to a new agent runtime.

Project overview

GPT-Image2-Skill combines a curated prompt gallery, an Agent Skill, and the `gpt-image` CLI for OpenAI image generation and editing. You can request gallery examples in natural language from Codex, Claude Code, OpenClaw, Hermes, and similar runtimes, or copy prompts into the command line and adapt them for posters, UI mockups, game interfaces, photography, maps, typography, or reference-image edits. The repository also explains prompt structure in English and Chinese. Scientific figures are framed as references or reproducible workflow targets, not unchecked final publication assets.

Project overview

claude-devtools reads the Claude Code logs and transcripts already stored under `~/.claude/` and reconstructs file reads, searches, edits, tool inputs and outputs, subagent execution trees, and per-turn token attribution. It helps you investigate what an agent actually did and why context usage grew without rerunning the original task.

Project overview

PicList extends PicGo with cloud file management for S3-compatible storage, Aliyun OSS, Tencent COS, GitHub, WebDAV, SFTP, and other providers. It can browse, search, delete, and batch-rename remote files, sync configuration and gallery data across devices, and process images with compression, watermarks, resizing, rotation, and format conversion. It also integrates with Typora, Obsidian, and most existing PicGo plugins.

Project overview

uPic is a macOS client for sending images and files to a configured hosting service or object store. Upload from Finder, the clipboard, a screenshot, drag and drop, the Share extension, or the command line, then receive a URL, HTML snippet, or Markdown link on the clipboard. It supports several providers plus custom upload APIs. The project notes that only the App Store build is current, while other installation channels remain on an older release.

Project overview

Tabularis combines connection management, SQL editing, data browsing, notebooks, and visual execution plans in a cross-platform desktop workspace. PostgreSQL, MySQL/MariaDB, and SQLite are built in, with plugins for additional data sources. Its MCP server lets supported coding agents inspect schemas and run queries, though users needing dozens of drivers may prefer a broader database client.

Project overview

100ProjectsOfCode is a categorized collection of hands-on programming ideas ranging from web and networking tools to applications, AI, computer science, cryptography, and games. Pick a project, create a repository, implement and test it, then use the finished work as a portfolio piece before moving to another challenge. Many entries include suggested languages, tools, or example implementations, although that guidance is still incomplete in places.