Articles from github.com
93 kept
- GitHub - sindresorhus/terminal-image: Display images in the terminal
The terminal-image npm package lets developers display PNG, JPEG, and GIF images directly in compatible terminals using native graphics protocols or ANSI block fallback.
- Release v2.0.0 · unlayer/react-email-editor
Unlayer's react-email-editor v2.0.0 drops support for React <16.8 and Node <18, adds ESM builds, fixes destroy-on-unmount, and updates tooling across the stack.
- GitHub - workweave/router at console.dev
Router from Weave is a drop-in proxy that routes each prompt to the optimal model in under 50ms, cutting costs by 40-70% with just an endpoint change.
- GitHub - lirantal/nodejs-cli-apps-best-practices: The largest Node.js CLI Apps best practices list ✨
A curated list of 38 best practices for building user-friendly, empathic, and interoperable Node.js CLI applications, covering experience, distribution, interoperability, accessibility, testing, errors, development, analytics, versioning, and security.
- GitHub - aidenybai/cnfast: Fast drop in replacement for `cn`
cnfast is a drop-in replacement for tailwind-merge that merges Tailwind classes 3.8x faster on average with byte-identical output.
- GitHub - emilkowalski/skills: Skills for Design Engineers.
A curated set of coding skills for design engineers that encode animation and UI best practices, helping AI agents produce better interfaces through domain expertise.
- GitHub - af/envalid: Environment variable validation for Node, Bun, and other compatible JS runtimes
Envalid provides validation and immutable access to environment variables, ensuring they meet expected formats before a Node.js or Bun program runs.
- GitHub - kristiandupont/kanel: Generate Typescript types from Postgres
Kanel generates TypeScript types from a live PostgreSQL database, offering type safety without an ORM.
- GitHub - Automattic/juice: Juice inlines CSS stylesheets into your HTML source.
Juice is a Node.js library that inlines CSS properties from style tags into HTML style attributes, primarily for HTML emails.
- GitHub - baidu/Unlimited-OCR: Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
Baidu releases Unlimited-OCR, a VLM-based OCR that processes entire documents in a single pass using reference sliding window attention to avoid memory overflow.
- GitHub - tamnd/kage at console.dev
A new tool called kage clones websites into offline, script-free static mirrors by rendering each page in headless Chrome and stripping JavaScript before saving.
- GitHub - ljtn/epiq at console.dev
Epiq is a local-first, Git-backed issue tracker with a terminal UI and MCP server for agent integration, requiring no SaaS accounts.
- GitHub - columnar-tech/databow at console.dev
databow is a command-line tool for querying databases via ADBC, offering an interactive SQL shell, syntax highlighting, formatted output, and file export.
- GitHub - gajus/zod-compiler: Compile Zod schemas into zero-overhead validation functions at build time. Works with Vite, webpack, esbuild, Rollup, etc
The zod-compiler tool compiles Zod schemas into zero-overhead validation functions at build time, providing 2-75x faster validation without requiring any code changes.
- GitHub - millionco/react-doctor: Your agent writes bad React. This catches it
React Doctor is a deterministic scanner that audits React codebases for issues across state, effects, performance, architecture, security, and accessibility, and integrates with coding agents and CI pipelines.
- GitHub - DietrichGebert/ponytail: Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Ponytail is a plugin that reduces AI agent code output by up to 54% by forcing a lazy senior dev heuristic ladder (YAGNI, reuse, stdlib, one-liners).
- GitHub - Kaelio/ktx: ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or any other AI agent to query data accurately and with full context of your company
ktx is a self-improving context layer that automatically builds approved metric definitions and business knowledge to let AI agents query data warehouses accurately.
- GitHub - apple/container: A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon.
Apple released an open-source tool, `container`, that creates and runs OCI-compatible Linux containers as lightweight VMs on macOS 26+ Apple Silicon Macs.
- GitHub - firecrawl/firecrawl-workflows
Firecrawl Workflows provides outcome-focused skills for AI coding agents to produce research reports, SEO audits, lead lists, and other deliverables using the Firecrawl web extraction tool.
- GitHub - Ataraxy-Labs/sem: Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 26 languages via tree-sitter. Built for coding agents.
sem is an open-source CLI that replaces line-level git diffs with entity-level awareness (functions, classes, methods) using tree-sitter parsing, designed for both human developers and AI coding agents.
- GitHub - alibaba/open-code-review: Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Alibaba's Open Code Review is a hybrid CLI tool combining deterministic pipelines with an LLM agent for precise, token-efficient code reviews at scale.
- GitHub - anthropics/defending-code-reference-harness: Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Anthropic released an open-source reference harness and Claude Code skills for automating vulnerability discovery, triage, and patching using Claude, alongside a managed product called Claude Security.
- GitHub - ideogram-oss/ideogram4: Ideogram 4: Open image model at the forefront of design
Ideogram 4 is an open-weight text-to-image foundation model with structured JSON prompting, best-in-class text rendering, and state-of-the-art design generation performance.
- GitHub - AllThingsSmitty/typescript-tips-everyone-should-know: A curated collection of practical TypeScript patterns that improve safety, readability, maintainability, and developer experience.
A curated collection of practical TypeScript patterns that improve safety, readability, maintainability, and developer experience.
- GitHub - Michaelliv/pi-dynamic-workflows
A Pi extension adds a workflow tool that lets the model write JavaScript scripts to fan out work across isolated subagents and synthesize results.
- agent-skills/skills/autoreview/SKILL.md at main · openclaw/agent-skills
The piece defines a structured pre-commit code review skill for AI agents, specifying contracts, scope governance, and engine isolation across multiple review engines including Codex, Claude, and others.
- GitHub - perspective-dev/perspective: A data visualization and analytics component, especially well-suited for large and/or streaming datasets.
Perspective is an interactive analytics and data visualization component for large and streaming datasets, built with WebAssembly, Python, and Rust.
- GitHub - zeke/agents.md: My global instructions for AI agents like OpenCode
A developer shares anonymized global instructions for AI coding agents, covering behavior, commit style, and pushback rules.
- GitHub - nkzw-tech/cloudsail: Self-hosted instant sandboxes for coding agents on Cloudflare.
Cloudsail is an alpha tool that provides self-hosted instant sandboxes for coding agents on Cloudflare, with secure credential injection and controlled egress.
- GitHub - kubernetes-sigs/agent-sandbox: agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
Kubernetes SIG Apps introduces agent-sandbox, a CRD and controller for managing isolated, stateful, singleton workloads like AI agent runtimes.
- GitHub - anomalyco/models.dev: An open-source database of AI models.
Models.dev is an open-source, community-contributed database of AI model specifications, pricing, and capabilities, accessible via API and TOML data files.
- GitHub - cyco130/vavite: Develop server-side applications with Vite
vavite is a Vite plugin that enables using Vite to transpile and bundle server-side code, simplifying SSR and non-SSR application development.
- GitHub - 2b2tplace/1m_release: The Largest World Download Project in 2b2t, and in Minecraft altogether. Full info + Renders + Timelapses (+ Torrent soon)
A team spent over a year downloading 24 TB of 2b2t Minecraft server world data, covering a 1m² Overworld area and other dimensions, and is preparing a public torrent.
- GitHub - anthropics/claude-for-legal: A suite of plugins for legal workflows
Anthropic open-sources a suite of Claude plugins covering 60+ legal workflows, deployable as desktop agents, CLI skills, or managed API agents.
- GitHub - zenbu-labs/zenbu.js: The framework for building hackable software
Zenbu.js is a JavaScript framework that makes applications extensible by default, allowing users to modify source code or inject plugins with hot reloading.
- Release v7.0.0 · Unitech/pm2
PM2 v7.0.0 drops Node.js 16, internalizes several dependencies to reduce supply-chain risk, and refactors the core process manager.
- bun/docs/PORTING.md at claude/phase-a-port · oven-sh/bun
This document defines the rules and idiom map for porting the Bun JavaScript runtime from Zig to Rust in a two-phase process: Phase A produces a draft Rust file, and Phase B makes it compile.
- GitHub - gragland/codex-imessage-handoff: Work from iMessage baby
A Codex skill routes prompts from iMessage or SMS into a local Codex thread via Sendblue, enabling remote continuation of coding sessions.
- GitHub - nexu-io/open-design: 🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems 🖼 Generate web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Runs on Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen / Copilot / Hermes / Kimi CLI.
Open Design is an open-source, local-first desktop app that turns coding agents into design engines for generating prototypes, slides, images, and videos with brand-grade design systems and multiple export formats.
- GitHub - stripe/link-cli: Let your agents spend on your behalf. Your payment credentials are never exposed. You approve every purchase.
Stripe's Link CLI lets AI agents generate one-time-use virtual cards or shared payment tokens for purchases, with user approval required and real card details never exposed.
- GitHub - vincentkoc/slacrawl: cli terminal app for slack with sqlite backend
Slacrawl is a Go CLI tool that mirrors Slack workspace data into local SQLite for offline search, querying, inspection, and git-backed archive sharing.
- GitHub - posit-dev/ggsql: A SQL extension for declarative data visualisation based on the Grammar of Graphics.
ggsql is a SQL extension that enables declarative data visualization within SQL queries using the Grammar of Graphics, currently supporting DuckDB and SQLite.
- GitHub - NikolayS/pgque: PgQue – Zero-bloat Postgres queue. One SQL file to install, pg_cron to tick.
PgQue is a zero-bloat Postgres queue engine implemented entirely in PL/pgSQL, using snapshot-based batching and table rotation to avoid the dead-tuple bloat that plagues SKIP LOCKED queues.
- GitHub - heygen-com/hyperframes: Write HTML. Render video. Built for agents.
HyperFrames is an open-source framework that turns HTML into deterministic MP4 videos, with AI agent skills and CLI tooling.
- GitHub - matthartman/ghost-pepper: Hold-to-talk speech-to-text for macOS. 100% local, powered by WhisperKit and local LLM cleanup. Hold Control to record, release to transcribe and paste.
Ghost Pepper is a free, open-source macOS app that provides 100% local, hold-to-talk speech-to-text and meeting transcription using on-device AI models.
- GitHub - slavingia/skills: Claude Code skills based on The Minimalist Entrepreneur by Sahil Lavingia
A GitHub repository offers 10 Claude Code skills based on Sahil Lavingia's book The Minimalist Entrepreneur, guiding users through community finding, validation, building, and growth.
- GitHub - MaxGfeller/open-harness: A code-first, composable SDK to build powerful AI agents
OpenHarness is a code-first, composable SDK for building powerful AI agents, built on Vercel's AI SDK and inspired by tools like Claude Code.
- GitHub - MiniMax-AI/skills
MiniMax-AI released a repository of structured development skills for AI coding agents, covering frontend, fullstack, mobile, shader, and document generation.
- GitHub - microsoft/apm: Agent Package Manager
Microsoft's APM is an open-source dependency manager for AI agents that lets teams declare agent configurations in a manifest file and reproduce them across tools like Copilot, Claude, and Cursor.
- GitHub - chenxin-yan/crust: A TypeScript-first, Bun-native CLI framework with composable modules.
Crust is a TypeScript-first, Bun-native CLI framework offering composable modules for command routing, argument parsing, prompts, validation, and persistence.
- GitHub - greyhaven-ai/autocontext: a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
A recursive self-improving harness runs tasks against evaluation, retains useful lessons, and outputs traces, reports, playbooks, and training artifacts for future agent runs.
- GitHub - NVIDIA/OpenShell: OpenShell is the safe, private runtime for autonomous AI agents.
NVIDIA OpenShell provides a sandboxed runtime with YAML-policy enforcement for filesystem, network, process, and inference access, protecting credentials and infrastructure during autonomous AI agent execution.
- GitHub · Change is constant. GitHub keeps you ahead.
GitHub markets its AI-powered platform, featuring Copilot for code writing and agent mode, collaboration tools, and AI-driven security, as essential for modern software development.
- GitHub - Gen-Verse/OpenClaw-RL: OpenClaw-RL: Train any agent simply by talking
OpenClaw-RL is a fully asynchronous reinforcement learning framework that trains personalized AI agents from natural conversation feedback and supports real-world agentic RL across terminal, GUI, SWE, and tool-call settings.
- GitHub - RunanywhereAI/RCLI: Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG
RCLI is an open-source, on-device voice AI for macOS that runs STT, LLM, TTS, and VLM entirely locally on Apple Silicon, with sub-200ms latency and no cloud dependency.
- GitHub - jackwener/twitter-cli: A CLI for Twitter/X — feed, bookmarks, and user timeline in terminal
twitter-cli is a terminal-first CLI for Twitter/X that reads timelines, bookmarks, and user profiles without API keys, with write support and AI agent integration.
- GitHub - JeanMeijer/slopmeter: CLI tool to show off how many tokens you use
Slopmeter is a CLI tool that generates usage heatmaps and token-count stats for six AI coding assistants over the past year.
- GitHub - akinalpfdn/claude-ground
Claude Ground provides modular rules, skills, and templates to impose structural discipline on Claude Code, preventing common workflow failures.
- GitHub - appsoftwareltd/vscode-agent-kanban: VS Code extension kanban board for agentic AI workflows
VS Code Agent Kanban is an extension that adds a kanban board with plan/todo/implement markdown workflows for managing agentic AI coding sessions in GitHub Copilot Chat.
- GitHub - es617/claude-replay: Community tool to convert Claude Code session transcripts into self-contained, embeddable HTML replays
Claude-replay converts AI coding agent session transcripts into self-contained, interactive HTML replays for sharing and embedding.
- GitHub - withastro/flue: The sandbox agent framework.
Flue is a TypeScript framework for building autonomous AI agents with a programmable harness that provides sandboxes, tools, skills, and durable execution across local and cloud runtimes.
- GitHub - vercel-labs/openreview: An open-source, self-hosted AI code review bot powered by Vercel.
Vercel Labs released OpenReview, an open-source, self-hosted AI code review bot that deploys to Vercel and uses Claude to provide on-demand PR reviews with inline suggestions and automated fixes.
- GitHub - jonathimer/devmarketing-skills: Claude Code and AI Agents Skills for Developer Marketing.
A GitHub repository offering markdown skills for AI agents to specialize in developer marketing, including audience analysis, content, and community engagement.
- GitHub - hamelsmu/evals-skills: Skills for AI Evals to compliment the course: AI Evals For Engineers & PMs
Hamelsmu's GitHub repo provides Claude Code plugin skills for auditing and improving LLM evaluations, aimed at engineers and PMs.
- GitHub - open-pencil/open-pencil: AI-native design editor. Open-source Figma alternative.
OpenPencil is an open-source, AI-native design editor that opens .fig files, offers a programmable CLI and Vue SDK, and supports real-time collaboration and MCP integration.
- GitHub - googleworkspace/cli: Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
Google releases a dynamic CLI for Workspace APIs that builds commands from the Discovery Service at runtime and includes 100+ AI agent skills.
- GitHub - hyperspell/hyperspell-openclaw: Hyperspell plugin for OpenClaw
Hyperspell provides context and memory for AI agents through an OpenClaw plugin that syncs data across sources like Notion and Slack.
- GitHub - HugoRCD/evlog: Logging that makes sense. Wide events, structured errors, zero chaos.
evlog is a TypeScript-first logging library that collapses multiple log lines into one structured wide event per request with context and self-documenting errors.
- GitHub - poteto/noodle: Orchestrate agents using skills
Noodle is a Go-based open-source tool for orchestrating agents using skill-based workflows.
- GitHub - arjunkmrm/recall: a skill for claude code and codex to recall past conversations
Recall indexes past Claude Code, Codex, and pi sessions into a SQLite FTS5 database for full-text search and resumption.
- GitHub - apple/python-apple-fm-sdk: Python bindings for access to the on-device model at the core of Apple Intelligence through the Foundation Models framework
Apple released a Python SDK for accessing the on-device foundation model powering Apple Intelligence on macOS.
- GitHub - wesm/agentsview: Fast local coding agent session viewer for Claude, Codex, Gemini, with analytics dashboard and full text search
agentsview is a local-first tool for browsing, searching, and analyzing session data and costs across multiple AI coding agents via a web UI and CLI.
- GitHub - corywilkerson/fastpass: Cloudflare Access in 60 seconds
fastpass is a CLI tool that automates Cloudflare Access configuration for adding authentication to internal apps via the Cloudflare API.
- GitHub - mandarwagh9/MachineAuth: Secure OAuth 2.0 authentication for AI agents and machine-to-machine communication.
MachineAuth provides OAuth 2.0 authentication and permission infrastructure designed for AI agents to securely access APIs and services.
- GitHub - nabeelhyatt/coworkpowers: Superpowers for knowledge work in Claude Code
CoworkPowers is a Claude Code plugin that implements a research-work-review-compound loop to systematically improve knowledge work quality and speed by extracting reusable patterns after each task.
- GitHub - supermemoryai/openclaw-supermemory: OpenClaw Supermemory lets to have long-term memory and recall for your openclaw agent.
OpenClaw Supermemory plugin gives OpenClaw agents long-term memory by automatically storing and recalling conversations via the Supermemory cloud service.
- GitHub - R44VC0RP/pgrok: Personal ngrok alternative. Expose local ports to the internet with automatic HTTPS via SSH tunnels + Caddy.
Pgrok is an open-source self-hosted ngrok alternative that exposes local ports to the internet via SSH tunnels with automatic HTTPS, a TUI dashboard, and HTTP request inspection.
- GitHub - KeygraphHQ/shannon: Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark.
Shannon is an autonomous AI pentester that analyzes source code and executes real exploits to prove vulnerabilities, achieving a 96.15% success rate on the XBOW benchmark.
- GitHub - AnthonyRonning/sage
Sage is an experimental, self-hosted AI assistant with persistent memory, encrypted messaging via Signal or Nostr, and confidential LLM inference inside a TEE.
- GitHub - needle-tools/md-browse: Markdown Browser – See the web like an AI does
md-browse is a markdown-first browser built with Electrobun that prioritizes markdown content and converts HTML to clean markdown using Turndown.
- GitHub - ibelick/webclaw: Fast web client for OpenClaw
WebClaw is a fast web client for OpenClaw, installable via npx and currently in beta.
- GitHub - mitchellh/vouch: A community trust management system based on explicit vouches to participate.
Vouch is a trust management system requiring users to be vouched for before contributing, designed to filter low-quality AI-generated contributions in open-source projects.
- GitHub - pierceboggan/primer: Get your repo ready for AI.
AgentRC is an experimental Microsoft tool that measures a repository's AI-readiness and generates contextual instruction files for coding agents.
- GitHub - gavrielc/nanoclaw: My personal Claude assistant that runs in Apple containers. Lightweight, secure, and built to be understood and customized for your own needs.
NanoClaw is a lightweight, container-isolated AI assistant that runs Claude agents in Docker with filesystem-level security, multi-channel messaging, and a small codebase designed for easy customization.
- Exploring Solutions to Tackle Low-Quality Contributions on GitHub · community · Discussion #185387
A maintainer proposes PRAS Bot, a signal-based triage tool that scores pull requests as likely-spam, needs-review, or looks-good to filter low-quality contributions on GitHub.
- Kimi-K2.5/tech_report.pdf at master · MoonshotAI/Kimi-K2.5
Moonshot AI releases its most powerful model, Kimi K2.5, detailing its architecture and capabilities in a technical report.
- GitHub - kanishkg/endless-terminals
Endless Terminals is an autonomous pipeline that procedurally generates terminal-use tasks without human annotation for training terminal agents with reinforcement learning.
- GitHub - ComposioHQ/open-claude-cowork: Open Source version of Claude Cowork built with Claude Code and Composio Tool Router
An open-source desktop chat application that integrates Claude Agent SDK and Composio Tool Router to automate work across desktop and 500+ SaaS apps.
- GitHub - matsonj/mviz: A chart & report builder designed for use by AI.
mviz is a skill for Claude that generates static HTML charts and reports from compact JSON specs, optimized for fast, AI-driven ad hoc analysis with 17 chart types and a 16-column grid.
- GitHub - GMLR-Penn/Multiplex-Thinking: Multiplex Thinking
Multiplex Thinking introduces a token-wise branch-and-merge mechanism enabling efficient multi-path reasoning in large language models while keeping token representations compact.
- GitHub - puffinsoft/syntux: Consistent, cacheable generative UIs for the web.
syntux generates React UIs from data values using a JSON-DSL schema, enabling streaming, caching, custom components, and reactivity.
- GitHub - brianlovin/claude-config: My Claude Code setup
A developer's configuration for Claude Code and Codex provides settings, reusable skills (e.g., browser automation, accessibility review), and a managed sync script with backups.
- GitHub - langchain-ai/openwork
openwork is a desktop interface for building deep AI agents with filesystem capabilities, planning, and subagent delegation via deepagentsjs.