TypeScript

colinhacks/zod

Zod: TypeScript schema validation with zero-dependency type inference — Zod lets you define schemas once and get both runtime validation and static TypeScript types from them, removing the need to keep separate interfaces in sync. It's aimed at TypeScript developers who want safer parsing of API responses, form input, or config files without extra boilerplate.

TypeScript-first schema validation with static type inference

invoke-ai/InvokeAI

A polished local web UI for Stable Diffusion workflows — Invoke packages Stable Diffusion image generation into a React-based web UI with a free, commercially-friendly license, aimed at both professionals and hobbyists. It supports txt2img, img2img, inpainting, outpainting, and runs locally on Windows, macOS, or Linux, with a dedicated launcher for installation.

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

videojs/video.js

Video.js v10 rebuilds the player as a modular, React-ready framework — Video.js v10 is now stable, rewritten as a modular, composable media player framework for both plain Web and React/Svelte/Vue apps. It ships an AI-agent skill so coding assistants read version-matched docs before generating integration code, aimed at developers upgrading or starting fresh.

Video.js v10 - open source media player framework for HTML and React.

genlayerlabs/genlayer-project-boilerplate

A GenLayer starter kit built around a football-bets intelligent contract — This boilerplate demonstrates GenLayer intelligent contracts with web access and LLM integration via a football betting example. It bundles fast in-memory direct tests, full integration tests against GenLayer Studio, contract linting, a CI pipeline, and a Next.js 15 + TypeScript frontend, giving developers a complete reference setup for building and testing GenLayer dApps.

mattermost/mattermost

Self-hosted chat platform adds AI integration and voice calling — Mattermost is an open core, self-hosted collaboration platform combining chat, workflow automation, voice calling, screen sharing, and AI integration. Built in Go and React, it runs as a single Linux binary on PostgreSQL, with monthly MIT-licensed releases. Suited for teams needing DevSecOps, incident resolution, or IT service desk workflows on their own infrastructure.

Mattermost is an open source platform for secure collaboration across the entire software development lifecycle..

Companion-Inc/feynman

A CLI agent that automates literature reviews and paper audits — Feynman is an open-source CLI research agent with built-in workflows like /lit, /deepresearch, /audit and /replicate for literature review, paper critique, code-vs-claims auditing and replication planning. It targets researchers and ML practitioners who want structured, citation-checked investigation instead of ad-hoc chat prompts.

The open source AI research agent.

atomicstrata/llm-wiki-compiler

A CLI compiler that turns raw sources into an interlinked wiki — llmwiki compiles raw documents into an interlinked, Obsidian-friendly wiki using LLMs. Version 1.5 decouples wiki behavior from storage, adds bearer-authenticated Converse gateways, removes the fixed concept page limit, and gives the live viewer auto-refresh after compiles. Useful for anyone building and maintaining a growing knowledge base from scattered source material.

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

openclaw/openclaw

A self-hosted AI assistant that lives in your chat apps — OpenClaw runs locally and meets you across Discord, iMessage, Slack, Teams, Telegram, WhatsApp and native apps, keeping state, memory and credentials on your own hardware. Model backends like Claude, Codex or local models plug in interchangeably, and one Gateway scales from a personal laptop setup to shared team deployments.

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

browserbase/stagehand

An SDK that gives Playwright scripts AI-driven browser agents — Stagehand combines Playwright automation with AI actions, letting developers mix deterministic code and natural-language commands to extract data or interact with any website. It integrates with tools like Claude Code, Codex, Eve, and Mastra, targeting developers building browser agents in TypeScript or Python.

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

geastack/examples

A multi-target app gallery for building and testing GeaStack apps — This repo collects sample TSX apps that run across web, ESP32, GeaOS, and Apple targets, each with a Gea manifest describing compatibility and build scripts. It serves as the shared app source for the GeaStack simulator, VS Code/Cursor extension, and marketing demos, useful for anyone building or testing Gea targets.

Example Gea apps, used by the simulator and all targets.

microsoft/apm-action

A GitHub Action that wires APM agent packages into CI — This action installs Microsoft's APM (Agent Package Manager) CLI and deploys agent primitives like instructions, prompts, skills and agents directly in CI, with no config needed beyond a one-line step. It adds isolated mode for inline dependencies without an apm.yml, a setup-only mode mirroring actions/setup-node, and an update mode to refresh branch/tag-pinned dependencies against the lockfile.

GitHub Action for Agent Package Manager

wileai/pi-codex-connectors

Bridge Codex connectors and web search into any Pi model — A Pi extension that exposes your already-connected Codex (ChatGPT) apps and tools to other Pi models, using three generic tools instead of hundreds of schemas. It also adds direct web search via Codex's alpha search endpoint, without triggering a model turn. Useful for Pi users who want ChatGPT connector access outside Codex itself.

Use every connected Codex (ChatGPT) connector from any pi model

yash-gadodia/claude-mods

Claude Code mods that keep an agent honest — function hooks that guard scope, verify deploys, and draw the session above the prompt.

cm-yoshikikasama/blog_code

Blog-paired code samples with a heavily automated dev setup — A companion repo for blog posts, holding AWS CDK infrastructure code and serverless examples (Lambda, Glue, Step Functions). Notable for its tooling: pre-commit hooks covering multiple languages plus Claude Code hooks that auto-format and lint files on edit. Useful reference for readers wanting both the code and a multi-language lint/format setup.

blog backup md

rociiu/talorys

A personal AI agent you own, hosted on your own Cloudflare account — Talorys is a self-hosted AI assistant deployed with one npx command into your own Cloudflare account, no external server or vendor database involved. It handles chat, long-term memory with optional semantic recall, tasks, notes and scheduled automations, aimed at single users wanting a private, free-tier-friendly, telemetry-free assistant.

Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes and scheduled reminders, deployed with one command: npx create-talorys@latest. Free-tier friendly, single-user, no telemetry.

openobserve/openobserve

A single-binary Datadog alternative claiming 140x lower storage costs — OpenObserve bundles logs, metrics, traces, RUM, session replay, pipelines, SLOs, and LLM observability into one cloud-native platform written in Rust. It positions itself as a simpler, petabyte-scale substitute for Datadog, Splunk, and Elasticsearch, deployable as a single binary with much lower storage overhead.

Open source observability platform for logs, metrics, traces, RUM (web, android, ios), Session replay, pipelines, SLO and LLM observability. A sophisticated, simple and highly performant alternative to Datadog, Splunk, and Elasticsearch with 140x lower storage costs and single binary deployment.

microsoft/playwright

Playwright now spans test runner, CLI, and AI agent tooling — Playwright has expanded beyond its test runner and library into new entry points: a CLI for coding agents like Claude Code and Copilot, and an MCP server for LLM-driven browser automation. This makes it relevant not just for e2e testers but also developers building AI agents that need to control Chromium, Firefox, or WebKit.

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

Open-Dev-Society/OpenStock

A free, open-source alternative to paid stock tracking tools — OpenStock offers real-time price tracking, custom alerts, and company insights as a free alternative to costly market platforms. Built with Next.js, shadcn-ui, and Tailwind CSS, it's aimed at developers and investors who want an open, community-driven tool instead of paid subscriptions.

OpenStock is an open-source alternative to expensive market platforms. Track real-time prices, set personalized alerts, and explore detailed company insights — built openly, for everyone, forever free.

freeCodeCamp/freeCodeCamp

A nonprofit's full-stack curriculum keeps expanding its certifications — freeCodeCamp is a donor-funded nonprofit codebase powering a free, self-paced coding curriculum that has helped over 100,000 people land developer jobs. It now offers full-stack certifications covering Responsive Web Design, JavaScript, Python, databases, and APIs, with interactive lessons, labs, and project-based exams for each.

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

appwrite/appwrite

Appwrite now bills itself as an MCP and agent-first backend — Appwrite adds a hosted MCP server so coding agents like Cursor, Claude Code, and Codex can operate directly on a live project, alongside its existing Auth, Databases, Storage, Functions, Messaging, and Hosting modules. It's for developers and AI agents building apps that need self-hosted or managed backend infrastructure.

The open-source cloud for agents & devs. Including Auth, Databases, Storage, Functions, Messaging, Hosting, Realtime, WAF and more

composo-ai/DishwasherBench

Benchmarking LLMs by making them load a dishwasher — DishwasherBench turns dishwasher loading into an LLM benchmark, using rigid-body physics and simulated wash chemistry on an exact model of a Bosch SMV4HAX40G. Humans play the same game, called Spotless, in a browser, while models act through MCP, with every episode deterministic and replayable for verification.

A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The game inside is called Spotless.

vercel-labs/scriptc

Vercel Labs compiles TypeScript straight into native binaries — An experimental Vercel Labs project that compiles TypeScript/JavaScript to native executables and WebAssembly, using TS type-checking to generate machine code. Output runs without Node.js, imported npm packages compile along, and a coverage command reports unsupported code with rewrite hints.

TypeScript-to-Native Compiler

microsoft/AI-Engineering-Coach

A local dashboard that scores how well you work with AI coding tools — AI Engineer Coach parses local AI coding session logs from any harness into a single dashboard, with 45 rules to spot anti-patterns in prompting, session hygiene, and context use. It also surfaces reusable skills from repeated prompts and tracks code output by model and workspace—all without sending data off your machine.

better agentic engineering

KnockOutEZ/wigolo

Local-first web search and crawling for AI agents, zero API keys — wigolo gives coding agents search, fetch, crawl and research via MCP without cloud APIs or per-query costs. It plugs into Claude Code, Cursor, Codex, VS Code and more, positioning itself as a local alternative to Exa, Firecrawl and Tavily during its public beta.

The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.

BuilderIO/agent-native

A framework pairing autonomous agents with purpose-built UIs — Agent-Native is an open-source TypeScript framework from Builder.io for building agents that work alongside a dedicated UI. Developers define each capability once as an action, usable both as an agent tool and as a UI function, sharing validation and permissions. Useful for teams building knowledge-work agents that need inspectable, editable results, not just a chat box.

A framework for building agentic apps

dream-num/univer

An embeddable office SDK built as a runtime for AI agents — Univer is an open-source SDK for embedding spreadsheet, document, and presentation editing into your own product, running the same architecture in browser or Node.js. It now frames itself as an 'Office Harness' where humans and AI agents share files via a plugin architecture, Canvas rendering, formula engine, and unified Facade API.

The Office Harness for AI Agents — Spreadsheets, Docs, Slides, Canvas, Relational Tables, and PDF in one runtime.

swimmingbrain/brainotes

A browser-only notebook for handwriting over lecture PDFs — braiNOTES is a local-first, open source handwriting app like OneNote or GoodNotes, but running entirely in a browser tab with no account or server. It's built for students: slides can sit beside your notes or become the pages you write on, with snipping, pen pressure and PDF export, and it works offline once loaded.

Handwritten notes and a whiteboard in your browser. Write with a pen, keep the pdf next to your notes. No account, nothing leaves the browser.

directus/directus

Turn any SQL database into instant APIs and an admin app — Directus wraps existing SQL databases (PostgreSQL, MySQL, SQLite, MSSQL, MariaDB) with instant REST and GraphQL APIs plus a customizable Vue-based admin app. It suits teams who want a headless CMS or no-code backend without migrating data into a proprietary store.

The flexible backend for all your projects 🐰 Turn your DB into a headless CMS, admin panels, or apps with a custom UI, instant APIs, auth & more.

OpenBMB/PilotDeck

OpenBMB's WorkSpace-based platform for AI agents with memory — PilotDeck is a task-oriented productivity platform from OpenBMB organizing AI agent work into WorkSpaces, with native MCP support for tool integration. It focuses on operational boundaries and memory evolution, aimed at developers building persistent, context-aware agent workflows rather than one-off chat tasks.

Task-oriented AI Agent productivity platform

microsoft/vscode

The open-source core behind Microsoft's monthly-updated editor — This is the Code - OSS repository where Microsoft and the community develop the editor that ships as Visual Studio Code. It combines code editing, navigation, debugging and an extensibility model, with monthly feature releases and a daily Insiders build for those who want changes first.

Visual Studio Code