Onlook - Visual AI Editor for Designers
Open-source visual code editor that brings AI-assisted design directly into your Next.js codebase. Figma-like interface meets real-time code editing.
Tag
110 posts tagged #github-trending
Browse 110 posts tagged Github Trending, including practical setup notes, reviews, comparisons, and workflow patterns for engineers working with AI tools.
Open-source visual code editor that brings AI-assisted design directly into your Next.js codebase. Figma-like interface meets real-time code editing.
Elephant Agent is an MIT-licensed, macOS-first personal AI agent that grows a correctable Personal Model of identity, world, pulse, and journey, then helps shape long-running Paths.
LUKSbox is an Apache-2.0 Rust encrypted-container tool with passphrase, FIDO2, TPM 2.0, and ML-KEM hybrid post-quantum keyslots, mountable as a real drive on Linux, macOS, and Windows.
FanBox is an MIT-licensed macOS desktop cockpit for Claude Code and Codex with file browser, embedded terminal, live agent dashboard, project memory, and one-click session resume.
agent-skills-eval is an MIT-licensed test runner for the agentskills.io standard that runs every eval with_skill and without_skill, grades both with a judge model, and ships a static HTML report.
boo is a GNU screen-style terminal multiplexer written in Zig on top of libghostty-vt, with a faithful terminal state model and agent-friendly peek, send, wait, and JSON primitives.
PriceAI is an AGPL-3.0 comparison radar that aggregates 100+ Chinese card-shop channels for ChatGPT, Claude, Gemini, Grok, and AI API reseller pricing into comparable standard SKUs.
Parastore is a synthetic-consumer retail sandbox where you draw a store, generate LLM personas, and watch them shop an isometric 3D space with pathfinding and per-aisle analytics.
Agent-HTML gives agent outputs a durable React artifact workspace with inspectable blocks, themed presentation, and a Vite-powered Canvas host for dashboards, reports, and mockups.
MobileGym is a browser-hosted Android simulator with 28 apps, 416 task templates, deterministic code-level judges, 256 parallel instances, and Sim-to-Real validated GRPO training.
GOD is an Apache-2.0 real-time operator console for generative-agent societies, with pause-time, targeted ask, real-time intervention, no-code setup, and pixel-replay worlds.
sandboxd is an MIT-licensed self-hosted engine for isolated Linux sandboxes, built-in OpenCode and Claude Code agents, and live preview URLs from a single Go binary.
Whale is a DeepSeek-native terminal AI coding agent written in Go with ~98% prompt cache hit rate, 1M-token context, MCP, dynamic workflows, and Claude Code compatibility.
WeSight is an open-source Electron desktop console for Claude Code, Codex, Kimi Code, OpenClaw, Hermes Agent, OpenCode, and other local AI coding agent runtimes.
OpenOSINT is an MIT-licensed AI OSINT agent with 16 tools, an interactive REPL, a CLI, a Web UI, and an MCP server, supporting Anthropic Claude, OpenAI, and local Ollama models.
Burrow is a free, open-source, native macOS GUI for the Mole CLI, with long-range metric history, an MCP server for AI agents, and tools for clean, purge, and uninstall.
specification.website is an MIT-licensed, source-cited web spec covering HTML, SEO, accessibility, security, llms.txt and more, with an MCP server for AI agents.
Learn how journal-adapt-writing-skill turns a manuscript and a target journal's papers into an auditable dynamic writing skill for Claude Code and Codex revision work.
Awesome Architecture is a bilingual architecture knowledge base with 26 tutorials, 25 system maps, and 6 end-to-end cases for developers designing AI and distributed systems.
Ponytail is a portable AI coding skill pack that pushes Claude Code and Codex toward smaller diffs, fewer dependencies, and measurable cost savings. Drop-in setup guide.
Baguette turns iOS Simulator into scriptable infrastructure with headless boot, browser dashboards, gesture injection, and multi-device farm control for iOS 26 workflows.
TokenSpeed targets agentic LLM inference with static-compiler parallelism, KV-safe scheduling, and aggressive Blackwell-era performance goals in its preview release.
RMUX is a Rust terminal multiplexer with tmux-style control, browser sharing, typed SDK APIs, and security-minded web multiplexing for agent workflows.
Google's Antigravity SDK packages typed tools, streaming responses, MCP integration, hooks, and triggers into one Python agent runtime for production-grade workflows.
OpenSquilla combines routing, planning, memory, and optional MCP support into a token-efficient local-first agent workflow with practical CLI setup and tradeoffs.
Perplexity's Bumblebee scans lockfiles, package metadata, MCP configs, and extensions on macOS and Linux to quickly show where vulnerable software is present.
raiyanyahya/how-to-train-your-gpt teaches modern decoder-only LLM internals with a 12-chapter walkthrough, runnable notebooks, a commented `main.py`, and fine-tuning guides aimed at Python developers.
Denis Sergeevitch's agents-best-practices packages provider-neutral guidance for building AI agent harnesses with typed tools, approval gates, context compaction, MCP connectors, and rollout safety.
Evan Bacon's serve-sim turns booted iOS simulators into browser-accessible streams with gesture control, camera injection, middleware embedding, and an agent skill for Codex or Claude Code.
Alibaba's Open Code Review is an AI code review CLI with deterministic file coverage, line-accurate comments, CI examples, and agent integrations for Codex and Claude Code.
guard-skills adds second-pass checks for AI-generated code, tests, docs, and WordPress or WooCommerce changes before merge.
Paper Pilot is a local-first desktop research assistant that crawls academic sources, stores papers in SQLite, and adds grounded AI synthesis to your library.
patent is a Rust TUI and CLI that searches open-source projects before you build, using embeddings and semantic matching instead of plain keyword search.
sandboxd packages multi-tenant Docker sandboxes, preview URLs, idle stop and wake, and agent task APIs for teams building coding playgrounds.
Harbor SDK packages TypeScript and Python clients, generated protocol types, and a local Harbor-compatible server for teams building agent systems.
Petdex turns Codex pets into an installable ecosystem with a web gallery, npm CLI, desktop floater, and documented pet package format for builders.
Mainline records intent, constraints, risks, and validation before AI-generated diffs land. This guide covers install, workflow, Git integration, and where repo memory beats PR descriptions.
Facts turns project claims into checkable records for coding agents, with lifecycle tags and CLI verification. This guide covers install, workflow, commands, and where it fits in real teams.
Second Brain on Cloudflare gives Claude, ChatGPT, Cursor, and MCP clients shared memory you host yourself. This guide covers one-click deploy, client wiring, auth choices, and real tradeoffs.
Tessera organizes Claude Code, Codex, and OpenCode into one workspace with panes, tabs, worktrees, and Git status. This guide covers install paths, first run, architecture, and adoption tradeoffs.
Microsoft Intelligent Terminal brings ACP-compatible agents into Windows Terminal with agent panes, error-aware prompts, and hooks. This guide covers setup, limits, privacy, and adoption tradeoffs.
Recomby GEO packages GEO skills, schemas, and a 7-stage workflow for Claude Code and Codex, giving agents a local-first, human-in-the-loop operating model for AI search visibility work.
Paper Pilot is a local-first desktop research assistant that crawls 8+ academic sources, stores papers in SQLite with FTS5 and vector search, and grounds AI synthesis in your local corpus.
Microsoft Intelligent Terminal adds ACP-native agent panes, error-aware fixes, session tracking, and prompt delegation to a Windows Terminal fork for Copilot, Codex, Claude, and Gemini.
WeSight turns Claude Code, Codex, OpenClaw, and other local agent CLIs into one macOS desktop workspace with visual chat, live diffs, model routing, skills, and runtime metrics.
CC Desktop Switch is a Claude Desktop provider manager that routes through third-party models like DeepSeek, Kimi, Zhipu, Alibaba, and MiMo using a local gateway.
GPT Image Canvas is a free, local-first AI image editor built with tldraw + GPT Image 2. Text-to-image, reference editing, multi-step workflows — all on your machine, no cloud needed.
Local-mode multi-agent matrix framework that runs supervised Claude Code or Codex agents — coordinated through JSON-RPC, per-agent worktree isolation, and async message bus.
VibeSearchBench is an AI search benchmark with 200 vague, multi-turn, real-world tasks scored with triplet F1, built to measure agent search quality beyond toy evals.
Version control purpose-built for AI coding agents — blame which prompt wrote any line, inspect full change context, and track every agent turn as a content-addressed step.
Persistent memory layer for AI agents across sessions — 9-stage consolidation turns observations into facts, relationships, patterns, and wisdom over time.
AI outpainting with five integrated 2D game art studios — Poisson-blended seams, parallax backgrounds, autotile sets, character sprites, and decoration props.
AWS skills and MCP server for Claude Code, Codex, and Kiro — covers 300+ AWS services through CDK, CloudFormation, serverless, containers, and Bedrock agents.
High-throughput GPU storage engine built on Rust and io_uring — GPUDirect Storage, RDMA, erasure coding, 6x higher throughput than conventional object stores.
Self-improving context layer for data agents — ingests databases, BI tools, and wiki content; builds semantic layer with automatic fan/chasm trap resolution.
Ingest documents into persistent navigable memory — tree-like hierarchy reconstruction, multi-modal parsing, and agentic RAG with evidence-based citations.
AnySearch MCP Server gives AI agents real-time web, finance, and academic search through MCP tools, with batch queries, URL extraction, setup steps, and practical use cases.
Animated desktop pets that react to Claude Code, OpenCode, and MCP agents — privacy-safe reactions and speech without exposing code or secrets.
Butterbase is an open-source backend-as-a-service with Postgres, auth, storage, serverless functions, AI gateway features, and a built-in MCP server you can self-host with Docker.
Arkon compiles company docs into an AI knowledge wiki and serves it to Claude via MCP with role-based access control. Self-hosted with Docker with.
An AI data analysis agent for business users. Upload CSV, connect SQL databases, and describe what you want to find. Charts, stats, and reports generated.
DeepMLab wraps Scilab with an LLM-driven natural language interface. Describe your math problem in plain English and get Scilab code, plots, and results — an.
A prompt catalog, Agent Skill, and Python CLI for OpenAI GPT Image 2. 80+ templates for text-to-image, editing, research figures, and brand outputs.
An AI-powered GitHub maintenance bot that reviews issues and PRs on schedule, writes conservative reports, syncs review comments, and auto-closes items with.
OpenLess is an open-source voice input tool for macOS and Windows. Hold a hotkey, speak, and AI-polished text streams to your cursor.
Butterbase OSS is an open-source backend-as-a-service with a built-in AI gateway. Postgres, auth, storage, edge functions — self-hostable with Docker Compose.
World2Agent standardizes how AI agents perceive the real world — screenshots, device state, sensor data — into a typed protocol. TypeScript SDK with React.
The official Python SDK for Google Antigravity. Build AI agents with Gemini, MCP tools, custom skills, and managed infrastructure. Async-first API with typed.
Harmonist orchestrates up to 186 AI agents with mechanical protocol enforcement and dependency management. Define agent workflows in YAML — portable across.
Future AGI is a self-hostable platform for evaluating, observing, and improving LLM apps. Includes tracing, evals, simulation, datasets, an AI gateway, and.
Serve Sim is npx for Apple iOS simulators. Spawns simulators on demand with a single command, exposes them via HTTP for screenshots and interaction, and runs.
DeepSeek-Reasonix is a TypeScript agent framework built for DeepSeek models with structured reasoning, tool calling, and multi-step planning.
A public knowledge base of 150+ agent design patterns from dozens of production deployments. Covers planning loops, tool design, prompt engineering.
Terax AI is a 7MB terminal-first AI dev workspace built with Tauri and Rust. Bundles AI agents, code editing, and terminal into one cross-platform desktop app.
Mercury Agent runs 24/7 from CLI or Telegram with a personality system, token budgets, and permission-hardened tools. Built with TypeScript and Docker with BYO.
Garden Skills bundles four Agent Skills for Claude Code, Cursor, and Codex: web design, video presentations, GPT Image 2 prompting, and local knowledge.
Open-source Flutter app for systematic English listening practice. Blind listening → intensive → shadowing → retelling → spaced review.
An MCP server for secure credential and secret management in AI agent workflows. Store API keys, tokens, and secrets with access control — let agents use.
An AI agent skill for adapting research papers to target journal formats. Handles style, references, and discipline conventions. Built for Claude, focused on.
Turn job descriptions into projects, projects into resumes, and resumes into interviews. AI-driven internship prep tool for CS students — from JD analysis to.
Generate complex, high-density PowerPoint presentations with AI. 17 built-in templates, auto-updating skill system, and compatibility with DeepSeek, Claude.
An executable context layer for data and analytics AI agents. Let Claude Code, Codex, and any agent query data accurately through MCP with skills, memory, and.
Store files securely in cloud storage without trusting the host. Rust encrypted containers with passphrase, FIDO2 (YubiKey), TPM 2.0, and post-quantum ML-KEM.
A tree-of-thought brainstorming skill for coding agents. Fans divergent ideas across cognitive frames, scores, prunes dead ends, deepens survivors.
Spec-driven coding harness with self-improving context memory. 12 specialized agents, 32 skills — kills context rot and ships features instead of spaghetti.
CLI, SDK, and IDE plugins for adversarial AI agent workflows. Pit two AI agents against each other — one builds, one critiques — for higher-quality code.
One-command setup for AI coding workflows. Installs OpenSpec and Superpowers across 28 AI coding platforms — dual-star workflow for specs, plans, and.
A feature-rich terminal UI client for Discord written in Rust. Keyboard-driven navigation, markdown rendering, and low resource usage for developers who live.
A test runner for agentskills.io-style AI agent skills. Validate skill behavior with YAML test specs, JSONL output, and OpenAI-compatible evaluation — ship.
A personal-model-first AI agent that evolves its own behavior over time. Self-evolving memory, context-aware responses, and persistent learning — your AI that.
Battle-tested at Alibaba scale. Hybrid code review combining deterministic pipelines with LLM agents for precise line-level comments — catches NPE.
Speed up scientific workflows with DeepMind's Science Skills. Integrates AlphaGenome, AFDB, UniProt, and 30+ databases for grounded, token-efficient AI-powered.
Run a 13k-line Rust coding agent at 16MB RAM. Multi-provider, session management, permission system, MCP support, and integrated search — the leanest AI coding.
Use Yao Open Prompts as a prompt catalog for AI work, learning, content, marketing, GEO, and prompt reuse with evidence and versioning checks.
Set up Raindrop Workshop for local agent traces, tool-call debugging, replay workflows, SQLite storage, instrumentation, and eval repair loops.
Deploy TrustClaw with Vercel, Composio, Neon, Upstash, and AI Gateway while planning env vars, cron limits, public signup, and cost controls.
Evaluate TokenSpeed as a preview LLM inference engine for B200 benchmark reproduction, model recipes, server docs, and production-readiness checks.
Set up RMUX for detachable agent terminals, tmux-like sessions, Rust SDK control, diagnostics, migration checks, and terminal automation.
Use rkn-block-checker for RKN blocking diagnostics with network context, resolver comparisons, reproducible logs, and careful reporting limits.
Evaluate Photo-agents for image-agent workflows, including license keys, Python isolation, sample-image testing, metadata checks, and batch safety.
Set up OpenSquilla with uv, onboarding, OpenRouter env keys, gateway runtime, Git LFS model files, and migration paths from other agents.
Complete setup guide for OpenMonoAgent.ai — local .NET 10 coding agent with Dockerized llama.cpp, MCP support, sub-agents, and hardware-aware model sizing. No cloud needed.
Evaluate humanize-text for AI-text rewriting workflows, with setup notes, privacy checks, meaning preservation, detector caveats, and review steps.
Use how-to-train-your-gpt to learn tokenization, notebooks, CPU-friendly training loops, main.py experiments, and practical GPT study habits.
Set up Dulus as a terminal AI agent with native and Docker paths, installer profiles, WebChat ports, repo safety checks, and shell-access risks.
Evaluate CodexPlusPlus for Codex launcher enhancements, API relay mode, provider sync, local state handling, update flow, and rollback planning.
Review Bumblebee for Go package inventory workflows, including setup, dependency validation, CI adoption, supply-chain use, and report checks.
Set up Baguette for iOS Simulator automation, web dashboards, device farms, gesture input, streaming, and camera testing with Xcode caveats.
Explore awesome-agentic-ai-zh as a Chinese agentic AI learning roadmap, with setup notes, track selection, study workflow, and evaluation guidance.
Evaluate Automotive Skills Suite for APQP, ASPICE, HARA, safety-plan, and DIA workflows with setup notes, governance risks, and SME review guidance.