Trending Repos

Omnigent is a unified platform for managing various AI agents, allowing you to switch or combine them without rewriting code.

Why: It enables efficient collaboration and control over different AI systems, enhancing productivity and security.

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

面向 GPT-image-2 的 AI 图片生成 WebUI 工作台，支持 Codex Responses 与 OpenAI 兼容 API 接入，内置公用图库、多类型 Chip 快捷引用、提示词模板、多任务并发和本地队列管理。An AI image generation WebUI workbench for GPT-image-2 with Codex Responses and OpenAI-compatible API support, shared gallery references, multi-type quick chips, prompt templates, concurrent tasks, and local queue management.

A tool to help AI job seekers convert job descriptions into projects, projects into resumes, and resumes into interviews.

Why: It streamlines the process of preparing for AI internships by providing a structured approach to showcasing relevant skills and experiences.

Harness Anything - AI agent control hub: WPS, MS Office, Zotero, Photoshop, 47 CLI commands, 27 academic skills, SVG-to-PPTX

AI agent skills created by me: Dan McAteer

An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.

ICT/SMC trading-knowledge skill for AI coding agents (Claude Code / Codex / OpenClaw / Hermes)

Govern, Observe, Direct - a real-time control room for agent societies

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

Repo dependency analyzer with **blast-radius impact scoring** for AI-assisted development.

Clean-room, model-agnostic harness for Claude Code-class coding agents

A free detector capable of identifying content generated by all advanced AI models.

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.

🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.

BrandDocs is a set of agent skills that learn your existing Word, PowerPoint and Excel templates and generate new on-brand documents from them. Unlike generic AI document generators, it preserves brand, structure, styles and formulas by construction. Built for Claude Code, Codex and compatible AI agents.

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

An AI agent for coding and others

A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.

An open-source agent harness that turns your AI agent into your personal DNA expert

The open-source Trend-to-Video Agent Framework for content creators

Self-evolving memory palace for AI agents — persistent memory with automatic learning, knowledge graph, and multi-agent support

Damru is the ultimate stealth Android browser automation framework. Unlike tools that use detectable JS injections, Damru achieves true undetectability via native C++ overrides, OS-level root prop spoofing, and GPU binary patching. Designed to bypass ALL CDNs, and score 100% on CreepJS using Redroid and Playwright.

An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.

CLI harness for WPS Office -- let AI agents control Writer, Calc & Impress via COM automation

An easy-to-use desktop utility powered by AI to automatically remove background from photos locally, offline, and in high resolution.

The AI agent memory cloud you’ll wish existed yesterday. Manage agent memory like a GitHub repo: switch devices, switch agents, switch sessions, and your AI still remembers who you are, what it has learned, the rules you taught it, where the project left off, and what to do next.

Production LLM call layer for AI agents and tools: keep OpenAI/Anthropic/AI SDK/LiteLLM, hot-swap models with MDA presets, and add cache, retries, circuit breakers, key rotation, singleflight, and Python/TypeScript/Rust parity.

AI-driven Azure operations workbench. Chat with your tenant, investigate incidents with a team of specialist AI agents, and assess, monitor & remediate your cloud — runs in your own subscription. One-click deploy.

AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation with NVIDIA LocateAnything-3B, manual refinement, one-click YOLO training, video keyframe extraction, and model validation. Supports image and video.

Fully stealth chromium for AI agents.

An AI-assisted newsroom workflow system for event tracking, evidence organization, approval chains, correction handling, and post-publication monitoring.

GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.

Build academic conference posters as a single HTML/CSS file, rendered to print-ready PDF via headless Chromium. A coding-agent skill.

Open skill for capturing AI agent work as structured traces.

AI identity layer for Claude Code, Codex and Cursor — stores who you are, not just what you did. Local-first, MCP-compatible.

A unified anti-dead-loop toolkit for LLM agents — loop detection, budget ceiling, state stasis guard, and circuit breaker in one library.

OpenLoop is a universal loop engineering framework for AI agents, enabling play-test-fix-verify-improve cycles with logs, heartbeats, baselines, guardrails, and auditable stop conditions.

桌面 AI 副屏 Skill：M5Paper 墨水屏 + AI Agent 推送 widget。装 Skill 后由 Agent 自动引导烧固件、配 Wi-Fi、推送内容。本地运行、无云依赖。

Crash-test insurance claim AI agents before production.

AI Agent的Skills 合集

工程化 RAG 文档助手：知识库、PDF 索引、Agent 工具编排、scope 检索、引用溯源与拒答阈值。FastAPI + Vue3

Awesome list of Indonesian open source projects listing on https://indopensource.org/projects and https://tokengratis.id/opensource

The open-source Stainless — point your existing stainless.yml at it and get the same idiomatic Python SDK. Zero migration. No SaaS.

A real traffic light for AI agents.

Code knowledge platform that analyzes repositories into AST graphs, builds GraphRAG indexes, and generates source-grounded developer wikis with FastAPI, React, and LiteLLM.

Black-box, open-source red-team testing for AI agents. Point Argus at any HTTP, gRPC, or browser-using agent endpoint, run 500+ adversarial probes (OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, TAP/PAIR/GCG), get LLM-judged findings as SARIF, gate CI via GitHub Code Scanning. Ships with CLI + GH Action.

Reusable GitHub Action that reviews Terraform PRs for security, cost, and style using a LangGraph multi-agent system, posting a single severity-ranked comment.

Bypass all api restraints within Kimi-CLI

Validate, repair, and retry LLM structured outputs. 13 repair strategies for common JSON malformations, JSON Schema validation, and retry-with-feedback prompts.

Apple Watch notifications for Claude Code and AI agent workflows.

Spec-first, evidence-gated engineering-procedure enforcement for AI coding agents (Claude Code + Codex). The agent can't edit until it writes a passing spec.

Powerful Google Maps Crawler / Scraper tool with REST API, Docker support & multi-format export

Desktop AI agent with conversational chat, visual workflows, 100+ tools, skills, MCP, and multi-model support.

Engineering workflows for AI coding agents or flesh engineers. It helps absorb silent base-model quality drift.

Give Your AI Agents Access to Quantum Compute

从零精通 AI 工程 · 20 阶段 503 课 · 中文全量翻译 + 配套站点 aieng-zh.cn · 如何成为 AI Agent 工程师的修成指南

Find and redact secrets in AI coding agent histories (Claude Code, and more).

An MCP to expose process monitoring and ETW tracing functionally to AI agents to assist in security work

Multi-model AI workflow engine with built-in quality arbitration. Plan → Approve → Execute → Audit pipeline. Dual-brain design: Brain #1 (planner) + Brain #2 (arbiter, different model) stops hallucination leaks cold. Zero-config token saving.

Prompt-first starter kit for making repositories safer for AI coding agents.

Demonstrate once, execute anywhere — secure remote skills for AI agents.

Semia, security audit for AI agent skills.

Multi Agent for Business Automation is a multi-agent orchestration platform for business automation and decision support. It coordinates specialized AI agents—each with distinct roles, personalities, and tools—through LangGraph workflows, shared memory, and human-in-the-loop (HITL) approval gates.

Delegate tasks to DeepSeek right inside your Claude Code / Codex sessions.

🤖 Cortex AI: #1 智能量化交易系统 — 全自动加密货币套利引擎 v3.4。支持 Solana、TON、Binance (币安) 和 Bybit。2026年最佳高频量化交易机器人。

Token-budget-aware graph navigation for AI coding agents. Serve exactly the noodles your LLM needs. 🍜

Self-evolving AI agent that rewrites its own source code in real-time. 6 mutation strategies. 7 autonomous drives. GitHub absorption engine. Built by KORRO.

Authoritative, source-cited Claude Code plugin/skill that lets a coding agent autonomously build production-grade AI agents on AWS (Strands Agents, Amazon Bedrock, Bedrock AgentCore) with official best practices.

A CLI for DaVinci Resolve 18+ — project / media / render / timeline control for humans and AI agents.

Cross-architecture LLM internal observation database (23 models, 13 architecture families). Exposed as MCP tools for any AI coding agent.

全球宏观预期概率面板 (AI Skill) — Polymarket+Kalshi 双源 · 5端点 · 10模块 · 零鉴权 | Global-macro-probability panel skill for AI coding assistants (prediction-market data pipeline)

A library-science-inspired personal knowledge management system with LLM agents

AI Deep SAST - LLM-powered deep static analysis for CI/CD. Combines Semgrep, tree-sitter code indexing and frontier LLMs (e.g. GPT-4o, Claude) for fast and deep vulnerability scanning.

Eve Agent V2 Unleashed — local-first autonomous AI coding agent powered by Ollama

Simple Python linter

A curated skillstack for AI agents. Make your AI code editor write code like a Tech Lead. Stop copy-pasting instructions. Install 794 expert rules, workflows, and custom personas in Cursor, Claude Code, and Windsurf with one CLI command.

AI-powered personalized IELTS corpus distillation — install-only skill (zero-backend Agent loop) + runnable backend with QMD-RAG. 7-stage pipeline producing schema-validated corpus.json & static profile site.

AI-powered multilingual FIR drafting assistant using Flask, NLP, and Machine Learning.

Turn your SLOs into pytest assertions.

Universal AI behavior rule framework — pin your 5-10 rules so AI doesn't drift in long tasks. Dev-scenario preset built in; switch to any scenario in one line. Claude / Codex / Cursor / Hermes. Zero LLM, zero network, zero deps.

Static analysis engine for Python web-applications

A desktop ambient lighting companion for AI coding assistants. It listens to hook events, maps assistant status to Yeelight light effects, and intelligently aggregates multiple running tasks to avoid flickering or unstable state changes.

Context-aware project memory for AI coding tools. Zero LLM calls. Runs locally.

WebStrike — automated web-pentesting framework that orchestrates Kali tools (subfinder, httpx, katana, ffuf, nuclei, sqlmap, dalfox) into one phased recon→exploit→report pipeline.

A coding agent skill that helps measure and close the understanding gap in any codebase, research corpus, or documentation set.

SEPCC — A Claude Code proxy with context that survives. Route Claude Code through 17+ providers, resume sessions across restarts, and never lose your place. Fork of Free Claude Code.

Agent platform you build, run, and improve using coding agents.

إطار مفتوح المصدر لتكييف مساعدات الذكاء الاصطناعي وسير العمل القانوني مع البيئة القانونية السعودية. Open-source framework for adapting AI assistants and legal workflows to the Saudi Arabian legal environment.

A customizable Claude Code setup for knowledge workers: agents, safety hooks, skills, memory, and an Obsidian knowledge base. Clone, run setup, make it yours.

CLI debugger that lets coding agents inspect live Python runtime state, with optional MCP integration.

花 4 個月慢慢一步一步調整到可以自動化去防 AI Slop 的機制，包括：CLAUDE.md 跟 Hook 之間的設定跟腳本，目的就是幫助整個系統在運作的時候減少 AI Slop。

A durable blackboard runtime for verifiable Claude Code agent loops.

🤖 Autonomous Multi-Agent AI Workspace in your terminal. Codes, researches, and executes real tasks with 40+ tools and 280+ skills And Some Captcha Resolver With Only Vision Mode Any Captcha And Opening A Browser And Full Control Of It

Goal-Driven agent for long-running tasks, docker-isolated workers, intelligent task decomposition, and autonomous execution

Papers in, ideas out. Generate research, product, or feature ideas from 250M+ academic papers.

ZavaShop supply-chain workshop: 5 LABs on Microsoft Agent Framework + Microsoft Foundry, with shared data fixtures, AG-UI control tower, and a GitHub Copilot coding agent.

IBL AI Agent helps you use a coding agent such as OpenAI Codex to analyze International Brain Laboratory (IBL) data.

Workspace-isolated context engine for AI coding agents. Claude Code stable; CLI and runtime exports planned.

Wiki-based retrieval for AI coding agents. 65× token reduction, +24pp Coverage@5 on SWE-bench Verified.

Reverse-engineered Doubao (豆包) API → OpenAI-compatible REST service. Free multimodal chat, image/video/music generation, and file hosting for AI agents.

From idea to playable game — 6 AI agents collaborate to design, code, review, test, and generate art

Claude Code workflow for mapping projects into clean-room behavior docs, file maps, batch reports, verification, and rebuild-ready blueprints.

A senior-engineer protocol for polyglot code generation, architecture, testing, security, performance, and agent validation.

GAN-style self-improvement loop for any text artifact: mutate, grade with a SEPARATE model, keep only verified wins (pairwise-judged), revert the rest. The git history is the improvement log.

一个让新版codex用国产模型的工具，目前适配国内主流模型，编程没有问题，codex cil,codex桌面，vs插件都可以

Drive the Django admin from your terminal — browse, search, filter, edit, and run admin actions, with the same permissions and audit as the web admin. Built on Textual.

Static analysis toolkit for Python — detects performance issues, anti-patterns, and code smells using AST

Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemini and Windsurf.

Debug and troubleshoot ComfyUI workflows faster. Offline static analysis tool & JSON fixer to repair broken links, type mismatches, and node errors.

Two skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique), plus a fixture-based eval suite.

114 source-backed /goal contracts for coding agents, plus 200 separated seed patterns.

Self-hosted NL-to-SQL analytics — query your database with plain English

A beautiful, web-based adb logcat viewer; Android Studio's Logcat without the IDE.

Instantly understand any codebase. One command, zero API keys, works fully offline. Auto-detects 20+ project types, maps architecture, and exports rich Terminal, Markdown & HTML reports.

A benchmarking suite for Agent Skills (SKILL.md files) that measures whether a skill actually improves LLM output quality, and by how much.

Diagnosis-first Agent Skills that turn AI from answer machine into learning tutor.

AFSIM-SKILL 是一款专为 AFSIM（Advanced Framework for Modeling, Simulation, and Command & Control）仿真引擎设计的 AI 编程助手，让你在 Cursor / Trae / VSCode 中通过自然语言快速生成、调试和优化 AFSIM 场景代码。 AFSIM-SKILL is an AI coding assistant for AFSIM (Advanced Framework for Modeling, Simulation, and Command & Control). Generate, debug, and optimize AFSIM scenario files directly in IDE

Domain-specializált, RAG-alapú multi-ágens pre-audit rendszer transzferár-dokumentációk (TP) elemzésére. 🏆 7. helyezés a PwC Hungary AI Hackathon 2026-on.

Your AI coding recovery score, from the terminal. Parses Claude Code JSONL sessions → cost, tokens, DRS estimate, per-project breakdown. Zero deps, Python 3.9+.

Este projeto permite inspecionar e listar informações do ambiente Docker de forma simples através de endpoints HTTP, incluindo containers em execução, imagens, redes e volumes.

Senior Architect Agent: AI architecture skill for existing system mapping, software architecture documentation, Mermaid diagrams, and AI agent handoff.

USB-portable offline AI assistant. AES-256 encrypted history, Turkish-tuned LLM (Trendyol), RAG over PDF/DOCX. KVKK uyumlu, %100 offline.

Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

Local-first dashboard for Claude Code token usage. Parses ~/.claude/projects/*.jsonl and serves an interactive viewer on localhost. No API calls.

Agent Skill for generating deployable system prompts for AI agents

An autonomous AI coding agent with novel innovations in tool state management and code editing, running in a Docker sandbox with a persistent shell, parallel tools, and a VNC desktop.

Save your tokens!

Extract WeChat (WCDB/SQLCipher4) database encryption keys on Linux. Auto-adapts to new versions via ELF static analysis — no manual reverse engineering needed per update. Linux 微信数据库密钥提取工具。通过 ELF静态分析自动适配新版本，无需每次更新手动逆向。

Learn backend engineering through real production failure cases.

Deterministic linter for scientific docs

Stream Coding v2.1.0 — Documentation-first development methodology. 59 skills, 5-gate enforcement, multi-agent support (Antigravity, Claude Code, Gemini CLI). When docs are clear enough, code generation becomes automatic.

Offline audiobook reader for EPUB, PDF, and TXT with local OmniVoice TTS, character voices, and synced highlighting.

基于递归对话与动态工具编排的 AI 智能体系统。包含代码编辑器、浏览器、语音、视频等工具模块，以及完整的 WebUI 和任务编排引擎。An AI agent system based on recursive dialogue and dynamic tool orchestration, featuring code editor, browser, speech, and video modules, along with a complete WebUI and task orchestration engine.

An agnostic AI-driven exploratory test framework that intelligently explores, tests, and validates any application

Noesis — Core Agent Framework for building autonomous AI workflows

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewer, get scored and coached on your weak areas. LiveKit · LangGraph · Next.js · Cloud: deepinterview.today

OpenAI-compatible LLM gateway: routes to the cheapest model meeting latency/quality targets, with SSE streaming, semantic caching, per-key rate limiting, and cost tracking.

Honeypot for LLM attacks — detects and traps Prompt Injection & Jailbreak attempts. Built with FastAPI + DistilBERT classifier. Part of proactive AI security research.

Local AI video translation, dubbing, subtitles, and blur editing with faster-whisper, Argos Translate, Supertonic, FFmpeg, and yt-dlp

Deterministic 5-Phase Autonomous AI Engineer with Semantic Code Graph Analysis & Static Data-Flow Tracking.

Dual-engine (llama.cpp + vLLM) LLM benchmarking pipeline for GGUF & safetensors on NVIDIA GPUs — speed, quality, live dashboard, publishable cards.

🐱 MiNerva·咪涅瓦 — 替你干活的赛博猫｜An autonomous AI agent that actually does the work.

Open-source, AI-driven penetration testing framework. Multi-agent loop (recon → analyst → pentester → coder) on LangGraph, with tool execution in an isolated Kali container. Hosted version at fenneclabs.ai.

Make any web app voice-controllable in 37 languages. Drop-in widget + open-source agent server — visitors speak, the agent talks back and drives their browser in real time.

A collection of AGENTS.md configurations, skills, and prompts tailored for Data Scientists to maximize productivity with AI coding assistants.

Autonomous multi-agent AI pipeline that reviews GitHub pull requests, generates fixes, runs test validation, and produces documentation.

Generate better AI code with task-aware policies

OpenAI-compatible HTTP serving for diffusion language models. Continuous batching + LocalLeap acceleration.

An index of the pages published at fivethirtyeight.com

Offline local-first personal knowledge base with document upload, vector search, and Ollama-powered RAG chat.

Production-grade LLM Evaluation & Benchmarking Framework — GPT-4, Claude, Gemini, Mistral. Accuracy, latency, cost, hallucination, reasoning metrics.

High-performance, real-time code-debugging and version-control insights empower distributed teams with adaptive DevTools suite.

Open-source observability and trust layer for AI agents: trace every step, score every output, catch hallucinations and runaway loops in real time. Self-hostable.

Open-source real-time restaurant bill splitting app with OCR

Installable Codex/AgentSkills workflow pack for dev, Agent/RAG, API/data, Office artifacts, research diagrams, and authorized security review.

Repo-native project memory for AI-assisted development: workorders, playbooks, examples, checks, handoff rules, and release-readiness discipline.

From-first-principles research toward a standalone agent skill suite for code review & maintenance — a comprehensive map of what factors into code quality.

A from-scratch Mixture-of-Experts (MoE) agentic AI coding assistant designed to run on consumer hardware. Built with a custom 7.5B parameter transformer (2.5B active per token), ReAct reasoning, self-learning capabilities, and a full-stack web dashboard

A local-first, lightweight Markdown workflow tool for AI-assisted development. Turn plain `.md` files into interactive pages with checkboxes, progress bars, Mermaid diagrams, editable text blocks, buttons, and write-back updates.

PoC for CVE-2024-37032 (Probllama): Ollama <=0.1.33 path traversal/arbitrary file write via model digest handling, using a FastAPI rogue registry, connector workflow, and shared object preload demo for authorized lab testing.

Urdu Programming Language is a high-performance, natively localized programming language for the Urdu-speaking world. A comprehensive full-stack ecosystem featuring advanced AI/ML layers, secure cryptography engines, asynchronous web servers, and enterprise database drivers.

Telegrab is a cross-platform desktop app that turns your Telegram account into unlimited, private cloud storage.

Sistema web de gerenciamento de filamentos de impressão 3D

Open-source browser automation broker for AI agents: persistent Chrome profiles, proxy-aware identities, remote API, MCP tools, browser-use/OpenBrowser adapters, human auth handoff, telemetry, and audits.

The largest universal agent skill library - 500+ production-ready skills across 14 categories. Supports 13 platforms including Claude, Cursor, Gemini, Doubao, Qwen, and more.

Real-world AI workflows for creators.

Reanime.to full rest api

Strongly typed Python-first library and CLI for multi-provider, multi-agent coding LLMs with Erlang roots and aspirations.

🦞 AI 量化交易系统 — 37 因子选股 · 8 层风控 · 同花顺数据大屏 · 全自动盯盘

Plugin para Claude Code com 40 skills de outbound B2B + briefing canônico que persiste entre sessões. Tunado para lemlist, agnóstico em fundo.

AgentWatch — Real-time reasoning auditor and observability platform for AI agents. Catches silent failures in your agent's reasoning chain before they execute — not after they break production.

🎙️ OmniVoice Thai API — Zero-shot Thai TTS with Web UI + REST API (Voice Cloning, Voice Design, Auto Voice)

Autonomous AI decision engine for OpenClaw — give your AI a brain that decides for itself

CLI coding agent สไตล์ Claude Code — Claude API / Cloud / Ollama / llama.cpp, 42 skills, single-file

A lightweight LLM evaluation layer that turns subjective model outputs into deterministic decisions by scoring attribution, specificity, relevance, and context quality—designed to detect hallucinations and enable production-grade LLM reliability.

A Django Hello, World example

基于 ripgrep + LLM 的轻量个人/部门知识库；Lightweight local knowledge base using ripgrep + LLM (agent loop, multi-modal, no vectors, no external API)

Language Server for Python behave BDD feature files

ローカル完結の議事録・要約作成アプリ（Local-first meeting minutes app）

Lighthouse is designed to handle log data from multiple sources without blocking the main application flow. By utilizing a message queue (Redis), it ensures that log ingestion is decoupled from log processing, providing high availability and fault tolerance. This project serves as a practical implementation of backend engineering patterns, focusing

Multi-tenant SQLite databases for Django.

Self-hosted media resource management service for BT users.

Measure AI co-programming effectiveness on any git repo. Detects Claude/Copilot/Cursor/Codex signatures and triangulates productivity multipliers via top-down roles, bottom-up formula, and an optional Claude Code subagent that reads diffs.

Lightweight multi-tenant Agent router.

Web Design Enhancer - Premium UI/UX enhancement skill for AI agents

Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 22+ MCP tools.

Local CLI-first AI code review for git diffs with analyzer-backed context.

Run pytest as an Airflow task. Pluggable runner/parser, structured XCom results, Airflow 2.x/3.x support. SOLID, typed, tested.

AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.

🔎 深度研搜对话式多智能体 AI Agents，最适合系统学习 DeepAgents 的实战项目｜AI Deep Research Agent 实战 · LangGraph + RAGFlow + Tavily + FastAPI + WebSocket 从0到工程化落地。前后端完整代码全栈可跑，Docker 环境一键部署，配套 ai-agents-from-zero 免费教程与章节代码分支。适合系统学习大模型应用、多智能体 Agent 和企业级 AI 工程落地

Autonomous AI Agent optimized for low-end PCs. A powerful, lightweight alternative to OpenClaw and Hermes with 100+ skills for DevOps, 3D rendering, and OSINT

Code3DBench: Single-Image to Executable Low-Poly 3D Code Generation

Your real-life F.R.I.D.A.Y. — a voice-controlled, self-improving AI OS that perceives your screen, remembers everything, writes production code, and gets smarter every week. One founder = one team.

Python toolkit for KiCad project automation, electronics design workflows, library checks, release packaging, and hardware documentation support.