Code agents

【AIGC 实战入门笔记 —— AIGC 摩天大楼】分享 大语言模型（LLMs），大模型高效微调（SFT）,检索增强生成（RAG），智能体（Agent），PPT自动生成, 角色扮演，文生图（Stable Diffusion） ，图像文字识别（OCR），语音识别（ASR），语音合成（TTS），人像分割（SA），多模态（VLM），Ai 换脸(Face Swapping), 文生视频(VD)，图生视频（SVD），Ai 动作迁移，Ai 虚拟试衣，数字人，全模态理解（Omni），Ai音乐生成 干货学习 等 实战与经验。

Task Planning and Tracking toolset for Pydantic AI agents, enabling hierarchical task management with subtasks, PostgreSQL storage for multi-tenancy, and an event system for webhooks and callbacks.

Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.

AGENT-FORGE is a Context Engineering Toolkit that generates GitHub Copilot customization files for your VS Code project. Instead of manually authoring .github/ configuration, you describe what you need and a multi-agent AI pipeline plans, generates, validates, and installs everything.

一条命令，把微信变成任何 AI Agent 的入口 | Connect WeChat to any AI Agent with one command

Agent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift. Works with Claude Code, Codex, and any agent that supports Agent Skills.

Write one app, render it to a terminal, a browser, or as agent tools. The terminal for your Gundam.

Zotero AI plugin Research assistant for Zotero 9. Chat with your library, run federated scholarly search, RAG, OCR, systematic reviews, and manage cloud storage. Includes standalone MCP, Agentic capabilities, and skills library.

Open-source local-first cognitive memory. AGM-compliant belief revision (49/49 postulates). When a fact changes, downstream beliefs are automatically re-evaluated, not just flagged.

Interactive testing CLI for Tauri v2 apps : lets AI agents inspect, interact with, and debug Tauri applications in real-time

Mnemosyne is a agentic memory and orchestration system designed to provide Claude Code with persistent semantic memory across sessions.

Continuous memory + self-improvement for AI agents. Learns how you work, recalls it automatically, no commands. Claude Code & Codex.

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

claude code for video editing

AI Agent 面试知识库：覆盖 LLM、Prompt、RAG、MCP、Tool Use、Agent 架构、Multi-Agent、LangGraph、Claude Code、Codex CLI、工程化评估、安全与源码解析。

Agent Research Copilot (ARC) is a set of skills and tools (MCP) for theoretical physics literature review, idea generation and performing calculations.

transformers safetensors Emu3 text-generation custom_code arxiv:2409.18869

transformers safetensors qwen2 text-generation conversational en

transformers safetensors qwen2 text-generation code codeqwen

Run AI coding agents in parallel on one git repo and safely auto-merge their work — only changes that build and pass tests land. On top of plain git; bring your own model.

Fast, interruptible verification browser for AI coding agents: 35 ms checks, pixel diffs, live human hand-off

CLI & MCP for GitHits - The Code Context Layer for AI Coding Agents

Xplor (Formerly know as Xplorer) an AI-native Chromium fork with Grok built in at the source level: Grok as the default search, the "Grok it" page button, a unified Grok toolbar (X Chat · Grok Build · Grok Web · Groki), Grok Build apps, and an always-on local agent gateway (CDP + high-level API) for any agent to drive.

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE, native video/document understanding, long-horizon tool agents, quantization-aware training. Scales: Tiny (25M) to Large (1.3B).

Skills for shipping better software.

Open-source AI agent for workers in mainland China to organize employment facts and evidence, estimate compensation, and prepare negotiation and arbitration drafts.

Node.js client for the chatgpt API. No third party dependencies.

A golang lib to help you to get openai access token and refresh the token(一个golang sdk，帮助你更容易的获取openai chatgpt的accessToken :)

This user-friendly tool creates custom AI roadmaps based on your goals ( old ai-roadmap.com )

Nature of Code - Autonomous Agents examples in 3D

`fdgt` is a mock API for the Twitch. Via `fdgt`, you can simulate events without having to spend a penny!

A simple example that demonstrates how to use the function call feature of the OpenAI API

OpenAI API and Whisper based Video Translation

Automated pull requests reviewing and issues triaging with ChatGPT.

Minimal agent runtime built with DSPy modules and a thin Python loop. Includes CLI, FastAPI server, and eval harness with OpenAI/Ollama support.

A GitHub Action that uses OpenAI ChatGPT to do code review

Extract data from websites in LLM ready JSON or CSV format. Crawl or Scrape entire website with Website Crawler

An intelligence layer grounding autonomous agents in verified, real-time knowledge at scale.

BrainX 是一个智能系统，分析各种媒体格式，整合到知识库，并生成定制内容，包括机器人、洞察和媒体。它旨在为用户提供个性化和自动化的解决方案。

Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors in .cursorrules, CLAUDE.md, AGENTS.md and more.

A complete system for managing Obsidian vaults with Claude Code and Cowork. Designed for two vaults (work and personal) with consistent structure, frontmatter schemas, agent skills, automation hooks, and migration tooling.

Stop your AI agent from shipping insecure IaC. ops0 CLI sits between Claude Code, Codex or Gemini and your cloud, scanning every .tf the agent writes and blocking destroy commands before they run.

Agents, and RL environment, for optimizing GPU kernels on AMD ROCm using LLM agents. Benchmarks LLM serving workloads end-to-end, profiles bottleneck kernels, optimizes them via Claude Code or Codex, and scores on compilation, correctness, and speedup.

🇪🇪 Open-source AI SDK for Estonian government and private services. MCP servers and skills. Connect Claude, GPT, agents and models, to Estonia's digital infrastructure.

OpenPawz is a native, offline-first desktop AI platform (Tauri v2 + Rust) that lets you run local models or connect to any compatible provider. It gives you private-by-default agents with hybrid memory, strong security guardrails, and extensibility through built-ins plus n8n community integrations

local-first analytics for AI agent skills

AI coding skills and prompts for Android lead engineers, works with Claude, GitHub Copilot, Gemini, and Cursor. Covers Jetpack Compose, shared element transitions, beautiful UI, architecture decisions, code reviews, and MCP integration.

MCP server for OpenRouter — chat with 300+ LLMs (Claude, Gemini, GPT), analyze images / audio / video, generate images / speech / music / video (Veo 3.1, Sora, Seedance, Wan) from Claude Desktop, Cursor, Kiro, VS Code.

Local-first AI memory — runs offline on any machine with 8 GB+ RAM (SBC, mini PC, laptop, workstation). Zero-loss verbatim archive, knowledge graph, hybrid retrieval. Framework-agnostic, no cloud.

Marketing skills for AI agents — paid ads, social media, SEO, competitor research, creative generation, email, analytics, and more. Powered by Hyper MCP.

AI-native IDE workspace for legal and document-heavy workflows: files, agents, plugins, WPS editing, OCR, evidence chains. VS Code for lawyers.

Where the fox came from — the original AI full-stack project generator with multi-agent codegen and live preview.

Deploy a recurring, self-funding sovereign AI agent on Ritual testnet with one command.

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

An open standard for portable, interoperable AI memory across tools, sessions, and devices.

Battle-tested model-dispatch doctrine for Claude Code — portable ops rules that let Sonnet/Haiku reliably run projects. Iterated in real deployments, not one-shot generated.

Beads, planning, and knowledge injection for AI coding agents

A local dashboard to manage AI coding agent skills — sync, install, and organize skills across OpenClaw, Cursor, Claude Code, and more.

Zero-dep agent workflows with structured approval gates and adversarial review.

Policy guardrails for coding agents (Claude Code, Codex, Cursor) — every tool call is checked locally, before it runs.

OpenCode Mobile — open-source Android client for the OpenCode AI coding agent. Run AI coding sessions from your phone against your self-hosted server over Tailscale. Available on F-Droid.

transformers pytorch mpt text-generation custom_code dataset:glaiveai/glaive-function-calling

transformers safetensors qwen text-generation custom_code zh

Your AI agents can't see your files. ctxd connects your cloud data and makes it searchable via API, CLI, or MCP.

The package manager for AI agents — install, test, publish, and manage skills & MCP servers across 86+ agents. Zero-dependency CLI.

Production-grade agent skills and Custom GPT prompts for ChatGPT, Claude Code, and Codex. 140 skills, 28 agents, Agent Skills spec compliant.

InkAI 是一个基于大语言模型的长篇小说智能创作框架，覆盖从创意构思到章节成品的完整流程。系统由 25 个专业 Agent 协作驱动——标签推荐、角色创建（Big Five 人格模型）、三幕剧故事线生成、章节写作、五维质量评估，以及读取前文知识的智能续写。前端为 Bootstrap 5 交互界面，后端 Flask API + 模块化 Agent 编排，JSON 文件持久化，零数据库依赖。 支持都市 / 玄幻 / 历史 / 科幻 / 悬疑 / 言情六大门类，70+ 风格标签。适合网文创作、剧本辅助、创意写作教学和内容生产自动化。

Auto commit & push for AI coding agents, with a safety level you pick.

Turn any empty repo into a loop-ready repo: a portable per-project spine + anti-slop build loops for AI coding agents.

Bring Claude Code to Visual Studio 2026: A native diff with accept/reject, a live debugger Claude can drive autonomously, Roslyn code navigation, and Test Explorer integration. The IDE half of Claude Code's integration protocol. Community-built, unofficial.

Air traffic control discipline for agent output. Written for a reader with ADHD.

A browser agent with a Google Chrome extension that can work in your browser. Based on Google Gemini 2.5 computer use model.

This project applies the core knowledge from the LLMOps module, including the design and implementation of the API Layer, Inference Layer, Observability Layer, Cache Layer, Guardrails Layer, Routing Layer, and the Data Ingestion Pipeline.

GPT4-powered Slack bot that can scrape URL contents

This is a web app that integrates GPT-3 with google searches

GPTModels - a multi model, window based LLM AI plugin for neovim, with an emphasis on stability and clean code

This code provides a gpt agent that can automatically execute several basic steps of the lean startup approach for business model developmet

VS Code Extension that shows information about the estimated token usage of GitHub Copilot

100 Days of Code | Daily Challenges | Beautifully Crafted Designs | Created for Full-stack/Frontend/Web Developers - Vibe Code with AI.

PWN is an open security automation framework that aims to stand on the shoulders of security giants, promoting trust and innovation.

Laozy is a self-hosted web application that helps you build and deploy LLM-based dialogue robots. The robot you built can connect to instant messaging platforms like WeChat, Telegram, etc. You can also integrate it into your app with REST APIs.

Official Code for "Non-Probability Sampling Network for Stochastic Human Trajectory Prediction (CVPR 2022)"

Swama is a powerful command-line interface (CLI) tool for interacting with Swagger/OpenAPI definitions

Query a database using natural language

A sophisticated RAG intelligence engine for Singaporean laws, policies, and history. Comes with a triple-AI failover backend (Gemini/Llama/Groq), semantic embeddings using FAISS, and an Apple-inspired interactive UI. Designed with precision and high availability in mind.

Research framework that quantifies how steganographic obfuscation of embeddings defeats off-the-shelf statistical detection in RAG pipelines, paired with the VectorPin cryptographic-provenance defense

Laravel integration for the Anthropic API: facade, config publishing, install command, testing fakes, messages, streaming, tool use, thinking, and batches.

AI Agent Daily Digest — Collect and analyze your AI coding assistant usage

🎓 课表解析 · 点名预测 · 逃课方案 · 反馈学习

Code for running the implementations proposed in: Westny, T., Oskarsson, J., Olofsson, B. and Frisk, E., "MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs", IEEE Transactions on Intelligent Vehicles

🦀 Open-source alternative to Claude Code, built from scratch in Rust. Agentic coding CLI — thinks, plans, and executes with any LLM. Compatible with Claude Code workflows.

A Python desktop application that enhances Excel and CSV files using AI transformations. Features dual AI backends (OpenAI API and local Ollama models), customizable prompt templates, batch processing, and an intuitive interface. Perfect for data cleaning, formatting, and analysis tasks with the power of large language models.

Loom is an AI harness, that can be used with local or cloud LLMs, for complex tasks. It decomposes work, drives execution through a verification harness, and keeps models on track with structured state instead of history. It can route between thinking and acting models, verifies outputs, and exposes an APP/TUI/API/CLI/MCP for both humans & agents.

Hooks for Claude Code and Cursor for secrets scanning

Simple opinionated issue tracker for AI Agents

Give your AI agent access to all crypto data — prices, wallets, social, on-chain, prediction markets. One skill, 83+ endpoints.

A small Recursive Language Model: let any LLM run code on its context instead of stuffing it into the prompt.

OpenVitamin is a local-first AI execution platform that unifies Agents, Workflows, and multi-model inference into a single programmable system — designed for building real, production-grade AI applications.

AI-powered platform for OSINT intelligence analysis. Features archive discovery with hypothesis-driven investigation, GLiNER entity extraction, Mapbox geospatial visualization, network analysis, and document processing. Built with FastAPI, Next.js, Weaviate, and DSPy.