Code agents

Portable Agent Skills for AI-assisted engineering workflows

Terminal coding agent built from scratch — routes models by task, adapts execution policy to model capability, and verifies its output before handing it back

为 Claude Code 等 Agent 打造的分层记忆管理系统，让 AI 跨会话、跨项目、跨机器持久化并共享项目与个人知识。

Structural context for AI code reviews. Resolves blast radius through the TypeScript type system.

A powerful CLI for AI-powered chat, automation, and multi-platform integrations — terminal-native alternative to Claude Code & OpenClaw. Chat with your bots, automate workflows, and connect Telegram, Discord, Slack & more.

Codex-style computer use plugin for DeepSeek Harness (DSH): screenshot, click, type, scroll & open apps on macOS / Linux / Windows. 桌面自动化 AI Agent 插件。

A collection of skills for Claude Code — installable via plugin marketplace. First skill: ebay-seller (full eBay.de selling workflow).

Daedalus — self-evolving, local-first AI coding assistant powered by the Hermes Deep Mind engine: persistent memory, failure immunity, sleep-time compute, causal world model, MoE routing over 23 providers, calibrated confidence. Terminal + Web IDE + VS Code.

yeaboi — AI Scrum Master in your terminal: sprint planning, standups, retros, planning poker, 1:1s and delivery reports for your team, plus cost, daily digests and security posture for the AI coding agents working alongside it.

Private, local Claude Code usage intelligence track tokens, estimated cost, cache efficiency, budgets, projects, and live sessions with zero telemetry.

Free, open-source AI video editor for macOS, Windows and Linux — drive the whole timeline from Claude, Cursor, or any MCP client.

BOTCF Agent：基于 DeepSeek Harness 的本地 AI Agent 桌面客户端，集成 BOTCF/NewAPI、多 Token 模型路由与渠道健康监测（非商业许可）

transformers gguf code codeqwen chat qwen

An open-source AI agronomy agent that runs locally on your own machine or server, reaches you on Telegram and WhatsApp, and computes aquaponics system designs from a deterministic, source-cited engineering core instead of guessing them.

Automated development pipeline plugin for DeepSeek Harness: requirement pool → LLM refine/design/plan/review → workspace-routed implementation → verify → merge → report

Synthelion compresses prompts before they reach any AI model — cutting token usage by up to 70%, reducing API costs, and speeding up responses. It works with any agent or framework: Claude Code, OpenAI, LangChain, OpenCode, Cursor, and more.

The most comprehensive LLM + MCP security guide i.e. OWASP aligned, real CVEs, actionable checklists

Production-style AI knowledge platform for research papers using FastAPI, React, PostgreSQL/pgvector, Ollama, Docling, hybrid retrieval, cross-encoder reranking, streaming responses, and intent-based query routing.

🛠 Chrome Built In AI 기반 멀티 에이전트 프레임워크 🛠

Local control plane that routes engineering tasks across Claude Code, OpenCode, and Codex with real fallback, capability-tier routing, and durable task state.

论文服务公司多agent架构

The multi-agent coding loop that covers every angle — one model builds, independent AI models review it from every direction, tests decide, you hold the final gate. Privacy-enforced, anti-drift, self-improving.

Governance-as-code for AI coding agents: author a policy once, enforce it on every agent (Claude, Copilot, Cursor, Codex) via git hooks, CI, and native controls.

GUI for pi - Sessions, Streaming, Tools, and Thinking without leaving the agent stack.

AI-native developer collaboration platform unifying team chat, ticket lifecycle, and AI code execution. Two-stage agent pipeline (Planning → Code) with human approval gates, running entirely on local open-weight LLMs via vLLM. FastAPI/PostgreSQL modular monolith, Redis, Qdrant, React/TypeScript, Docker sandboxing.

Open Vibe Architecture (OVA): architecture-as-markdown framework and Python CLI for coding-agent repositories.

Agentic AI coding tool for your terminal. Reads and searches your repository, edits files, runs commands, and verifies the change. Source-visible client.

Open-source, multi-tenant AI agent platform on AWS Bedrock — visual agent builder, RAG knowledge bases, evaluation suite, and omnichannel delivery (SDK widget, REST API, WhatsApp, Telegram). Self-hosted, MIT licensed.

Enterprise-grade conversational AI platform built with Django REST Framework, Next.js 15, LangChain, and PostgreSQL with pgvector, featuring Docker orchestration, Celery task queues, and production-ready architecture patterns for scalable AI chatbot deployments.

Fast Rust proxy that turns GitHub Copilot into OpenAI- and Anthropic-compatible API endpoints. Works with Claude Code, Codex CLI, and any OpenAI/Anthropic SDK.

Letta Code mod that detects non-English agent output (GLM Chinese-drift) and corrects it immediately — deterministic Unicode detection, turn_end + polling layers, anti-spam rails

DeepSeek Harness 批量并行子 Agent 调度插件：swarm_batch 工具（Kimi Code Swarm 模式移植）+ /swarm 命令 + 聊天内实时进度条

Open-source MCP supervisor for Codex to delegate, monitor, and manage Grok, Cursor, and DeepSeek coding agents.

Evidence-bound multi-agent council for Cursor and Claude Code. Scout (last30days), Advocate vs Skeptic, Fact Checker (deep-research). Ranked verdict with dissent.

Autonomous autoresearch framework for Codex and Claude Code, combining experiment DAGs, scientific memory,literature grounding, agentic planning, reproducible benchmarks, and local dashboards.

Run OpenAI Codex CLI on HarmonyOS PCs / 鸿蒙 PC 上跑 Codex CLI 的一键移植包

Autonomous trend detection to pump.fun token launcher. Ten sources, independence-weighted scoring, hard-capped spend rails, a self-tuning agent inside a code-enforced allowlist, and a public dashboard that shows its own duds.

ArchGraph — an architecture-graph driven framework for Agentic Engineering. A long-term memory for coding agents, built on one ArchiMate 3.2 intent graph read/written through a single MCP interface.

Always-on AI desktop companion: a 3D VRM avatar that listens, talks, runs your PC, and remembers you — local-first multi-LLM, RAG memory, voice pipeline, Dockerized backend, portable Windows app.

gguf code agent agentic-coding moe llama-cpp

Build Your Own ChatGPT AI App in JavaScript | OpenAI, Machine Learning

A NextJS application who consumes OpenAI (GPT-3.5) for generating blog posts based on a given topic.

Create a text to speech AI host for Twitch

tweetGPT

Branching story writing tool with generative AI

Prompt Creator – A lightweight Python GUI tool that visualizes project structures and automatically copies code to the clipboard, streamlining the creation of prompt contexts for ChatGPT.

Kaspa sovereign architect engine ; engineering skill for AI agents, with source-gated protocol intelligence and release packaging.

Source-only Linux packaging for OpenAI Codex Desktop — local DEB, AppImage, and Wayland builds

Compact tmux status-bar widget showing Claude Code & Codex CLI 5-hour usage — bars, reset countdowns, brand-colored glyphs.

Unofficial local Windows 11 Codex usage monitor with a Liquid Glass widget, quota tracking, live task status, Token usage, and bilingual UI.

Example chat application using vue 3 and openai api

API gateway for OpenAI Chat Completion using Cloudflare workers

A safe local-first Codex session migration toolkit with web UI, backups, restore, and health checks.

A Ruby wrapper for OpenAI API

Hot-switch custom Codex models, API endpoints, and keys without restarting Codex. Includes a follow-window Windows sidecar.

Build web applications with local AI. Describe your app in natural language to generate code in a browser workspace with a built-in code editor.

The .ah (Teleological Semantic Format) skill bundle for Claude Code, Cursor, Trae, Zed & Kiro by David C. Cavalcante. 9 gematria-checksummed skills: coding guidelines, project audit, problem-solving, AI engineering, NPM/Node, content craft, deliberation council & research-grade benchmarking. Token-efficient, always-on after one load.

Multi-key proxy for NVIDIA NIM with a native desktop dashboard — auto-rotation, cooldown, RPM limiting, Claude Code + Codex CLI + opencode support. Free-tier keys pooled behind one endpoint.

AI agent skills for Claude Code and compatible agents — workflow, coding, design, Claude Code meta, media, productivity, and writing

Switch between multiple Claude.ai accounts in Claude Code without re-logging in — live rate-limit visibility, session warm-up, and a launch-time account picker.

Restore Claude Code desktop sessions after switching Claude accounts (macOS)

出门前电脑上开的活，到手机上就接不上了？用飞书接着指挥同一个 Claude Code 会话，回来接着干。 Continue the same desktop Claude Code session from your phone through Feishu / Lark.

An opinionated workflow system that restructures how product managers work with Claude Code. 16 PM skills, 9 agents, 10 coding rules, 13 slash commands, 6 automation hooks, product brain system, and session lifecycle with memory/handoffs.

Video-analysis skill for AI agents.

Widget flutuante para Windows que mostra o consumo da conta Claude Code: sessão de 5h, janela semanal, limites por modelo, créditos extras e tokens gastos por modelo. Lê a credencial OAuth local, sem telemetria.

Four idempotent installers for an AI-agent terminal workflow (Linux · macOS · Git Bash): a TUI project picker, one git worktree per agent task, Ghostty tuned for agent output, Claude Code on DeepSeek's Anthropic-compatible endpoint, plus the GitCraque and surf-skill CLIs.

LLM Playground - Demo Solution

A production-ready, WhatsApp-native AI agent that qualifies real estate leads, maintains contextual conversations, extracts structured CRM data, and automates follow-ups - handling 90–95% of real-world customer interactions without human intervention.

Enclave — self-hosted, private legal AI for law firms & in-house teams. AI co-counsel, contract review, due diligence, drafting & playbooks, all inside your own VPC. Built on Onyx + Paperclip.

Memory Operations Platform for AI agents — ingestion, lifecycle, token-aware retrieval, and control UI

A personal AI assistant that runs entirely on your own machine: encrypted knowledge base, approval-gated tools, local models (MLX/Ollama) or your own cloud keys, built-in voice, and end-to-end-encrypted phone access. Source-available (ELv2).

RAG-powered document chatbot using Llama 3.2 with hybrid retrieval, conversational history, and Gradio interface.

读 CSSOM 量出一个网站的设计系统 —— 不截图、不用视觉模型的 design token 提取 skill · OKLCH 色板 · token 溯源 · 系统漂移检测

some tool i decided to make which makes ai type for you in discord

Lightweight, ultra-fast FastMCP server for Computer Use & GUI automation on Linux and Windows (Mouse, Keyboard, OCR, Video, Web).

Drive Unreal Engine 5 from an AI agent — MCP server over the Remote Control API and in-editor Python. No C++ plugin to compile.

微信聊天机器人。基于微信 iLink Bot API 的 AI 聊天机器人，支持 Termux 手机部署。内置 CoreCoder Agent 可执行文件读写、Shell 命令，流式分段回复模拟真人打字，网页控制台管理配置与日志。所有消息由 AI 驱动，可帮忙写代码、改文件、运行任务。

Community plugins for DeepSeek Harness (DSH) Web GUI: token cost meter, billing balance, update checker — plain JavaScript, no build required.

Distill Dan Koe's content frameworks and thought systems into an accessible digital brain to scale your personal brand and one-person business.

面向 Codex 的桌宠生成与校验 Skill，可创建、修复、验证、安装和打包 Desktop Pet Launcher 高清宠物包。

Make AI-generated content undetectable. Prevents em dashes, buzzwords, over-formatting, narrating comments, git co-author trailers.

A modular AI agent framework built on Vercel AI SDK. Zero-config agents with real tools, durable workflows, and HTTP interfaces.

Terminal-first AI financial agent — runs fully offline via Ollama, 19+ cloud LLM providers, live market data, and a built-in quant research engine.

DeepSeek Harness plugin that auto-nudges agents to consult docs or web search when local trial-and-error becomes costly. DeepSeek Harness 插件：当本地试错成本升高时，自动注入检索提示，引导 Agent 查阅文档或联网搜索。

通用考试知识库：AI 备考搭子，不用啃教材直接刷题就能过。索引→精讲→错题→检索协议，任何考试可复用（考公/考研/CIA/CISA/CPA/CFA/法考），CIA-Part3 为完整实例

Lossless context folding for the Pi coding agent: only the oldest context changes; the fresh window stays untouched.

AlphaStream India is a production-grade, real-time investment intelligence terminal designed to empower Indian retail investors. Featuring a Bloomberg-style terminal UI, it integrates Gemini 2.0 Flash, FastAPI, and React 19 to deliver grounded, backtested, and high-alpha investment signals.

Full-stack Procurement & Vendor Management ERP - React 19 + Express 5 + MongoDB + Redis + Socket.IO. Features Google OAuth, LangChain AI assistant (Gemini 2.5 Flash), 2-level approval workflows, auto PDF invoices via ImageKit, Brevo email, JWT auth & Redis rate limiting.

One MCP server for 185+ live web-data APIs: search, social, e-commerce, real estate, jobs, travel, news and finance. Clean JSON from sites that block scrapers.

Self-contained pwn/rev CTF solving kit for Claude and Codex — tools, doctrine, knowledge, and automated analysis workflows.

gguf pretrained text-generation en license:other endpoints_compatible

Multi-agent AI skill orchestration — 13 skills, 7 lifecycle phases, from idea to post-release. Works with Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and any agent that reads Markdown or speaks MCP.

A wall of mail slots for coding agents running in parallel. Each git worktree gets a pigeonhole; agents post what they are working on and leave each other notes. No server, no daemon, no MCP. One POSIX shell script and the filesystem.

A local, open source reference for conversational analytics over an Iceberg lakehouse: a Strands agent talks to a WrenAI semantic layer over MCP, with Trino execution and long-term memory.

Bedside: manners for AI agents that operate tools for smart, high-judgment non-experts. Ship and test, not only write.

YAAC: yet-another-agentic-chat. Messaging between concurrent AI coding sessions, across clients, over MCP. Zero infrastructure.

One IDE for every AI model

12 production-grade AI agent patterns in pure Python — ReAct, planner-executor, reflection, routing, memory, guardrails — on free NVIDIA NIM APIs

AI-powered dashboard for global cyber threats, trends, and defense.