Code agents

Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-turn RL environment with support for agent, user, user feedback, transition and veto models. It also implements KTO and expert iteration for training on user preferences.

这是一个基于大语言模型的 Text-to-SQL 工具，支持： 1. 多种 LLM（OpenAI、Qwen、硅基流动） 2. SQL 验证和安全检查 3. Schema 管理和语义注释 4. Few-shot 学习 5. 置信度评估 6. 查询执行和结果格式化

code for an agentic search tool using Langchain

利用ChatGPT最新的function-calling，实现类似LangChain Agent代理的联网、环境交互，目前支持 百度百科 | 网易新闻 |百度百科 | csdn | 掘金 | 谷歌api | Bing 工具

Generative web browsing chat agent with text + vision input. Powered by MultiOn, llama-3, llava, qwen, Next.js, FastAPI, and Supabase. Landed me an internship at MultiOn :)

Code for Multi-agent reinforcement learning to unify order-matching and vehicle-repositioning in ride-hailing services

A multi-agent workflow for genetics-informed health optimization, designed for use with Coding Agents.

Joblet is a micro-container runtime for running Linux jobs with: Process and filesystem isolation (PID namespace, chroot) Fine-grained CPU, memory, and IO throttling (cgroups v2) Secure job execution with mTLS and RBAC Built-in scheduler, SSE log streaming, and multi-core pinning Ideal for: Agentic AI Workloads (Untrusted code)

Official Telnyx Local Model Context Protocol (MCP) Server that enables interaction with powerful telephony, messaging, and AI assistant APIs. This server allows MCP clients like Claude Desktop, Cursor, Windsurf, OpenAI Agents and others to manage phone numbers, send messages, make calls, and create AI assistants.

用 Claude Code 的方法论来指导 Agent 开发 / Build agents the way Claude Code is built.

A template for creating and publishing Claude Code skills as npm packages

Claude Code Swarm Intelligence Plugin — agent coordination via hooks + DuckDB

A simple agent-runnable repo that interviews you, learns your taste/voice/references, and builds a personalized Creative Brain in markdown — so Claude Code, Hermes, Cursor, or any agent can create with your actual context instead of starting from zero.

A Claude Code Plugin that enables seamless integration with Codex AI Agent for code analysis, implementation, and collaboration tasks.

Calling Elixir or Erlang functions from native code written in Rust

Supercharge agents with React runtime values.

基于 Planner–Manager–Executor 的文本 Agent；Executor 支持 YAML / Python 高度自定义；可选 Neo4j+Graphiti 记忆图谱；FastAPI + React。

ArXiv Agent is a terminal-based intelligent assistant designed for researchers and engineers who want to stay on top of the latest AI trends without drowning in PDFs. It combines daily digests, RAG-powered chat, and automated implementation into a single, cohesive workflow.

开源我自己 — A Claude Code skill trained on Flood Sung's entire Zhihu corpus (152 articles + 178 pins + 254 answers). Fork it to open-source yourself.

Build realtime AI interviewer voice agent that joins meetings. It demonstrates integrating Deepgram (STT), OpenAI (LLM), and Eleven Labs (TTS) via WebRTC for natural conversations.

🧴glooit keeps your AI agent rules, MCP, Skills & Commands configurations in perfect sync across Claude Code, Cursor, Roo Code, and other AI development tools.

A Blueprint-style visual node editor for creating FastMCP servers. Build MCP tools, resources, and prompts by connecting nodes - no coding required.

Security scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.

Build your own mini coding agent in Rust.

Repo-local OpenClaw workspace with modular JSON5 config, plugins, and Docker sandboxes — runs coding-agent CLIs on desktop or Android Termux.

How I Met Your AI CLI

Zero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)

Agentic Operations & Observability Workshop: Hands-on guide for implementing AI-enhanced observability in cloud apps using Azure Monitor, Application Insights, and Azure SRE Agent. Covers metrics, logs, traces, multi-cloud monitoring, and agentic DevOps best practices.

Source code for the Foundations of Agentic AI for Retail Book

JanSahayak AI – A multilingual AI assistant that helps citizens understand and access government welfare schemes through conversational voice and chat.

OpenCode OpenAI plugin for native Codex auth, multi-account rotation, and identity spoofing.

A Serverless Chat App with Contextual Note Integration Featuring Amazon Bedrock, the OpenAI API and SST

End-to-End-Graphrag-implementation

Integrate Odoo with OpenAI and GPT Models. Make OdooBot finally useful by integrating with OpenAI ChatGPT-3!

This repository contains a collection of AI-assisted development prompts designed to improve code quality, consistency, and efficiency in your projects

♾️ ChatGPT [API] - (PHP-AGC007)

A Toolbox Platform for Creating Your Own Tools. Bake Them with Code or AI.

A one command Voice AI deployment script for MacOS. Supports Sesame, Kokoro, Spark, Zonos and Whisper. Creates an api server with OpenAI server compatible endpoints.

AI-powered telephony solution that enables businesses to deploy intelligent voice agents for various use cases such as customer support, appointment scheduling, lead qualification, and information collection.

Multi-agent orchestration plugin for Claude Code — 10 specialized agents, persistent Brain memory, quality gates, continuous QA, wave-based parallel execution, and mechanical enforcement hooks

Open source Twitter AI Agent to post-tweet, schedule-tweet, auto-reply, auto-engage using X API and Browser Cookies

Cryptographically signed policies that constrain AI agent behavior. Same attestation primitives as cilock, applied to agent execution: identity binding via MCP, JWT + signing-key separation, sublayouts for sub-agents.

Aqua is a lightweight, agent-agnostic coordinator for CLI AI agents. It enables multiple AI agents (Claude Code, Codex CLI, Gemini CLI, or any CLI tool) running in separate terminal sessions to collaborate on tasks within a shared codebase. Built with Claude ❤️

Plan iron, verify real. Claude Code plugin: ironclad planning with independent verification chain. Turns any input into bulletproof plans, executes with TDD, verifies with agents that never saw the executor's work.

Human-first AI Design Engineer with 8 specialized personas.

Conduct autonomous Claude Code agents at scale safely. Human-on-the-loop orchestration platform with kill switch, cost tracking, and inter-agent messaging.

Enterprise AI Security Platform - Real-time firewall protection for LLM applications against prompt injection, data leakage, and function abuse attacks

ReviewScope is an open-source AI PR reviewer for GitHub that goes beyond the diff. Uses AST-based analysis and issue validation to deliver low-noise, actionable code reviews. Bring your own API key.

Real-time task tracking and conversation memory for Claude Code sessions

MemVector: Local Vector API, Storage & Embedding Engine for PHP

A self-improving knowledge base about LLM agent infrastructure

Real-time monitoring dashboard for AI coding agent fleets: session health, output streaming, and observability across Claude, Codex, and Gemini

HIPAA-eligible DIY Twilio alternative for voice AI telephone applications. Uses Asterisk PBX and AWS Chime SIP trunking.

Secure and lightweight Python code execution environment for LLMs

AI Agents internals - system prompts, tool architectures, and implementation patterns

Typescript library for integrating Adyen APIs via an MCP server

Code for the paper "Searching Privacy Risks in Multi-Agent Systems via Simulation"

Run many Codex & Claude agents in parallel without them overwriting each other. Isolated worktrees, file locks, PR-only merges. Auto-wires Oh My Codex, Oh My Claude, OpenSpec, and Caveman in every worktree.

This project demonstrates how to build a semantic search + RAG pipeline using .NET

🔗 Claude Code 飞书 Channel 插件 — 在飞书中直接与 Claude 对话，支持双向消息、配对认证、群组聊天、文件附件

Vorn - The agent command center

Human-vetted, community-curated skills for AI coding & agent tools.

Comprehensive, community-curated directory of autonomous AI agents, frameworks, platforms, and automation tools for developers and enterprises. Explore the latest in multi-agent collaboration, coding automation, workflow orchestration, and domain-specific AI assistants.

Official code for the paper: "Multi-User Large Language Model Agents"

The AI-native portfolio — this one talks back.

🍞 Toast notifications from AI coding agents on your macOS menu bar, with tmux pane switching

Local-first Python CLI and MCP server for versioned, cited context from web and document sources.

基于 FastAPI 的生产级 AI Agent 框架，支持 100+ LLM 提供商、MCP 工具集成、多 Agent 协作、RAG 知识库和沙箱隔离执行

Multi-agent collaboration rooms for Claude Code, Cursor, Codex & Gemini — distributed dev, code review, PR handoff, FE↔BE integration. MCP-native, self-hostable.

The Vibe Coding Workstation — A desktop workspace where terminal, AI agents, and git live together for uninterrupted flow state

ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

Research Pilot helps AI agents understand, maintain, and advance research projects through papers, claims, evidence, experiments, and human-gated updates.

IMAP/SMTP email for AI agents -- read, send, organize folders, and manage attachments across multiple accounts, with auto-discovery.

A scalable AI chatbot platform built with FastAPI and LangGraph, featuring multi-agent orchestration, multi-tenant vector storage, cross-chat memory, and voice call capabilities through LiveKit integration.

멀티에이전트 Claude Code 하네스를 위한 토큰 비용 lint — 10 카테고리 × 31 sub-patterns 분류학 + 정적 감사 스크립트 + LLM 0회 결정 트리. Korean primary, English mirror.

Open-source RAG engine for ingesting, indexing, and querying unstructured documents

High-performance LLM Gateway built in Go - OpenAI compatible proxy with multi-provider support, adaptive routing, and enterprise features

Aqueduct is a simple yet fully-featured AI gateway built on top of the LiteLLM Router SDK using Django.

OpenAI Router 轻量级、持久化、零配置的 OpenAI API 统一网关

We read 17 Claude Code repos (500k+ stars) so you don't have to. 176 tips, nothing to install. Consensus-filtered, tagged by difficulty.

Open-source macOS SwiftUI Codex client with local Markdown chat history, reusable context, Skills + Mods, and explicit local safety controls.

AI Coding Agent Orchestrator with continuous learning. Orchestration layer on top of Claude Code and OpenCode

⚡️ Real-time Knowledge Graph for AI Agents. Connect LLMs to verified weather, stock, and currency data via instant tool-calling. No API keys, no scrapers, just grounded facts in <100ms.

Curated technical knowledge base: 785+ dense reference articles across 26 domains. Agent-first format with wiki-links, gotchas, runnable code. Not tutorials — verified references for AI agents and engineers.

👻 ghost gpt– A powerful Termux-based penetration testing suite for ethical hackers. Includes free and premium tools to enhance your security testing workflows.

A Deception Security Layer for MCP Servers. It injects "ghost tools" (fake security-sensitive tools) that act as honeypots.

Monitor Claude Code rate limits in real time from your Windows system tray. Native .NET app (~6 MB), speedometer gauges, dark/light theme, 14 languages, WSL + Windows support.

Governed local runtime for AI coding agents: task lifecycle, mandatory gates, reviews, doc-impact checks, and auditable completion.

GODMODE — AI Development Team powered by NEURON.ONE. Multi-agent orchestration for Claude Code. 56 skills, 16 rules, cross-model disputes (Claude + GPT + Gemini).

Team code review, standardized. Define your team's review rules once in YAML, enforce them on every PR/MR across GitHub & GitLab — right inside VS Code. Works with Copilot, Claude, or OpenAI.

Fully automated open-source trading bot for BIST (Borsa Istanbul), a Turkish stock exchange, including both technical indicators and AI news analysis. Implemented with NodeJS.

100 Claude Secret Codes — prompt shortcuts that change how Claude responds. Interactive version at clskills.in/prompts

Agentic AI Agents, LangChain v1, Gemini 3, Tool Calling, Agent Memory, Prompt Engineering, Guardrails, MCP, FastAPI

A configurable personality and mood system plugin for OpenCode

Persistent memory for AI agents. Extract once, recall forever.

A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

A meta-skill for Claude Code that routes requests to the right installed skill — suggest mode or silent auto-routing

All-in-one agent harness for OpenAI Codex CLI — Boss meta-orchestrator, 17 curated agents (+17 opt-in AI specialists), 123 curated skills, 3 MCP servers. Install once, curated specialists ready.

The enforcement tool for Canonical-Driven Development (CDD). Audit, generate, and guard your project documentation. Zero dependencies.