Code agents

Web-based usage monitoring tool for Claude Code

monoml-agent - temporary placeholder

Moon for Claude: run Claude Code on external LLMs via LiteLLM

Bundled plugins for Claude Code including Agent SDK development tools, PR review toolkit, and commit workflows

Bundled plugins for Claude Code including Agent SDK development tools, PR review toolkit, and commit workflows

Bundled plugins for Claude Code including Agent SDK development tools, PR review toolkit, and commit workflows

Bundled plugins for Claude Code including Agent SDK development tools, PR review toolkit, and commit workflows

A prompt algebra for LLM orchestration. The code reads as its own specification.

Code coverage for MicroPython

Observability and DevTool Platform for AI Agents

Python SDK for Claude Code

Local semantic code search for Claude Code (MCP) using EmbeddingGemma, FAISS, and AST/tree-sitter chunking. 100% local embeddings and indexing.

This is an MCP server that emulates Claude Code's task management system, providing persistent todo functionality for AI coding assistants in IDEs like Cursor, Windsurf, and others.

A set of block-based LLM agent node libraries designed for ComfyUI.This project aims to develop a complete set of nodes for LLM workflow construction based on comfyui. It allows users to quickly and conveniently build their own LLM workflows and easily integrate them into their existing SD workflows.

Add your description here

LLM Sandbox is a lightweight and portable sandbox environment designed to run large language model (LLM) generated code in a safe and isolated mode.

MCP server for code search using ripgrep

MCP server for Microsoft SQL Server with SQL Agent job management and stored procedure version control

Multi-agent framework with 684 skills, constitutional governance, 19-layer runtime (pipeline, privacy, AI, skills, cognitive, scalability, observability), and Anthropic SDK integration.

Multi-Agent Alpha is a robust, open-source framework for building, managing, and deploying intelligent multi-agent systems. It provides a flexible architecture for creating custom agents, with a focus on code quality, testing, and continuous integration.

Cookiecutter-based bootstrap CLI for new multi-agent Claude Code projects (companion to governance-core; P-0059).

Command-line tool for orchestrating multiple AI agents in parallel or sequence

Run multiple Claude CLI accounts with shared settings, plugins, marketplace sync, and backup/restore

Agent orchestration and swarm management for multi-agent development

Foundation framework with intelligent directory management for multi-agent development

A multi-agent system for debugging API failures

DevOps CLI system for multi-agent development workflows

A package for developing Multi-agents

A Python AI Agent framework for runtime self-iterating code

Style-aware code generation — analyze any codebase and generate new code that matches its style

A locally runnable LLM

CLI utilities for Claude Code plugins

MCP server for MyLLMWiki (Obsidian) capture across Cursor, Codex, Claude

Type annotations for boto3 DevOpsAgentService 1.43.80 service generated with mypy-boto3-builder 8.12.0

Report mypy annotation coverage for a Python codebase.

Reusable skills for AI coding assistants (Copilot, Claude Code, Cursor, Codex, Gemini CLI, and more)

Nano: A minimal, zero-frills coding-agent for research on agent-in-the-loop training

A terminal-native IDE that embeds Claude Code alongside a code editor, file tree, and terminal

Minimal AI Coding Agent - A lightweight alternative to Claude Code

Minimal AI coding agent (~1300 LoC) inspired by Claude Code. Works with any LLM.

In-house CLI agentic tool for NashTech — define, manage, and invoke AI agents from anywhere.

Agentic RAG MCP Server — 12 tools for AI-driven multi-round code retrieval that outperforms naive single-shot RAG

Powerful LLM framework — 3 lines of code to do what LangChain takes 30. Chat, Tools, RAG, Agents, Streaming.

Your Python AI Coder

NeoGPT: Chat effortlessly with Documents, YouTube Videos,Code, and Social Media Chats. Your go-to for quick and smart interactions! 🤖💬

Drop-in LangChain integration for Neruva agent memory substrate. v0.2.0 adds AUTO-PILOT: NeruvaAutoPilot (classify intent + reflect + extract via your LangChain LLM) and NeruvaAutoPilotCallback (BaseCallbackHandler). Plus NeruvaChatMessageHistory + NeruvaContextRetriever for memory + KG recall, NeruvaCodeGraph (5 code nav methods), NeruvaCognitive (13 cognitive primitives). Pattern-C: substrate stays $0/call.

The agent for NetDevOps, which interact with network device using CLI.

Python SDK for the NetIntGPT Agents API

The NeuraGens CLI is a command-line interface tool that you use to initialize, develop, scaffold, and maintain NeuraGens applications directly from a command shell.

A lightning-fast AI-powered CLI toolkit for terminal productivity. Generate code, craft git commits, execute shell commands, and chat with any OpenAI-compatible LLM (OpenAI, Ollama, Groq, Claude, Gemini) directly from your terminal.

Anthropic Messages → NVIDIA NIM Proxy for Claude Code

LLM-Based Neural Network Generator

Neural Retrieval-Augmented Generation for GitHub code blocks

Multi-agent coding system powered by local LLMs

Situational awareness layer for Claude Code with auto status-lite reports, interactive brainstorming mode, and structured error analysis - designed for lawyers and coding novices

Local code intelligence MCP server — semantic search + code graph + impact analysis. Ask code in plain language.

LangChain connector for Noxy human-in-the-loop — routes to all registered devices via agent middleware and webhooks.

LangGraph connector for Noxy human-in-the-loop decisions — routes to all registered devices via interrupt/resume and webhooks.

nurovo-agent - temporary placeholder

Anthropic Messages → NVIDIA NIM Proxy for Claude Code

Run Claude Code (and any Anthropic SDK client) on NVIDIA NIM models via a local proxy.

A terminal-based coding agent for lightweight, asynchronous development tasks

A set of utility classes to enhance AI agent development with LangGraph and OCI

Open source code interpreter agent

OpenEntityMap - CodernityDB Storage

Open source code interpreter agent

Measure agentic coding performance using Thread-Based Engineering framework

Claude Code 角色工具包管理器 - 从原始角色文档一键生成安装工具包

Memory-grounded autonomous coding loops for Claude Code and Codex.

MCP server for accessing Ollama models on a remote GPU server via Model Context Protocol

Ein autonomer KI-Entwicklungsassistent mit lokalem Ollama-Backend.

A CLI tool for agentic coding tasks using local LLMs with tool calling

Agentic coding assistant for Ollama - Claude Code alternative

A lightweight, feature-rich proxy for Ollama, designed for development, testing, and staging environments. It simplifies access to remote Ollama instances that are wrapped behind another proxy layer like OpenWebUI. Anthropic and OpenAI compatible endpoints, included.

Smart multimodal router — LLM inference, image generation, speech-to-text, and embeddings across your device fleet. Cross-platform: macOS, Linux, Windows.

Ollama CLI prompt tool for local LLM code analysis

OmegaAgents is a scalable ReAct-based multi-agent framework designed for rapid solution development. It enables LLMs and agents to dynamically create and coordinate sub-agents during inference, mimicking human-like task distribution and collaboration. With built-in tools, parallel processing, and ephemeral memory management, it streamlines complex problem-solving through autonomous agent orchestration and structured output validation.

Omni Coverage Reporter. Strives to be as universal as possible in receiving, converting and sending reports from many types to different online APIs

Claude Code hooks + learning loop integration

Claude Code hooks + learning loop integration

A small Framework built on top of openai agents sdk to develop one prompt autonomous agents

TUI manager for Claude Code sessions - browse, search, and teleport across time

🤖 CLI de IA para desenvolvimento - Cria projetos estruturados e código limpo usando OpenAI ou Google Gemini

Python-first agent framework: define composable agent trees once, compile them to multiple agent runtimes (opencode, Claude Code, Pi, Codex), auto-optimize them per harness and model with test-driven autoloops, and evolve repo-tailored coding harnesses.

Open-source Agent SDK for Python. Runs the full agent loop in-process — no local CLI required.

Evaluate the capability of open-source LLMs in Agent, formatted output, instruction following, long context retrieval, multilingual, coding, math and custom task.

Terminal interface for OpenAgent

Production agentic loop backend — FastAPI + WebSocket

Web apps in pure Python with all the flexibility and speed of nextjs.

Repo-aware directive generator with optional MCP server

Powerful claude code open source alternative. AI coding assistant powered by Abdel-Hazim Lawani — use it in any folder

A lightweight, framework-agnostic safe code execution library for AI agents

OpenAI-compatible local API server backed by Codex credentials

This Python package provides a comprehensive and efficient wrapper for the OpenAI API, designed to support advanced application development based on ChatGPT.

Pinned Codex CLI runtime for the Python SDK

Python SDK for the OpenAI Codex CLI (wraps the bundled codex binary).

This package is an example of a Dependency Hallucination. There is no code in this package, it is just a placeholder to prevent exploitation.

make python module as code interpreter tool for OpenAI Agent by MOSS protocol

openai-otel is a library that automatically instrument your OpenAI python code using OpenTelemetry