Code agents

NDK - Nostr Development Kit. Includes AI Guardrails to catch common mistakes during development.

Enterprise-grade MCP server for live docs, best practices, code audit. Context7 alternative — 445+ libraries, smart dispatch (use gt mcp), plain-text intent routing, telemetry, SSRF-hardened multi-source fetcher, atomic disk cache, IPv6 + Unicode-homoglyp

AI integration package for SuperDoc

Babysitter Codex skill bundle and integration package for OpenAI Codex CLI with SDK-managed process-library bootstrapping, 15 orchestration modes, and BOM-safe SKILL installation

CLI coding agent for complex agentic workflows and long-horizon development. Local models (llama.cpp / Ollama), BYOK across 17 providers, parallel agents, persistent memory, scanned skills.

Multi-Agent Orchestrator System — docker-compose for AI coding agents

MCP server + portable captain skill that turns any AI coding CLI into the orchestrator of a worktree-isolated multi-agent crew

Wander AI Auto Dev Config: A dual-mode interactive CLI and compliant Model Context Protocol (MCP) server for multi-agent development teams.

Multi-agent pipeline orchestrator for OpenCode — 7-gate autonomous execution

Maximum continuous integration for multi-agent coding — every edit is committed and pushed to trunk immediately

Build your own multi-agent harness: typed toolkit for authoring plugins (skills, agents, commands, hooks) and shipping them to Claude Code and Codex from a single source tree.

Multi-agent coordination for Pi - presence, messaging, file reservations

Shared primitives for the tinyweb-agent framework. **You usually don't import this directly** — the higher-level packages re-export what you need.

Voice / realtime call surface for `tinyweb-agent-framework`. Primary provider: **Google Gemini Live API**. Backed by [plan 0014](../../plans/0014-realtime-voice-overview.md) and [task 0003](../../.manager/tasks/0003-realtime-call-voi-agent-dung-google-rea

Public entry point for building agents. Combines the `llm`, `tool`, `protocol`, and `core` packages into a friendly Promise/AsyncIterator API. **Effect-TS is hidden** from the public surface.

LLM core: schemas, **OpenAI Chat protocol**, route architecture, tool runtime, and provider profiles.

Wire-format types and stream codecs. Install this in your frontend bundle if you want type-safe AgentEvents on the client without pulling the whole agent runtime.

Built-in tool factories + FileStorage adapters. Every factory returns a tool ready to plug into `defineAgent({ tools: { ... } })`.

Apex AI - a friendly agentic coding assistant for the terminal

Installs, migrates, audits, and repairs repo-local agentic development harnesses

Trợ lý lập trình agentic trong terminal (kiểu Claude Code), tiếng Việt, dùng sức mạnh Noob Demon — 3 mô hình flagship (Claude Opus 4.8, GPT-5.5, DeepSeek V4 Pro).

Enterprise agentic SDLC plugin and CLI for OpenCode and Claude-style skill workflows

MCP-first devtools for AI agents.

Agentic UI protocol for Zaby - EdTech Ready

An agentic coding CLI tool — interact with your codebase through natural language

Create a new Ombuto Code project — Agentic Software Engineering Workbench

🚀 Premium Agentic AI CLI with community packs, agent profiles, and interactive slash commands

Multi-LLM orchestration framework with agentic execution, memory/RAG, and training data generation

Agent orchestrator for terminal-based coding agents — discovers installed CLIs, runs them in parallel, ships giant projects in hours

AI agent and MCP server security scanner — discovery, static analysis, supply chain audit, and multi-agent trust analysis

Autonomous coding copilot

Python SDK for mink — sandboxed AI coding agent

Connect your OpenAI agents to Oversee — two lines of code for full observability

Persistent, concurrent-safe project memory for Claude Code agents

Knowledge flywheel MCP server + academic paper research pipeline for Claude Code and VS Code Copilot

StorageOps — S3-compatible object storage diagnostic toolkit. A Pi Coding Agent extension + skill pack.

Three minds, one context — Multi-agent AI orchestrator for Claude Code, Codex, and Antigravity CLI.

AI-powered UI element detection and device automation framework

A simple Spec-Driven Development (SDD) for AI-agent-assisted project workflows.

AI Agent Collaboration System for Creator Life OS - OpenCode plugin

Persistent memory layer for AI agent workflows

ctdovibe — AI agent CLI (fork of Qwen Code)

Multi-harness AI agent configurator. Stateless launcher + project-state mutator (suit up / suit off) — Claude Code, Codex, Gemini, Pi.

Node.js TypeScript CLI for discovering, staging, activating, and wiring reusable AI-agent assets across supported developer hosts.

Document-centered harness engineering toolkit for AI agent development

Cartoon-crepe debugger assistant for the browser — step through your app's runtime behavior with an LLM agent.

Langfuse extension for Pi coding agent

Three-tier memory architecture for OpenCode — distillation, not summarization

LangChain BaseChatModel adapter for @earendil-works/pi-ai — use Pi with any provider, model and auth. Includes a native opencode/Zen chat model (no pi).

Hub Hosted Cockpit のローカル常駐 agent。Hub と outbound WSS で接続し、ローカルの Claude / Codex チャットと tmux セッションを中継する。

Admin/helper/doctor toolbox and local API client for Kaseki diagnostics, setup, and API-backed coding-agent task workflows

AgentLink relay server

Claude Code opened to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models

Compatibility and diagnostics for DeepSeek V4 tool-calling agents.

Persistent evolutionary memory for the Pi coding agent

Aiko Code — your wholesome coding companion~ Fork of Anthropic's aiko Code. 9-phase fractal development loop with Fibonacci parallelism budgets baked in.

Local bridge process that pairs the host's Claude Code or Codex agent with a VoxAgent meeting.

Claudex CLI is a customized Codex CLI that runs locally on your computer.

OpenAI ChatGPT (Codex backend) OAuth auth plugin for opencode - use your ChatGPT Plus/Pro subscription instead of API credits

Soul-driven AI agent with 60+ tools, web search, vision, 12 LLM providers, local web UI, browser/desktop/Android automation, MCP plugins, REST API, Second Brain memory, and multi-channel access (CLI, Telegram, WhatsApp, REST API).

LaunchMyStore universal agent skill (SKILL.md open standard) — works in Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI, Windsurf, Antigravity, Aider, OpenCode, and any other SKILL.md-compatible host. Natural-language router for t

Multi-agent orchestration and Codex governance for OpenCode, Hermes, Grok Build, and OpenClaw

CLI for codeharness — makes autonomous coding agents produce software that actually works

Agent-neutral coordination for AI agents, coding CLIs, LLM APIs, IDE assistants, and custom tools through a local auditable channel — with a built-in local web dashboard (Cordn8 Mantle).

Bosun Autonomous Engineering — manages AI agent executors with failover, extremely powerful workflow builder, and a massive amount of included default workflow templates for autonomous engineering, creates PRs via GitHub/Jira APIs, and sends Telegram noti

Autonomous experiment loop for pi — run, measure, keep or discard. Inspired by karpathy/autoresearch.

A portable multi-agent harness for long-running coding work.

teamrc CLI - sync multi-agent teams across platforms

Premium multi-agent AI coding agent for your terminal — local-first via Ollama, NVIDIA NIM, or any OpenAI-compatible API. Watch the team work in front of you.

Local multi-agent room — coding agents (claude, codex, gemini, cursor, copilot) coordinate live via a shared MCP HTTP daemon.

Autonomous multi-agent coding swarm. One command, infinite commits.

Forge is a powerful open-source multi-agent coding agent for the terminal. Built for speed, cost-efficiency, and full control using DeepSeek models.

The Universal Reasoning Ledger for Agentic Development

Agentic CLI for Lovable.dev — agents in, apps out. Send prompts, verify builds, fix errors, and publish from the terminal.

Ranger brings automated QA to agentic development. The CLI sets up your project so your AI coding agent can verify UI features in a real browser, and your team can review the results on a shared dashboard.

MMCP — Multi-Model Context Protocol. Intelligent AI model routing with MCP server for Claude Desktop & Codex CLI. Auto-routes tasks to Claude, GPT, Gemini, DeepSeek, Llama with RL-based smart routing and cost optimization.

Cognitive-architecture AI coding agent — stateful LangGraph planner-critic loop, multi-tier memory, causal work graph, local-first routing, GitHub integration, eval harness, and plugin SDK

Universal skill library for Claude, ChatGPT, Cursor, Gemini, and VS Code. Install once globally, use everywhere.

Pi extension wrapping Context Hub (@aisuite/chub) for current API and SDK docs.

Visual debugger and observability dashboard for PydanticAI agent pipelines

An open-source agentic coding harness for building and studying AI coding agents

Apohara ContextForge plugin for vLLM V1 — multi-agent KV-cache coordination, JCR Safety Gate (INV-15), RotateKV INT4 hooks, on AMD Instinct MI300X.

Counterfactual replay and causal attribution over LLM-agent trajectories: find which step actually caused a bad outcome by intervening on it.

Run Python code in a MicroPython/WASM sandbox

AI-powered code reviewer and autonomous developer agent

A model-driven approach to building AI agents in just a few lines of code

An automated AI agent powered by Gemini models and more that helps you write software

DrizzyAgent - AI agent plugin for OpenCode

Collet component library documentation — API reference, framework guides, and AI agent setup

Autonomous AI agent memory system with CLAUDE.md protocol enforcement

Semantic TypeScript and JavaScript MCP server for code navigation, workspace intelligence, dependency topology, diagnostics, and refactoring.

Real-time agent-to-agent communication system

Readonly support agent for Xuda Network ambassadors. It can inspect the dev xuda_website CouchDB database through Codex with strict safety limits.

Voice and tone enforcement for user-facing copy

Everything you need to work with a coding agent: install shared policy skills for Claude Code, OpenAI Codex and opencode, and set up portable git security hooks.

pi-coding-agent extension: OpenAI-compatible endpoint support (OpenRouter, NVIDIA NIM, Nous Portal, Ollama, custom)

Local OpenAI-compatible HTTP/SSE server for Claude Code Agent SDK and CLI fallback.

CLI + Claude Code plugin that scaffolds and upgrades AI development harnesses

Initialize Queen Claude autonomous development system with Queen Styles design system enforcement

An AI-powered terminal coding assistant that can search your codebase, create plans, and automatically execute them.