Code agents

Bridge Claude Code to OpenAI and OpenCode Go models — API keys or ChatGPT/Codex-plan OAuth, with prompt caching, auto-compaction, model switching, and a Claude Code binary patcher

Network-tab-style DevTools for LLM calls in Angular apps. See every prompt, response, token, and dollar your app spends — without leaving the browser.

agent-connect — 从手机(钉钉/飞书/…)监控与控制本机多个 coding agent 会话：读写分离、信使寻址分派、写操作人工确认、Web 看板

Keyboard-driven primary-agent model switching for Pi — switch between agent profiles with Alt+Shift+←/→

OpenAI Codex provider for AgentLayer and the AI SDK. It talks to the ChatGPT Codex responses endpoint (`https://chatgpt.com/backend-api/codex/responses`) and supports ChatGPT OAuth/API-key auth through `@humanlayer/agentlayer-provider-auth`. Every factory

Swifty — CLI coding agent

AI-powered pre-commit hooks for repo-specific code quality guardrails.

Multi-provider AI coding agent for the terminal. Like Claude Code, but provider-agnostic with automatic failover.

Local Anthropic API powered by your Claude Max subscription. One subscription, every agent.

Subscription usage/rate-limit command extension for pi-agent (Claude and OpenAI Codex plans).

Terminuz - The Open Source AI Coding Agent

Give text-only pi models vision — describe images with a vision model you pick via an interactive picker, then hand off the text description to non-vision models

OpenAI-compatible streaming model provider for Truss.

konsistent is a CLI tool that enforces structural conventions in TypeScript codebases.

Core auth and in-memory OpenAI-compatible transport for openai-oauth.

`codelayer` is AgentLayer's reference coding agent — a multi-provider CLI (`@humanlayer/codelayer`) built on `agentlayer-core` and `agentlayer-filesystem`. It wires a `LanguageModel` (Anthropic, OpenAI, Codex, Copilot, or Fireworks/"firepass") to a filesy

The open backend for AI agents

社交关系AI管家 - 独立 CLI 工具。自动追踪社交关系，帮你拟消息、记待办、维护人脉。v3.0 起支持多 LLM provider（Claude/OpenAI/MiniMax）。

Badgr — run or serve GPU workloads from one command

Provider-neutral second-brain runtime and contract helpers for human and agent operators.

Agent cli for coding and more.

Remnic memory plugin for Codex CLI — hooks, skills, MCP integration

A super basic Pi extension that toggles GPT-5.4 / GPT-5.5 / GPT-5.6 Fast mode with /fast (the default 'priority'), nothing else - one file.

Self-evolving coding agent workflows for pi

Responses-compatible API bridge for Cursor Agent CLI

MCP SSH Manager: Model Context Protocol server for SSH remote server management. Control SSH connections from Claude Code and OpenAI Codex - execute commands, transfer files, database operations, backups, health monitoring, and DevOps automation. NEW: Too

Advanced n8n AI Agent node for Claude, OpenAI & Gemini — native PDF/image vision, Claude Max (Claude Code OAuth) support, Anthropic prompt caching, structured output with auto-fix, fallback models, and on-demand document fetch.

Autonomous coding agent CLI - capable of creating/editing files, running commands, using the browser, and more

Node.js runtime adapters, workspace management, config, auth, and plugin support for afk-dev.

Turn local coding-agent token usage into a satirical resource receipt and evolving mutation chronicle.

ConvoZen agent skills — install into Claude Code, Codex, Cursor, Gemini CLI and any agent that supports the Agent Skills spec

OpenCode plugin for auto-discovery of OpenAI-compatible models with dynamic provider configuration

Native macOS/Linux/Windows runner for the Donna orchestrator. Connects a developer machine to a Donna server and executes spec/plan/implement/verify/review stages locally.

Codex CLI for medical domain agents (fork of OpenAI Codex CLI).

Local autonomous agent control plane for software development

A quiet back-channel for long autonomous agent runs — tails Claude Code / Codex transcripts and gives you a multilingual Q&A thread about each session.

Autonomous agent team: role-specialized coding agents that propose typed work into Linear or Jira, gate material changes behind human-approved PRDs, and drain approved work into PRs — running on your machine against your Claude subscription.

***The workflow engine for traceable autonomous job execution***

Model-agnostic AI coding agent for your terminal — chat, autonomous agent mode, semantic codebase search, and MCP, with any OpenAI-compatible API, local or cloud.

Opt-in spending guardrails and a transparent, self-directed convenience fee for autonomous agent wallets in the Eliza framework. No fees by default; no hardcoded fee recipient.

Internal component of Sutra SDK — applications should install sutra-sdk. The Edge Harness. Offline-first autonomous agent runtime for local SLMs (Phi-3, Gemma, quantized GGUF/ONNX) with durable friction telemetry and on-device vector memory.

终端编码 agent:LLM + tool-call 循环 + 流式输出(含思考)+ 16 个工具,接任意 OpenAI 兼容后端。

AutoAIDev CLI — autonomous AI task loop with VS Code / Cursor launcher

🎨 Comprehensive DESIGN.md token spec system for AI agents — author, validate, export, and integrate Google DESIGN.md design tokens with 60+ autonomous agent tools. WCAG contrast checking, Tailwind/DTCG export, multi-agent compatibility, and viral-ready d

Jira adapter for the @llodev/pm-tasks-* family. Use when the user mentions Jira or Atlassian, asks to create a Jira issue, publish to Jira, post to Jira, transition a ticket, add a comment in Jira, or uses --publish-jira; OR for CRUD on existing issues (c

Scios autonomous scientific research plugin for Google Antigravity, Cline, Claude Code, and other coding agents

Quay — Autonomous AI Software Factory. Self-hosted AI agents, MCP integration, customizable pipelines, real-time Mission Control dashboard, cost transparency, and full audit trails.

Aerin your open-source coding agent

Open Source Gantry — vendor-neutral GXT substrate and Gantry CLI for local git-native agent governance

Turn Claude Code (or any headless CLI agent) into a local, human-approved customer-acquisition system: ICP interview, market research, SQLite prospect CRM, drafted outreach sequences you approve before anything sends over SMTP. No hosted CRM, no cloud dat

Autonomous QA for iOS + web. Your coding agent gets hands, eyes, and judgment: drive the app, explore it with no test code, and get a deterministic ship/no-ship verdict with evidence. iOS simulator native; web beta via Playwright.

Autonomous Node.js CLI and offline demos for HandoffKit.

All-in-one multi-agent orchestration for the Pi coding agent — parallel teammate dispatch, goals, plans, knowledge system, MCP/LSP/browser, and cockpit visualization in a single install

Orchestration spine for long-running pi development

Framework for agent-native application development — where AI agents and UI share SQL state, actions, and context

Fire-and-forget goal mode for Pi with visual planning, autonomous recovery, evidence, and independent completion audit.

Autonomous Multi-Agent AI Workspace in your terminal. Codes, researches, and executes real tasks with 40+ tools and 280+ skills

Autohand Code Agent SDK - CLI wrapper implementation

[BETA] Codex-style /usage status + autonomous coding harness for pi. Not production ready — expect breaking changes.

Multi-agent orchestration framework for AI-powered application generation — 28 specialized agents with shared memory, token optimization, and usage dashboard

Give an AI agent a real Chrome to drive, over MCP — browse, read, extract, and act on any page, getting through Cloudflare and sites that block headless/Playwright, with no automation fingerprint on reads.

reddb.io dev plugin - engineering skills for code agents (autonomous /afk loop, /go dispatch, triage, tdd, diagnose, graph-aware codebase understanding, ...)

Catalog of multi-agent development architecture patterns - design write-ups plus drop-in scaffolding (agents, slash commands, workflows, templates).

AutoDev — Autonomous Engineering Team. DevTeam in a Box. Runs on pi.

KALAI CLI — terminal-first AI coding agent

Install gspec specification commands for Claude Code, Cursor, and other AI tools

Core knowledge and workflows for AI agents developing or integrating with the TECHSHAN-IMS ecosystem.

Unified WeClawBot device, audio/voice, display, and VM app management CLI.

Ryker Multi-Agent Tech v1.0.0 — Enterprise Autonomous AI Agent Operating System (ELITE-NEXUS v2 Architecture)

AI assistant status monitor

ExecBro: React Native AI debugger and devtools MCP server. Gives AI agents eyes and hands in your running app (logs, network, state inspection, tap, screenshot).

Make your project Cendor-ready and Cendor-fluent for your AI assistant in one step — writes assistant rules files, optional MCP config, and a correct starter, plus a `doctor` that catches wiring mistakes. Offline, no key, no network.

Vibe Coding Tracker - AI coding assistant telemetry/usage parser, aggregate JSONL events into CodeAnalysis results

PKA — FREE-only AI CLI (Gemini · Groq · OpenRouter free models)

Policy-as-code authorization for AI SDK tool calls, powered by [Open Policy Agent](https://www.openpolicyagent.org/).

Run an AI SDK `HarnessAgent` (Claude Code, Codex, Pi) as a **durable workflow** using the [Workflow DevKit](https://www.npmjs.com/package/workflow). A turn can be divided into time slices or semantic agent steps.

Connects your own AI agent (Claude Code or Codex) to a live MockFlow board open in the browser. The agent is the brain, the browser tab is the hands, the bridge is the nervous system between them.

Toolkit for building ESLint plugins in TypeScript — AST helpers, type utilities, rule-creation scaffolding, security benchmarks, and SARIF output.

Small helpers for developing apps.

The **QuiverAI provider** for the [AI SDK](https://ai-sdk.dev/docs) adds image generation support for the [QuiverAI](https://quiver.ai/) API. QuiverAI generates SVG documents from text prompts and can also vectorize raster images.

Active state management for multi-agent coding: a shared, versioned project brain over MCP.

Multi-agent PR review orchestrator CLI

Multi-agent orchestration protocol for software development

Run durable, schema-enforced, resumable multi-agent workflows with Codex.

Multi-agent orchestration for OpenCode — 14 specialized agents, TDD, Themis review gates.

Multi-agent SDLC Orchestration System with Global Hooks for OpenCode Desktop

Deterministic multi-agent workflows powered by Codex App Server

Multi-agent round-robin debate plugin for OpenCode

Multi-agent command center for AI coding agents — from your phone, tablet, or any browser.

NERVous System — durable multi-agent orchestration, coding-agent coordination, and workflow recovery for pi.

ZERO Code - Multi-Agent AI Coding Platform

Multi-Agent AI Coding Assistant with ECHO Protocol

FlowDeck — production-grade multi-agent orchestration, governance, CI repair, and code intelligence for OpenCode

Kyo-so: MCP-native, ACP-powered multi-agent review gates for AI coding workflows.

TokenRing One — complete local-first multi-agent AI workspace

Ryker Multi-Agent Tech v1.0.0 — Enterprise Autonomous AI Agent Operating System (ELITE-NEXUS v2 Architecture)

Pi extension for reusable multi-agent workflows and CodeRabbit-style code audit. Built on pi-subagents + pi-dynamic-workflows.

Vibe Assembly: multi-agent Roo Code workspace template for free-tier vibe coding.

Assemble SDK for building and running multi-agent workflows

Schedulability compiler for multi-agent development: observe real code boundaries, refactor the conflicting seam, recompile the plan for parallel execution