Code agents

Angles Code CLI — terminal agentic coding assistant in one static Rust binary. Drives 30+ angles- tools over files, dirs, terminal, Git and web, switching 11 model providers at will.

Codex Skin review: compare features, pricing, use cases, access model, and alternatives for this Desktop AI Agents agent in 2026. Theme and skin manager for the Codex desktop AI agent

CLI to install, update, and manage modular AI agent skills for Wangs UI React applications

Local-first coordination for independently opened AI agent sessions.

AI agent that streams JavaScript into a persistent sandboxed Node.js runtime

Upload local AI agent sessions to turns.dev

Local A2A gateway for waking AI agent runtimes

Audit and prune unused AI agent skills, MCP servers, hooks, and agents

Server-side analytics for AI agent traffic

Audit AI agent skills folders for problems that fail silently

Standalone, multi-provider AI agent tools library in plain JavaScript

NewBeeDebugBridge 工程师端 CLI —— 远程运维(截图/执行/读文件)，对 LLM Agent 友好。

Typed framework for durable LLM agents: pipeline builder, FSM engine, durable checkpoints, and adapters for headless CLI providers (Claude Code, Codex CLI)

Robodev server SDK — defineDatabase, defineApi, defineMcpTool, defineMcp, defineJob, defineSocket, defineAuthHook, auth, email, llm, agent, storage, pdf, push, and the injected Drizzle db

Runtime CSS probe — inspect layout, colors, backgrounds, fonts and more in a live browser. AI agents and shell automation.

High-performance zero-dependency static analysis tool enforcing NASA Power of Ten rules across 20 programming languages, plus AI agent skill, MCP server config, prompt template, and LLM model security auditing.

Agent-driven proactive memory CLI for AI agents — autonomously recall, maintain, and evolve persistent, source-grounded knowledge across sessions.

Production patterns for AI agent orchestrators — tool-calling loops, multi-stage pipelines with checkpoints, LLM provider routing with fallback, four-layer memory with confidence decay — plus the wallet side of reselling LLM access. This package is the in

Pi extension that uses Claude Code (via Agent SDK) as a model provider and adds an AskClaude tool.

Connect this machine to Ensemble — runs the local agent runner and wires the ensemble session messaging so your coding sessions talk (per-org, isolated).

LangChain / LangGraph adapter for the GraphMind live agent debugger: a callback handler that streams the run tree as a live graph, plus tool wrappers that honour pause / step / inject / retry / abort gates.

<p align="center"> <h1 align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://pullfrog.com/frog-white-200px.png"> <img src="https://pullfrog.com/frog-green-200px.png" width="25px" align="center" alt="Green

Kritya — a lean, provider-agnostic terminal coding agent (NVIDIA, OpenAI, OpenRouter, Groq, Ollama, and more)

Anima Agent Development Kit - Framework for building production-grade multi-agent AI systems

Agent-safe CLI and skill for purchasing, renewing, and managing WarpMetal VPS servers

Harness-agnostic agent execution engine: run Claude Code, Codex (SDK/CLI + app-server), and any ACP agent behind one interface with a normalized event stream, multi-turn sessions, and resume. Root export is the wire contract; /core, /server, /client are t

Proactive semantic memory and mid-run steering for the Pi coding agent

Maintained, extension-first Pi coding agent with built-in workflows, subagents, web research, questions, skills, and an enhanced terminal UI.

STT orchestrator + bundled OpenAI-compatible STT provider for the Pi coding agent + @llblab/pi-telegram bridge. Wraps the inbound voice/audio pipeline (downloads voice notes, runs STT via the in-package OpenAI client, sends a 🎙️ echo to the user, and fee

Web Endpoint as PI Package for PI Agent (pi.dev), with Ollama API and OpenAI API compability.

GitNexus-native coding agent CLI

A2A (Agent-to-Agent) protocol wrapper for OpenAI Codex SDK. Drop a JSON config file in, get a fully-spec-compliant A2A server out. Supports repository sandboxing, MCP tools, streaming sideband events, and multi-agent delegation.

XENO-owned ACP agent-side stdio endpoint with fixture and approval-gated local provider adapters. NOT official Codex/Claude/Gemini/OpenCode ACP.

Kinetically Orchestrated Neural Execution Engine for Code

Zero-dependency AI chaining and autonomous agent framework utilizing device resources for Node.js ESM and Android Termux

Run autonomous agent cities: one chair seat, role-aware repo agents, repo-owned skills, and explicit roads.

Standalone autonomous agent fleet with Symphony orchestration, claim protocols, and continuous improvement loops

◆ Namo Studio — Your AI builder for code, projects, and development tasks. AI CLI agent dengan FreeModel (AI gratis), streaming chat, autonomous agent dengan diff preview, dan memory system.

Give an autonomous agent a real email address, a webhook URL, durable memory, and the ability to wait for an event without burning tokens. Paid per call in USDC over x402.

Superpowers skills library (TDD, debugging, collaboration workflows) as an MCP server for VSCode and Antigravity

PIKAA CLI - AI coding agent that runs locally in your terminal.

Ultra-fast, terminal-native AI coding assistant and agent built for Android Termux, Windows, macOS, and Linux.

Connect Claude Code, Codex, OpenCode, Gemini CLI, or Qwen Code to an OpenVisio team — MCP tools + optional autonomy — in one command.

The Local-First Spatial Audit & Surgical Revert Layer for Autonomous AI Agents

AI coding agent powered by DeepSeek via browser automation — no API key needed. HTTP API only mode - accept tasks via port 9527. Simplified and optimized for remote task submission.

Agent-Proof Mechanical Hard-Gate CLI for deterministic AI code governance

RedDB's AI coding agent for the terminal

Claude Code-style auto mode guardrail for pi.

Autonomous browser testing engine & MCP toolset for AI coding agents

The **[MiniMax provider](https://ai-sdk.dev/providers/ai-sdk-providers/minimax)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the [MiniMax](https://www.minimax.io/) platform, including the MiniMax-M model series.

Ably transport and codecs for building AI applications with Ably.

Titanium SDK skills and agents for AI coding assistants, including native game and sound synthesis modules

A Vercel AI SDK-compliant agent backed by Coder Agents, Coder's server-side agent runtime. `new CoderAgent()` returns a real AI SDK Agent (generate/stream).

Claude Code / Cursor skill for integrating Waffo Payment SDK (Node.js / Java / Go / Python / PHP)

Pi coding-agent runtime adapter for assistant-ui

CLI for OpenUI — scaffold generative UI chat apps, mint Gateway API keys, and generate LLM system prompts from component libraries, and deploy projects

Local observability dashboard for Codex and Claude Code multi-agent workflows

Radix Autonomous Multi-Agent Software Engineering CLI

Agent Experience for a repository: worktrees, sessions, and multi-agent orchestration.

Portable multi-agent engineering pipeline runtime

Pantheon-style multi-agent orchestration for pi, inspired by oh-my-opencode-slim

Socratic AI Terminal Coding Assistant & Multi-Agent Orchestrator

Strategic roadmap planning and multi-agent coordination for OpenCode

radcode — Rust AI development framework CLI: setup wizard (config.db + encrypted secrets vault), TUI, REPL, multi-agent dispatch, MCP brain.

Hands-off multi-agent GROUP CLI — coding first, optional email/X/Supabase — JagX & JRILICENSE

Codex Multi-Agent V2-style hierarchical subagents for Pi

Initialize Herdr multi-agent workflow projects — zero-collision AI orchestration by Plogr

神治（Thearchy）— deterministic multi-agent quality governance for coding agents.

Open-source multi-agent orchestration harness for OpenCode with specialized agents, durable workflows, review gates, and reproducible software-engineering processes.

Supervisor-led multi-Agent orchestration for Pi with durable workflows, quality gates, and observable subagents

Next-generation multi-agent harness with 6 specialized agents, presets, security guardrails, and audit trail

Pi extension for autonomous software engineering — structured discovery, ADR-driven design, and multi-agent implementation from idea to PR.

Multi-agent Skill installer and governed runtime adapter for Product OS 1.0.0.

Interactive multi-agent orchestration, messaging, and live sessions for the Pi Coding Agent

Autonomous multi-agent GitHub issue orchestrator powered by Claude CLI, git worktrees, DAG scheduling, and 5h rolling quota management

Inove AI Framework - Multi-Agent AI Development Kit

Governed multi-agent orchestration, map-reduce, and real-time status for Pi

Public TypeScript agent SDK for Matilda — agent lifecycle, streaming, client tool execution, and multi-agent composition on top of the Matilda API.

Dependency-free TypeScript multi-agent crew orchestration for Codex, Claude Code, OpenCode, and Antigravity.

Local multi-agent coding orchestrator with TDD, SonarQube, and code review pipeline

Minimal AI coding agent with multi-agent cluster — stripped, independent, research-grade

Coding Agents Team Management System — Trackers + CAMS RAG workflow scaffolding for multi-agent AI coding teams

Observable multi-agent orchestration for Pi: autonomous subagents, isolated worktrees, swarms, schedules, handoffs, and a live operator dashboard.

A portable, dynamic multi-agents workflow system for complex codebases. Reads cc-switch config, selects the right agent architecture (loop / orchestrator-workers / multi-agent / graph / dynamic / ultracode), generates per-agent configs, enforces cost-rate

HiveMind — Runtime composition engine for multi-agent orchestration, session continuity, and compounding intelligence in OpenCode

GPT-first durable workflow relay with audited decisions and multi-agent executors

Scaffold an agent plugin (multi-agent installer, MCP tools, hooks) from a battle-tested template — 22 agent targets in minutes.

Evolve SDLC CLI — Multi-Agent Architecture Lifecycle & Governance Tool for AI Coding Agents

PI-based agent framework — sessions, permissions, tools, runner, events (OpenCode-style).

TopCode — next-generation CLI agent framework (State-Manifold paradigm)

CLI that automates the initial setup of Coderium Agent Framework (CAF) in any repo

MCP server and framework adapters for Corsair. Expose 200+ integrations to any agent framework (Mastra, LangChain, LlamaIndex, OpenAI, Vercel AI, Claude) as tools.

An npx-executable, agentic TDD pipeline orchestration tool — 8-pass state machine for enterprise software development

MCP server serving agentic-context standards, playbooks, and conventions on demand, fetched over HTTPS with in-memory caching

An agentic coding terminal you can also drive from a web page.

Agentic AI vibe coding CLI with free model support

Agentic delivery workflows for GitCode and CodeArts-to-GitCode Actions migration

AI profiles shared across agentic harnesses

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches