Code agents

ACP-compatible coding agent using OpenAI-compatible relay APIs

Ralph Wiggum technique for iterative AI development loops with multi-agent support

Opinionated Pi package with web search, review workflows, sandboxing, memory, usage reporting, skills, and a theme

Prave CLI — discover, install, version, test, and ship Claude Skills. The developer platform for the complete Skill lifecycle.

proto - AI-powered coding agent

Nori AI CLI - An AI-powered coding assistant

A terminal coding harness agent for OpenAI Codex OAuth.

One CLI for all your AI coding agents - versions, config, cloud dispatch, sessions, and teams (now with first-class Grok Build CLI support)

<p align="center"><code>npm i -g @agent-lite/codex</code></p> <p align="center"><strong>Codex CLI</strong> is a local coding assistant maintained by Agent Lite. </br> For more information, visit https://agent-lite.com</p>

Keep your AI agents on a leash. Real-time spending limits in 3 lines of code.

SWT3 AI Witness SDK: cryptographic attestation for AI inference. 103 procedures, 52 namespaces, 7 languages, 18 profiles. EU AI Act, NIST AI RMF, CMMC, SR 11-7.

Fresh-context iterative loops for Claude Code — autonomous task completion with independent verification

AI coding session orchestration dashboard — launch, monitor, and manage Claude Code & OpenAI Codex sessions from a web UI

agentic coding in 30 loc. a loop, two tools, and an llm.

BYOK fork of the Codebuff CLI. Bring your own provider key (OpenAI, Anthropic, OpenRouter, OpenCode Zen/Go, custom OpenAI-compat). No codebuff.com account required.

Recursive Language Model (RLM) implementation using the Vercel AI SDK. Process long contexts through iterative code execution and sub-LLM queries.

OpenCode plugin that connects Cursor's API to OpenCode via OAuth, model discovery, and a local OpenAI-compatible proxy.

Per-key budget caps for AI agents. Local proxy enforces hard spend limits on API keys. Scans your tools, tracks costs, blocks when over budget.

minimal local-first coding agent focused on small local models

GitHub Copilot, OpenAI Codex, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.

A PM for your AI coding agents. Delegate, orchestrate, and audit Claude Code, Codex, Aider, OpenCode, Gemini, and any user-configured CLI agent from one local web UI — every AI action traced, every file scored, every spawn warmed with project memory.

<p align="center"><code>npm i -g @openai/codex</code><br />or <code>brew install --cask codex</code></p> <p align="center"><strong>Codex CLI</strong> is a coding agent from OpenAI that runs locally on your computer. <p align="center"> <img src="https://

Minimal AI coding agent with tool use, MCP, and skills support

Pi Coding Agent extension package for model routing, tools, background tasks, and safety hooks.

ACP to OpenAI protocol conversion gateway - expose ACP agents as OpenAI-compatible API endpoints

Autonomous agent orchestration for OpenCode.

> Version: **0.10.3** — persistent autonomous agent harness for [Reactive Agents](https://docs.reactiveagents.dev/).

Archon — autonomous agent that performs thorough security audits on your codebase, part of Vigolium

LangSmith-native autonomous agent optimization for Claude Code

Linear-orchestrated autonomous agent system

Autonomous Agent Fleet Management for Claude Code

A general-purpose, self-evolving autonomous agent OS with persistent memory across sessions

Autonomous Agent Development Orchestrator - Multi-agent TDD pipeline powered by Claude

AI-powered autonomous agent for Roblox Studio development. Real-time WebSocket bridge, persistent memory, and intelligent tool use.

Claude Code-style CLI for autonomous agent workflows powered by 0G, ENS, and Gensyn AXL.

Local-first deterministic CLI that scores whether an issue, spec, or decision artifact is ready for autonomous agent work. No LLM calls, no hosted backend.

Run Claude Code as an autonomous agent in Docker containers with git integration

Ralph Wiggum autonomous agent loop - TypeScript implementation

Autonomous agent that runs projects, explores them, captures screenshots, and records demo videos automatically

Autonomous agent runtime for the Deva platform — self-improving, self-replicating, sovereign AI agents

Autonomous agent control panel powered by Claude Code — orchestrate AI tasks, triggers, workflows, and skills from anywhere

Autonomous Agent Development Orchestrator - Multi-agent TDD pipeline powered by Claude

Autonomous agent pipeline — type `legend` in any repo

A CLI executor for the autonomous agent.

Claude Code autonomous agent manager - A web UI for managing Claude Code agents

uAAL — Universal Autonomous Agent Language VM. Stack-based bytecode execution engine for the uAA2++ 7-Phase Protocol.

Run Claude Code as an autonomous agent in Docker & Podman containers

VCR Protocol SDK — Policy-bound autonomous agent wallets with on-chain verification, ENS integration, x402 payments, and BitGo enforcement.

One CLI + one autonomous agent that does everything: coding, orchestration, tools, memory, security, and more.

Evoxiv autonomous-agent daemon. Runs on user hardware, claims tasks from the control plane, executes Stories via Claude/Codex.

FISHI — Your AI Dev Team That Actually Ships. Autonomous agent framework for Claude Code.

Scaffold a Notion-integrated autonomous agent workflow for Claude Code, Gemini CLI, or GitHub Copilot with MCP verification

AI-powered game development CLI with local LLM, 45+ tools, autonomous agent mode, and 50+ slash commands

Autonomous agent execution for feature specs — break specs into agent roles, run them in phased pipelines with coding agents

Solana devnet agentic wallet CLI — create wallets, sign transactions, transfer SOL/SPL tokens, and run autonomous agent flows. Built for AI agents.

Confucius Agent - Ralph Protocol v3 + Browser QA MCP Server with AI agent focusing system (ESLint strict mode). Autonomous agent scaffold with visual QA, accessibility testing, and typo/linting prevention.

Autonomous agent platform — Manus-class task execution, research, code generation, browser automation

AI planning CLI and autonomous agent orchestration for beans-based coding workflows

Autonomous AI task loop: reads TODO.md, sends tasks to Claude CLI, Copilot CLI, or OpenCode, tracks progress, supports session resume, Discord, and webhooks

Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base

An autonomous agent system that uses Claude Code to incrementally build projects from a PRD.

Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.

MCP-compliant agentic control framework with 83+ tools for Claude Code and autonomous agent development

Autonomous-agent CLI + TypeScript SDK for claws.software. Self-registers an Ed25519 identity, mints UCANs, signs RFC 9421 HTTP requests, and calls the MCP server. Designed to be invoked by LLM-driven agents (Hermes, Claude Code, Cursor) following an opera

A local-first agentic system wrapping Ollama's API, borrowing architectural patterns from the Claude Code paper

Enterprise architecture guardrail and AI autonomous agent orchestrator

Official CLI for CareerVivid — AI voice interviews, autonomous job applications, resume editing, and portfolio publishing from your terminal

Local-first AI engineering, visual generation, long-video production, memory, tools, and mobile automation in one command-line workspace.

Enterprise-grade Pull Request automation toolkit with AI-powered code review and description enhancement

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

Unstable - PR - Run Claude Code as an autonomous agent in Docker containers with git integration

Pi extension for coordinated AI teams, workflows, worktrees, and async task orchestration

AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop

The most powerful AI agent orchestration harness — 380+ MCP tools, 223 agent types, self-learning HNSW memory, A2A protocol, streaming, event triggers, process supervision, 8 LLM providers, interactive settings, zero-config swarms

Free Agent MCP - Portable, workspace-agnostic code generation using FREE models (Ollama)

Security by design CLI for AI-assisted development - scans projects and guards autonomous agent runs

Kody ADE — the free, autonomous development engine. Issue to tested, reviewed PR.

Paean AI CLI - Claude Code-like AI agent with local MCP integration, task management, and autonomous worker mode

Zerg Terminal Client - CLI agent for continual AI systems

MIND MCP Server — 28 tools. The most complete AI memory layer with the Focus → Project → Outcome → Task hierarchy (mind_focuses + extended mind_life with item_type/parent_id/focus_id and cross-account project sharing via share/list_shares/revoke_share), d

Autonomous PLAN.md execution loop for Pi that continues until all checklist items are complete.

Master Orchestrator for Pi Agent with skill-based autonomous development

Substrate — multi-agent orchestration daemon for AI coding agents

Conductor plugin for OpenCode

PikaKit FAANG-Grade AI Operating System — Install 52 skills, 19 workflows.

Autonomous recursive self-improvement engine for OpenCode and Hermes Agent. Subagent-first iteration loop with mechanical verification.

MCP-compliant agentic control framework with 80+ tools for Claude Code and autonomous agent development

El primer ingeniero QA Autónomo integrado al CI/CD. Creado por Arcadial.

Loki Mode by Autonomi. Autonomous spec-to-product system: takes a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief to a deployed app via the RARV-C closure loop with 8 quality gates. Provider-agnostic (Claude Code, OpenAI Codex, Cline, Aider).

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

Developer demo CLI for AI coding agents — record, edit, and export polished product demos from terminal

Learning system for Claude Code — avoids repeating mistakes across sessions

Pi-native ralph loop — autonomous coding iterations with mid-turn supervision

The most powerful open-source AI coding agent for the terminal. Goal-driven autonomous loops, side-channel conversations, pre-flight advisor workers, multi-agent swarms, adaptive skills, full-diff file rendering, and MCP with OAuth.

Scaffold a Claude Code environment (agents, standards, templates) for autonomous AI-driven development

kody — autonomous development engine. Single-session Claude Code agent behind a generic executor + declarative implementation profiles.

A minimal, public domain AI CLI agent compatible with OpenCode's JSON interface. Bun-only runtime.

A structured, AI-assisted development framework for coding agents

Agentuity Open Code plugin with specialized AI coding agents

Autonomous development toolkit for AI agents - screenshots, DOM queries, console logs, and JavaScript execution via WebSocket and Chrome DevTools Protocol