Code agents

CLI para gerar Custom Agents (VS Code + GitHub Copilot Chat) em qualquer projeto.

Monty-backed Python REPL middleware for Deep Agents, with a shared filesystem between the sandbox and the agent's file tools.

Flake8 plugin for detecting static-analysis escape hatches in Python code

Local AI coding agent — Ollama + any model

Catch AI code hallucinations before they ship. The linter for AI-generated imports.

Python SDK for Codex

AI agent framework for data analysis — write and execute Python code to answer questions about data

Local RAG indexer and MCP server for AI coding agents (Claude, GPT, Gemini, Cursor, Factory Droid, and more).

Thin AI agent harness — self-evolving, Claude Code-style memory

AI code/PR review agent. Fetches a pull request, asks an LLM to review it, posts inline comments + summary verdict back to the VCS. Self-hosted, multi-VCS (GitHub, GitLab, Bitbucket, Azure DevOps), multi-LLM (Anthropic / OpenAI / Google / Claude Code / Ollama). Standalone: no inter-package runtime deps.

Aider review: compare features, pricing, use cases, access model, and alternatives for this Coding Assistant agent in 2026. AI pair programming tool for terminal-based code editing with LLMs.

Kiro AI review: compare features, pricing, use cases, access model, and alternatives for this Code Generation agent in 2026. The revolutionary AI-powered IDE that transforms coding from concept to production.

AI automates Salesforce testing with no code and zero maintenance.

Build AI agents and chatbots easily with no code.

Smolagents: Easily build smart AI agents that write and run code.

Run any AI model on any device, fast, private, and offline.

Build React apps 10x faster with AI, design, and code in one place.

Tabby is an open-source AI coding assistant that helps you code faster.

WebsitePublisher.ai lets you create full websites just by telling your existing AI assistant what you want. No technical skills, coding, or learning new softwar

Automate your business calls with an AI phone agent, no coding needed.

Build custom AI agents fast, without coding or complex setup.

Tusk AI creates and updates code tests automatically for faster shipping.

Automate business campaigns with AI Agents. No coding needed.

Chat with your data. Get instant answers and insights, no code needed.

Automate any online task with AI, no coding needed. Just tell it what to do.

Analyze data with simple chat, generating code for you.

Build AI agents to automate business tasks, code-free and fast.

Bootstrap any project with AI-agent-ready documentation and conventions. Run once, let the AI do the rest.

Autonomous Local AI Agent. Vibe Coding v1.0.

Rich-like console rendering library for TypeScript with streaming support for AI agent responses

Manage persistent AI agent sessions with tmux

CLI for aix - unified AI agent configuration

MCP server for Brime — live web search, URL extract, and multi-round research for any LLM agent (Claude Desktop, Cursor, Claude Code, Codex, VS Code).

Secure local control plane for AI coding agents across supported MCP clients, with workspace-scoped remote access, approval gates, durable jobs, sessions, and audit receipts.

Agent Skills (Claude Code, Codex CLI): build, extend, validate, rebuild, fix, and join LLM wikis from any knowledge corpus. Token-efficient retrieval via hierarchical indices, DAG parents, and deterministic rewrite operators.

Utility commands and tools for Pi coding agent — lifecycle, diagnostics, cache, analytics, display, batch execution

AI coding agent

Stable wrapper for Whalent Agent core runtime

Cawdex — terminal coding agents with a mind for the whole repo. Speaks any OpenAI-compatible API with repo-aware context, benchmark tracing, MemPalace memory, and terminal-first agent workflows.

Use your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, the Agent SDK, your scripts — at subscription pricing, not per-token API bills. One local Anthropic + OpenAI-compatible endpoint.

Agent Connect command line — bridges Telegram Forum topics to Claude Code / Codex sessions in tmux

❄️ AI-Powered Development CLI with Interactive REPL

Professional Agentic SEO Platform for Google Antigravity 2 AI Agent — 44 specialized skills covering technical audit, E-E-A-T, schema, GEO, local SEO & more

Linear-driven orchestrator + scaffolder for coding agents on Sandcastle. `runway init` scaffolds a target repo (sandcastle + varlock + 1Password); `runway run` drains a Linear queue against it; `runway doctor`, `runway upgrade`, `runway upgrade-repo` roun

AI-assisted novel writing workflow for Claude Code, Gemini CLI, OpenCode, and Codex CLI

Local-first compiler for Claude Code rules, skills, loops, and multi-agent workflows

GitHub-native local runner for multi-agent coding workflows.

A kanban board + multi-agent (Claude + Codex) ops/dev harness: routing, pre-deploy gates, incident playbooks, 24h monitoring, Telegram Ops Thread mirror.

The runtime layer for Agentic AI. 108 MCP tools: persistent memory, autonomous agents, vault storage, scheduled workflows, DeFi execution on Base, deep research, and Noel Shell tool calling (estimate + execute swaps) — works in Claude Code, Cursor, Windsu

Base entry point for VortEX — a Multi-Agent Personal AI Work OS framework

Multi-agent development orchestration system for terminal-native vibe coding

Framework-agnostic widget shell for agent-devtools — closed Shadow DOM mount, composer, picker overlay, SSE transport

> **Experimental** — Flue is under active development. APIs may change. > > Looking for `v0.0.x`? [See here.](https://github.com/withastro/flue/tree/v0.0.x)

> **Experimental** — Flue is under active development. APIs may change. > > Looking for `v0.0.x`? [See here.](https://github.com/withastro/flue/tree/v0.0.x)

A multi-agent framework for Claude Code

Agent Content Watermark MCP — dedicated EU AI Act Article 50(2) GenAI watermarking. Visible + invisible + perceptual layers per the Code of Practice (2 Nov 2026 cliff). C2PA manifest envelope. By MEOK AI Labs.

Deterministic record-and-replay debugger for AI agent runs

Read-only linter for .claude/ and CLAUDE.md — measures token budget and audits agent/skill quality.

Multi-agent toolkit for analyzing and managing Google Analytics 4 properties. Works with Claude Code, Codex, and Gemini CLI.

Offline Expert Agent — local RAG, agent mode, plugins, privacy-first

Multi-agent code review system using LangGraph

Reserved package name; project under development.

A discreet, zero-dependency message bus that lets terminal AI agents (Claude Code, Codex, Grok, Aider...) talk to each other over tmux — via readable markdown threads + a doorbell.

Windsurf Editor review: compare features, pricing, use cases, access model, and alternatives for this Agentic IDE agent in 2026. AI-powered IDE that keeps developers in the flow state.

AgentLed review: compare features, pricing, use cases, access model, and alternatives for this Operations AI Agents agent in 2026. Transform Your Business with AI-Agents Collaboration in seconds. No Coding Required.

Extract web data by chatting with AI. No coding needed.

AppWizzy is an AI tool that helps you build and host full-stack web applications just by describing them. It gives you a real development environment with your

Build, debug, and deploy reliable AI agents with full visibility.

Ruflo - Enterprise AI agent orchestration for Claude Code. Deploy 60+ specialized agents in coordinated swarms with self-learning, fault-tolerant consensus, vector memory, and MCP integration

Autonomous AI agent runtime — TypeScript + SQLite + React

Unified MCP pipeline for recommend-page filtering and screening on Boss Zhipin

Cawdex — terminal coding agents with a mind for the whole repo. Speaks any OpenAI-compatible API with repo-aware context, benchmark tracing, MemPalace memory, and terminal-first agent workflows.

Agent Skills code-review harness (Claude Code, Codex CLI): wiki-organised corpus of ~476 specialist reviewer leaves selected by semantic tree descent against the diff, aggregated into an 8-gate GO/NO-GO release verdict.

Use Codex CLI with any OpenAI-compatible API provider. No OpenAI account needed. No fork needed.

TypeScript CLI for the chump coding assistant

Pi extension package for Feature Factory tool-orchestrated phase delegation

Hover's local Node service: agent invocation, Playwright CDP preflight, WebSocket bridge.

AI coding agent powered by Yiyan (文心一言) via browser automation (chat.baidu.com) — no API key needed. Performance-optimized. Enhanced with comprehensive security.

Autonomous desktop AI coding agent. Alternative to Claude Code, Cursor, Copilot. Runs locally, no per-token billing. $10 / 3 months on the whitelist · tsunamicli.nexworldtech.com

Your AI forgets everything between sessions. cachly fixes that permanently. Persistent memory + causal root-cause analysis for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, git commit, and CI run automatically. Arrives pre-briefed. P

Budget-Aware Multi-Agent Coding Harness for git-native worktrees

A multi-agent orchestration framework for AI-assisted software engineering workflows.

Multi-agent parallel code/spec review for OpenCode

iTeam client — CLI + agent daemon for the local-first multi-agent collaboration workspace

CLI for running PillowCouncil's multi-agent decision board locally.

Framework-agnostic core for agent-devtools — server, agent engine, widget shell

Terminal-native local AI assistant — offline, GPU-accelerated, agentic. Runs any GGUF model locally with full tool use.

Agentic coding tool for software development

JJK-themed agentic skills framework for coding agents

Agentic Coding Harness — AI pipeline that plans, implements, tests, and audits code changes

The unified CLI for Agentic Readiness. Optimize codebases for AI agents like Cursor, Windsurf, and Claude. Detect semantic duplicates, analyze context fragmentation, and improve agentic leverage.

Ucode is an agentic coding tool that lives in your terminal

A scope guardrail for agentic coding CLIs.

SpotMe - gym mode for agentic coding. Works with OpenCode and Pi.

Agentic code review skill and deterministic review tooling for AI-generated code.

A CLI to accelerate developing and testing Jahia in the Agentic era

The AgentHQ background server and `agent-hq` CLI — tools for agentic AI development.

Tensorlake provider for ComputeSDK - stateful MicroVM sandboxes for agentic applications and LLM-generated code execution

DevCortex CLI — structured requirements for agentic development

Reliability-first CLI for agentic software development.