Best AI agents for writing code (2026)

Turns a codebase plus its docs, SQL schemas, configs and PDFs into a knowledge graph that coding agents can query.

Claude-Mem

Gives coding agents memory across sessions by capturing what they do, compressing it and feeding the relevant context back in later.

Orca

Agent development environment for running a fleet of parallel coding agents on your own subscriptions and reviewing their work.

Strix

Open-source AI agents that run penetration tests on your app to find and help fix security vulnerabilities.

Goose

Extensible open-source AI agent that installs, runs, edits and tests code on your machine with any LLM and MCP extensions.

Herdr

Runtime for running and managing many coding agents side by side.

Codewhale

Rust agent engine and terminal coding client with model choice, tool approvals and review flows.

Oh My Claudecode

Multi-agent orchestration layer for Claude Code that coordinates teams of specialized agents.

DeepSeek-Reasonix

Coding agent built for complex software engineering tasks on DeepSeek models.

Oh My Pi

Terminal coding agent with IDE features wired in, from Stencil Labs.

PentAGI

Autonomous multi-agent system for running penetration testing tasks.

Context Mode

Context window optimizer for coding agents that sandboxes tool output and persists session memory.

AgentMemory

Persistent memory layer for AI coding agents.

Crush

Charm's terminal coding agent with a polished TUI, multiple models and MCP support.

Qwen Code

Open-source terminal coding agent from the Qwen team.

Vibe Kanban

Kanban board for planning and running tasks with Claude Code, Codex and other coding agents.

Beads

Issue-tracking memory for coding agents so they can keep track of long-running work.

Planning With Files

File-based planning for coding agents, keeping Markdown plans that survive crashes and session resets.

Happy Coder

Mobile and desktop app to run and control Claude Code, Codex and other agents using your own subscriptions.

Paseo

Orchestrate multiple coding agents from desktop and mobile.

jcode

High-performance coding agent harness written in Rust.

Coder

Self-hosted cloud development environments for developers and their coding agents.

DeepCode

Open agentic coding system that turns papers and specs into code with multi-agent orchestration.

Superset

Agentic IDE for orchestrating many coding agents in parallel.

Qodo

AI code review and testing agents that work in the IDE, the terminal and pull requests to catch issues before merge.

Agent Orchestrator

Runs and supervises teams of coding agents from planning to merge.

HumanLayer

Tools for getting coding agents to solve hard problems in complex codebases.

OpenChamber

Agentic development environment built around the OpenCode agent.

Trail Code

Context layer that makes Claude Code, Cursor, Codex and other coding agents faster and cheaper on large codebases.

Ralph for Claude Code

Autonomous development loop for Claude Code that keeps iterating until the task is done.

Hunk

Review-first terminal diff viewer for checking what coding agents changed.

Oh My OpenCode Slim

Lean multi-agent suite for OpenCode that mixes models and delegates tasks automatically.

Plannotator

Visually annotate and review coding-agent plans and diffs, then send feedback back to the agent.

Terax

Lightweight terminal-first AI development environment.

Worktrunk

CLI for managing Git worktrees so several AI agents can work in parallel.

Munder Difflin

Free, open-source harness that runs Claude Code, Codex, Gemini CLI and other terminal agents together like an office.

mini-SWE-agent

Tiny 100-line agent that solves GitHub issues or helps on the command line, from the SWE-agent team.

SuperPlane

Open-source platform for orchestrating one-shot engineering work with agents.

Gentle AI

Configures the coding agents you already use with shared rules, skills and settings.

OpenRig

Builds persistent teams of Claude Code, Codex and Pi agents with roles and shared context.

Backlog.md

Markdown task board in your Git repo for coordinating work between people and AI agents.

Mission Control

Self-hosted control plane for dispatching tasks to agents, reviewing runs and tracking spend.

Semble

Fast code search for agents that uses far fewer tokens than grep and file reads.

Potpie

Builds a knowledge graph of your codebase so agents can help across the software lifecycle.

Tokscale

Tracks token usage across AI coding agents from your terminal.

Code-Graph-RAG

Graph-based RAG for monorepos that lets agents query and edit multi-language code.

Entire CLI

CLI that captures AI agent sessions alongside your Git commits.

Integuru

Agent that builds integrations by reverse engineering platforms' internal APIs.

gptme

Terminal agent with local tools that writes code, runs commands, browses the web and uses vision.

Jupyter AI

Official JupyterLab extension that connects AI agents and chat to notebooks.

Command Code

Coding agent built for open models.

abtop

htop-style monitor for Claude Code and Codex sessions and token use.

HolmesGPT

CNCF sandbox SRE agent that investigates alerts and incidents.

Grok CLI

Open-source coding agent for the Grok API.

Maestro

Command center for orchestrating multiple coding agents.

PentestAgent

Agent framework for black-box security testing and bug bounty work.

Ralph Orchestrator

Orchestrator for autonomous agent loops using the Ralph Wiggum technique.

Chaterm

Open-source AI terminal for deploying, troubleshooting and automating cloud infrastructure.

Ruler

Applies one set of rules to all your coding agents.

CodeBoarding

Generates interactive architecture diagrams of codebases.

Nanocoder

Community-built open coding agent for your terminal.

Imbue

AI research company building tools for coding agents, including Sculptor for running parallel agents.

BackAnt Kairos

Backant's Kairos, an autonomous developer that runs Claude Code against your repository.

Cleric

NewcodingEnterprise

AI SRE agent that investigates production alerts and finds root causes.

Coddo

Desktop app that puts a visual interface and voice input on top of terminal coding agents.

Coldtea

Agents that test every pull request on real devices, watch production and file issues before users hit them.

KaneAI

AI testing agent that plans, writes and evolves end-to-end tests from natural language.

Nimbalyst

Visual workspace for working with coding agents like Claude Code on docs, code and plans.

Runcell

AI agent for Jupyter notebooks that writes and runs code cells.

Verdent

AI coding agent that plans, codes and verifies tasks in parallel.

Langflow

Visual drag-and-drop builder for AI agents and workflows that you can run locally, deploy as an API or expose as an MCP server.

Deer Flow

NewresearchOpen source

ByteDance's open-source long-horizon agent harness that researches, codes and creates using sandboxes, memory and sub-agents.

Context7

MCP server and platform that feeds coding agents up-to-date, version-specific library documentation.

Chrome DevTools MCP

Official MCP server that lets coding agents control and inspect a live Chrome browser through DevTools for debugging and performance work.

Codebase Memory MCP

MCP server that indexes codebases into a persistent knowledge graph so coding agents can look up structure quickly.

GitHub MCP Server

GitHub's official MCP server for letting agents work with repositories, issues, pull requests and Actions.

Serena

MCP toolkit that gives coding agents semantic code retrieval and editing, like IDE features.

Sim Studio

Workspace for visually building, deploying and monitoring AI agents and workflows.

TencentDB-Agent-Memory

Newpersonal agentsOpen source

Team-level memory hub that turns conversations, docs and code into shared memory for agents.

agenticSeek

Fully local autonomous agent that browses, codes and plans without paid APIs.

Activepieces

Newapp buildersOpen source + cloud

Open-source automation platform with AI agents and hundreds of pieces usable as MCP servers.

NocoBase

Open-source no-code platform with AI employees for building business systems.

MaxKB

Newbrowser/computer useOpen source + cloud

Open-source platform for building enterprise agents and knowledge-base assistants.

Maxun

Turns websites into structured APIs with no-code robots for extraction and monitoring.

OpenSandbox

Newapp buildersOpen source + cloud

Secure, fast sandbox runtime for AI agents to run code.

InsForge

Open-source backend platform that gives coding agents a database, auth and storage.

CubeSandbox

Lightweight, concurrent sandbox for running AI agent code securely.

Feynman

NewresearchOpen source

Open-source research agent that searches, reads papers and writes cited reports.

PraisonAI

Multi-agent framework for building a self-improving AI workforce with little code.

Astron Agent

iFlytek's enterprise agentic workflow platform for building super agents.

microsandbox

Local-first microVM runtime for running untrusted agent code safely.

GitMCP

Free remote MCP server that gives agents up-to-date docs and code for any GitHub project.

OpenEvolve

Open-source take on AlphaEvolve that uses LLM agents to evolve better code and algorithms.

Unstract

LLM-powered platform for extracting structured data from documents via APIs and ETL pipelines.

Voyager

NewgamesOpen source

Research agent that explores Minecraft on its own, writing and reusing code skills to learn as it goes.

Talk to Figma MCP

Newpersonal agentsOpen source

MCP integration that lets coding agents read and edit Figma designs.

Kun

Local-first agent workspace for coding, writing, design, research and automation.

Nexent

Zero-code platform that generates AI agents from plain-language descriptions.

PySpur

Visual playground for building and iterating on agent workflows.

Wigolo

Newapp buildersOpen source

Local-first web search, fetch and crawl for coding agents over MCP, with no API keys.

VibeSDK

Cloudflare's open-source kit for running your own vibe-coding platform.

Agent Device

NewMCP & infraOpen source + cloud

Mobile app automation and verification for coding agents on iOS and Android.

Judge0

Sandboxed code execution system for running untrusted code from people and AI.

Langroid

Python framework for multi-agent programming with LLMs.

LazyLLM

NewvoiceOpen source + cloud

Low-code framework for building multi-agent LLM applications.

vocode

Open-source library for building voice-based LLM agents for phone calls and apps.

Playwright Skill

Playwright automation skill for coding agents.

Ax

DSPy-style framework for building LLM programs and agents in TypeScript.

jCodeMunch MCP

MCP server for symbol-level code exploration that cuts token use.

Figma MCP Server

Figma's MCP server that brings design context from Figma files into coding agents.

MATLAB MCP Server

MathWorks' MCP server that lets coding agents run MATLAB code and tests.

Ref

Token-efficient documentation search for coding agents.

SonarQube MCP Server

SonarQube MCP server for code quality and security analysis from agents.

Buildkite MCP

Newbrowser/computer useFreemium

Buildkite's MCP server exposing pipelines, builds, jobs and logs to coding agents.

Anchor Action Index

Shared memory of web workflows for Anchor's cloud browsers: computer-use agents replay proven paths as deterministic code and the model only steps in where a page has changed, exposed as tools on Anchor's MCP server and REST API.

Appian

Newbusiness agentsEnterprise

Low-code process automation platform with AI agents built into enterprise workflows.

BetterClaw

Build and deploy AI agents without code on 28+ model providers, connected to Telegram, Slack, Discord and Gmail.

Blockscope

Newno-code buildersEnterprise

AI on-chain investigator that decodes transactions, profiles wallets and traces stolen funds across 8 chains.

Boomi

Integration platform with Boomi AI agents and agent management.

Cassidy

Newno-code buildersPaid

Build AI assistants and workflows trained on company knowledge for teams.

CircleCI MCP

CircleCI's MCP server for inspecting projects, pipelines, failed jobs and test results from coding agents.

Cod3x

No-code AI trading agent: describe a strategy in plain English and it trades 24/7.

CustomGPT.ai

Newbusiness agentsPaid

No-code platform for building AI agents grounded in your business content, with citations and anti-hallucination controls.

Duckie

Newbusiness agentsPaid

AI support agent for technical products that resolves tickets.

Griffin AI

Platform to build and launch DeFi agents without code.

Jotform AI Agents

Build AI agents from forms and docs that answer customers via chat, voice and messaging.

Magia Trade

Newbusiness agentsEnterprise

No-code visual strategy lab with AI agents that send signals and deploy live trading on Binance and B3.

Mindflow

No-code automation and AI agents for security and IT operations.

Momen

Newapp buildersFreemium

No-code full-stack app builder with AI agent features.

MyShell

Newpersonal agentsFreemium

Platform to build, share and use AI agents and apps.

Ninja AI

All-in-one AI assistant with research, coding and writing agents.

Nora

Deep-reasoning AI coding agent for building and securing Web3 apps and smart contracts.

Octane

Newno-code buildersEnterprise

Agentic security analysis that finds exploitable vulnerabilities in mission-critical code, including DeFi smart contracts.

SnapLogic

Integration platform with AgentCreator for building enterprise agents.

Tray.ai

Newno-code buildersEnterprise

Integration and automation platform for building enterprise AI agents.

Turnkey

Secure key infrastructure for programmatic and agent-controlled wallets.

opencode

Open-source terminal coding agent that works with many model providers.

Claude Code

Anthropic's terminal coding agent that edits code, runs commands and handles git.

OpenAI Codex CLI

OpenAI's open-source coding agent for the terminal; also runs in the cloud.

Gemini CLI

Google's open-source terminal agent powered by Gemini.

OpenHands

Open-source platform for autonomous coding agents.

Cline

Autonomous coding agent inside VS Code with step-by-step approvals.

Roo Code

VS Code agent with custom modes (architect, code, debug).

GitHub Agentic Workflows (gh-aw)

Run AI agents in GitHub Actions workflows; v0.91.10 pre-release (Oct 13) defaults read-only workflows to no network.

Jevgrep

CLI that finds relevant repo files and excerpts from natural-language questions for coding agents; claims ~40% cheaper agent runs.

Aider

Pair-programming agent in your terminal that commits changes to git.

Amp

NewcodingUsage-based

Agentic coding tool for the terminal and editor.

Cursor

AI code editor with an agent mode and background agents.

Devin

Cognition's autonomous software engineer that takes tickets and opens PRs.

GitHub Copilot

AI pair programmer with a coding agent that works from issues.

Windsurf

AI IDE with the Cascade agent, now rebranded as Devin Desktop after Cognition acquired Windsurf (windsurf.com redirects there).

Dify

Open-source platform for building LLM apps and agents visually.

Flowise

Drag-and-drop builder for agents and LLM flows.

GPT Researcher

NewresearchOpen source

Autonomous agent that researches the web and writes cited reports.

smolagents

Hugging Face's minimal library for code-writing agents.

Stagehand

NewMCP & infraOpen source + cloud

Browser automation framework mixing code with natural-language actions.

TryVoice

NewvoiceOpen source

Hands-free voice runtime for coding agents with wake word, push-to-talk and streaming replies.

Cicero

NewvoiceOpen source

Self-hosted voice interface for coding agents (Claude Code, Codex, ACP); talk from a browser or Telegram call.

E2B

Secure cloud sandboxes for running agent-generated code.

Lindy

No-code AI assistants for email, meetings and ops.

Make

Visual automation platform with AI agents.

n8n

Workflow automation with AI agent nodes; self-host or cloud.

Relevance AI

No-code platform to build AI agent teams for business work.

Zapier Agents