“coding”

ALWAYS activate for programming-language work and code-adjacent project work: implementation, refactoring, debugging, code review, tests, CI fixes…

Performance-grounded code implementation, bug fixes, refactors, code reviews, and technical guidance.

The user's coding and docs conventions and taste.

Auto-document vibe coding sessions - collect, summarize, and publish

Local MCP server for reliable long-running AI coding workflows.

Voice interface for Claude Code: talk to your agent and it talks back while it works.

Subagent "code-simplifier" from coleam00/Archon: Identifies code simplification opportunities for clarity and maintainability while preserving exact…

Subagent "claude-code-guide" from FlorianBruniaux/claude-code-ultimate-guide: Expert on the Claude Code Ultimate Guide.

Subagent "code-reviewer" from coleam00/Archon: Reviews code for project guideline compliance, bugs, and quality issues.

Kilo Code: AI Coding Agent, Copilot, and Autocomplete

kilocode

Open Source AI coding agent that generates code from natural language, automates tasks, and runs terminal commands.

Mistral Vibe VS Code

mistralai

Mistral Vibe is an AI coding agent for VS Code that works across your whole project.

Andromity: Free AI Coding Agent for VS Code

agenticmarket

Free, open-source AI coding agent and an alternative to Cline, Kilo Code, Claude Code and Cursor that shows exactly what it did: live Waterfall, Fingerprint…

Open-source coding agent for VS Code, JetBrains, the CLI and the cloud that works with 500+ models

Anthropic's coding agent that reads your codebase, edits files and runs commands from the terminal, IDE, desktop app, web and Slack

Terminal-native AI coding assistant that reads and writes code, runs commands, manages Git and keeps persistent project memory.

Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding.

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long…

North Mini Code is Cohere's first agentic coding model and the debut of its North family.

Managed AWS sandbox where AI agents write and run code, with pre-built language runtimes and file handling.

Open-source infrastructure that runs AI-generated code in isolated cloud sandboxes.

Code execution API that lets LLM-generated code run in isolation and returns its output.

TypeScript library that lets agents call MCP and UTCP tools by running model-written code in a sandbox.

Minimal TypeScript agent harness with an agent runtime, multi-provider LLM API, terminal UI and coding agent CLI that users extend themselves.

TypeScript SDK that gives programs Claude Code's built-in tools for reading, editing and running code, installed from npm.

Workflow automation platform with a visual canvas, custom code and AI agents; source-available under a fair-code license, self-hostable or cloud

Integration layer for AI agents and developer workflows, with managed auth, 10,000+ prebuilt tools, an MCP server and custom code steps

Open-source, Apache-2.0 visual tool for building AI agents, apps and workflows with plugins, knowledge bases and an API and chat SDK

Open-source, MIT-licensed platform for observing production AI agents and turning failures into tracked signals

Coding agent security platform that watches agent actions on developer machines and blocks dangerous chains.

Open-source tool to trace, evaluate and improve AI agents, run locally or self-hosted

JSON-RPC protocol that lets any code editor run any coding agent, locally over stdio or remotely over HTTP.

Plain Markdown file at a repository root that tells coding agents how to build, test and work in the project.

Continuously refreshed coding benchmark built from new contest problems to limit training-data contamination.

Fine-grained authorization for apps, APIs and AI agents, with policy as code and an MCP gateway

Open-source platform for code-first API integrations, auth and MCP tools for products and agents

Pre-authenticated access to 1,000+ app toolkits for AI agents, with per-user sessions