Coding Agents

OpenAI's local terminal coding agent (Rust) that reads repos, proposes patches, and runs shell commands; pairs with Codex Web cloud agent and IDE extensions

Cognition's agentic IDE (ex-Codeium Windsurf) with Cascade-style flows and in-editor autonomous agents; marketed alongside Devin

Microsoft/GitHub's coding assistant across IDE plugins and Copilot CLI/agent modes—completions, chat, and multi-step agent workflows in VS Code and beyond

GitHub's issue-to-PR and agentic workspace flows that plan, edit, and open pull requests from natural-language tasks inside the GitHub ecosystem

Cognition's cloud autonomous software engineer that plans, codes, debugs, and deploys in a sandboxed environment with its own IDE/browser

Open-source git-native CLI pair programmer with repo maps, automatic commits, and multi-model support for surgical multi-file edits

Open-source VS Code & JetBrains assistant for chat, autocomplete, edit, and agent modes with full model/provider control including local LLMs

Open-source autonomous coding agent as VS Code/JetBrains extension, CLI, and SDK—file edits, terminal, browser tools with human approval gates

Popular Cline fork / VS Code agent with specialized modes (code, architect, debug) and multi-mode autonomous workflows

MIT open-source terminal coding agent (TUI/desktop/IDE) that is model-agnostic across 75+ providers including local models

Block-originated open-source local-first agent (desktop + CLI + API) for code and general workflows with deep MCP extension support

Sourcegraph's opinionated agentic coding product (VS Code extension + CLI) emphasizing frontier models, shareable threads, and subagents

Sourcegraph's codebase-aware coding assistant leveraging code search/graph context across large repositories

Privacy-first AI code completion and chat with on-prem/VPC options and license-aware models for regulated enterprises

AWS coding assistant for IDE chat/agents, code transformation (e.g. Java upgrades), and AWS-aware guidance; CLI lineage moved toward Kiro

Google's IDE coding assistant (completions/chat) powered by Gemini; enterprise Standard/Enterprise licenses; consumer/CLI path consolidating into Antigravity

Google's agent-first coding surface—desktop IDE fork, `agy` CLI, and extensions for VS Code/JetBrains/Zed—with planning, terminal, and browser subagents on Gemini

AI coding assistant that turns GitHub issues into PRs and offers JetBrains plugin/autocomplete workflows

Historical open-source CLI coding assistant (AbanteAI) for multi-file edits; CLI and mentat.ai bot service discontinued/archived

Open-source platform for autonomous software agents that code, use a terminal, and browse in sandboxed environments (formerly OpenDevin)

smol-ai's open-source prompt-to-codebase scaffolding agent that generates multi-file projects from a product spec

Open-source (and hosted gptengineer.app lineage) tool that generates entire codebases from natural-language prompts

Multi-model coding assistant with VS Code extension, CLI/agent tooling, and a large hosted model router for inference

Ultra-fast Rust editor with built-in AI assistant/agent features and Agent Client Protocol (ACP) for external coding agents

Enterprise coding assistant built for huge codebases with deep context engines and agentic edit workflows

ByteDance's AI IDE ('The Real AI Engineer') with Builder/SOLO-style autonomous modes and generous model access historically

Agentic development desktop/CLI platform emphasizing multi-agent collaboration, long-horizon tasks, memory, and cloud agents

Open-source agentic engineering platform spanning VS Code, JetBrains, and CLI with 500+ models at provider rates

Charmbracelet's glamorous open-source terminal coding agent with multi-model sessions, LSP-enhanced context, and MCP extensibility

AWS's agentic IDE/CLI/web/mobile platform (Q CLI successor path) focused on specs, steering, skills, and parallel agents

AI-native terminal (Warp) with an autonomous agent that runs multi-step shell/dev tasks inside a modern block-based terminal UX

Google's asynchronous coding agent that clones repos into Cloud VMs, implements tasks, and opens GitHub PRs for review

Terminal-based AI developer for large multi-step tasks with huge context, cumulative diff sandbox, and versioned plan branches

Ultra-fast AI code completion extension with a very large context window (up to ~1M tokens class)

Self-hosted open-source coding assistant (completions/chat) you run on your own GPUs—Copilot alternative for air-gapped teams

Native AI chat, completion, and agent-style assistance embedded in IntelliJ-based IDEs

Open-source VS Code-fork AI IDE (now deprecated) that sent prompts directly to BYO providers/local models without a middleman

Rust/Ratatui TUI coding agent with multi-provider support, Agent Skills, MCP, ACP, and ast-grep semantic search

Alibaba/Qwen terminal coding agent (Qwen Code / Qwen CLI) for agentic coding with Qwen models and multi-agent workflows

AI pull-request reviewer that comments on diffs with codebase-aware findings inside GitHub/GitLab workflows

AI code review agent that learns full-repo context to review PRs beyond single-diff heuristics

Developer copilot focused on long-term workflow memory, snippet/context capture, and assist across tools

Mistral's agentic coding product across CLI (`mistral-vibe`), VS Code/JetBrains/Zed, and web Code Mode with sandboxed remote sessions

Open-source Rust terminal coding agent—clean-room reimplementation of Claude Code behavior with multi-provider TUI, plugins, and ACP editor integration

Factory's agent-native development platform—Droids via CLI/TUI, IDE, web, Slack/Linear for delegated coding missions

Nous Research open-source self-improving CLI agent with persistent memory, skill creation, sandboxed execution, and multi-chat-platform reach

Minimal extensible terminal coding harness from the pi-mono toolkit—unified LLM API, TUI, skills, and MCP rather than a locked product

Google's open-source terminal coding agent (Apache-2.0) with MCP and large-context Gemini workflows; product path consolidating toward Antigravity CLI

AI-native IDE for design→production code

Terminal agent with Figma MCP / Code to Canvas

Agent development environment for shipping with coding agents. Run Claude Code, Codex, Gemini, Cursor CLI, and other CLI agents in parallel across isolated worktrees.

Self-hosted daemon to run Claude Code, Codex, Copilot, OpenCode, and Pi on your machine with your full env, then connect from phone, desktop, or web.

Open-source agentic development environment (YC W26): run coding agents like Claude Code and Codex in parallel, schedule work, and review changes in one place.

Orchestrate Claude Code, Codex, OpenCode, or any coding agent in one workspace: parallel tasks, isolated changes, and unified review.