Agentic Dev Tools

aider-chat

An open-source AI pair programming CLI that works in any terminal, makes git-committed edits across multiple files, and supports over 100 LLM providers.

Amazon Web Services

AWS's agentic coding CLI that integrates with the terminal, understands AWS services deeply, and can plan and execute multi-step coding tasks using the Amazon Q model.

Sourcegraph

Sourcegraph's agentic coding tool that combines a terminal CLI and VS Code extension with deep codebase search, giving the model precise context retrieval across large repositories.

Augment Code

An enterprise AI coding platform with a 500K-file Context Engine for deep codebase understanding, autonomous Remote Agents for background task execution, and a multi-agent Cosmos orchestration layer covering the full software development lifecycle.

StackBlitz

StackBlitz's browser-based agentic development environment using WebContainers to generate, run, and deploy full-stack applications entirely in the browser with no local installation required.

Anthropic

A terminal-based agentic coding tool that runs in the developer's own environment, giving Claude read/write access to the file system, shell, and browser to complete coding tasks end to end.

Cline

An open-source VS Code extension that embeds a full agentic coding loop — file edits, terminal commands, and browser control — directly into the editor, with support for any LLM provider.

Codebuff (YC)

A Y Combinator-backed multi-agent CLI coding tool with a free tier (Freebuff), using specialised agents for file picking, planning, editing, and reviewing to autonomously modify codebases.

CodeRabbit

An automated code review agent that triggers on every pull request, generating plain-English walkthroughs, sequence diagrams, and line-level bug and security findings across GitHub, GitLab, Azure DevOps, and Bitbucket.

OpenAI

OpenAI's open-source agentic coding CLI that runs in the developer's terminal with sandboxed code execution, giving GPT and o-series models access to files and shell commands.

Continue

An open-source IDE extension for VS Code and JetBrains that adds AI autocomplete and chat with full model flexibility, acting as an open alternative to GitHub Copilot.

CrewAI Inc.

A role-based multi-agent orchestration framework where developers define specialised AI agents with distinct roles, tools, and goals, coordinate them through structured workflows, and deploy them as autonomous crews for software development pipelines and SDLC automation.

Charmbracelet

A Go-based TUI terminal coding agent from the makers of Glow and Bubble Tea, with LSP integration, MCP server support, session management, and a --yolo mode for fully autonomous operation.

Anysphere

An AI-first code editor built on VS Code that integrates LLMs directly into the editing workflow, enabling chat-driven code generation and multi-file edits.

Cognition AI

An autonomous AI software engineer that accepts a task, spins up its own sandboxed environment, and works end-to-end on coding tasks with minimal human checkpointing.

Factory

An enterprise autonomous coding platform where specialised AI Droids handle the complete software development lifecycle — feature development, code review, incident response, migrations, and documentation — integrated with GitHub, Jira, Slack, and PagerDuty.

TailCallHQ

A terminal-based AI pair programmer with a three-agent architecture — implement, research, and plan — supporting 300+ models and offering interactive TUI, one-shot CLI, and shell plugin modes.

Google

Google's open-source agentic coding CLI that runs Gemini models in the developer's terminal, with a 1M-token context window and MCP tool support.

GitHub (Microsoft)

GitHub's AI pair programmer, deeply integrated into VS Code, JetBrains IDEs, and GitHub.com, offering inline autocomplete, chat, and code review assistance.

GitHub (Microsoft)

A GitHub Copilot feature that translates natural-language descriptions into shell commands, explains what a command does, and suggests corrections — a command-helper, not a coding agent.

GitHub (Microsoft)

GitHub's cloud-based autonomous coding agent that accepts an assigned GitHub issue, researches the repository, writes code on a branch, runs tests via GitHub Actions, and opens a draft pull request — with no developer involvement during execution.

Block

Block's open-source agentic developer tool that runs locally, supports any LLM provider, and extends its capabilities through a rich MCP and custom-extension ecosystem.

Open source (ErikBjare)

One of the earliest open-source terminal coding agents (Spring 2023), combining code execution, file editing, web browsing via Playwright, and shell access in a persistent conversation interface.

Greptile

An AI code review platform that indexes the entire codebase into a call-graph and deploys a swarm of parallel agents per pull request, catching cross-file dependency issues that diff-only reviewers miss.

Google

Google's cloud-based autonomous coding agent that accepts a GitHub issue, creates a plan, executes it in an isolated Google Cloud VM powered by Gemini 2.5 Pro, and opens a pull request — entirely without developer involvement.

JetBrains

JetBrains' native AI coding agent deeply integrated into IntelliJ, PyCharm, WebStorm, and other IDEs, generating a multi-step Task Blueprint before writing code, running tests, and iterating until the build is green.

Kilo-Org

The community-governed open-source continuation of Roo Code (archived May 2026), providing a full agentic loop across VS Code, JetBrains, and CLI with 500+ model support and 1.5M+ users.

Amazon Web Services

AWS's agentic IDE built on a VS Code core that uses spec-driven development — converting natural-language requirements into formal specs, design documents, and task lists before writing and testing code.

LangChain, Inc.

A low-level Python and JavaScript framework for building stateful, multi-actor agentic applications as directed graphs, with first-class support for cycles, human-in-the-loop, and persistence.

Letta AI

A memory-first terminal coding agent from the creators of MemGPT that accumulates knowledge about your codebase across sessions, ranked first among model-agnostic open-source agents on Terminal-Bench at launch.

Lovable

A browser-based AI full-stack app builder that generates, iterates on, and deploys React/TypeScript applications from natural-language prompts, with GitHub integration, Supabase backend, and an autonomous Agent Mode.

DeepWisdom

A multi-agent framework that simulates a full software company — product manager, architect, and engineers — collaborating to generate user stories, architecture docs, and working code from a single natural-language requirement.

Princeton NLP / Stanford

A radically minimal autonomous software engineering agent — approximately 100 lines of core Python — that scores above 74% on SWE-bench Verified using only bash commands in a sandboxed environment.

Mistral AI

Mistral AI's open-source terminal coding agent powered by Devstral 2, with file editing, shell execution, and a cloud execution mode that lets sessions run remotely when the local machine is off.

Open Interpreter

An open-source terminal interface that lets language models run code locally, giving them access to your file system, browser, and any application on your computer.

LangChain

LangChain's open-source framework for building fully autonomous async coding agents that pick up issues from Linear, Slack, or GitHub and independently write, test, and PR code — operating as another engineer on the team.

SST

An open-source terminal-based agentic coding tool from the SST team, designed for multi-provider LLM support and a keyboard-driven TUI workflow.

All Hands AI

An open-source autonomous software agent (formerly OpenDevin) that executes multi-step engineering tasks inside a sandboxed Docker container, from issue to pull request.

Earendil Works

A minimalist open-source terminal coding agent that runs across 15+ LLM providers, with a TypeScript-based Skills system for extensibility and session branching for non-destructive exploration.

Plandex AI

An open-source terminal coding agent designed for large, multi-file development tasks with a cumulative diff sandbox that stages all AI-proposed changes for human review before applying them.

Potpie AI

An open-source agentic platform that converts a codebase into a knowledge graph and runs specialised agents — debugging, code generation, test planning, and code review — with full structural understanding of the repository.

Qodo

Formerly CodiumAI, Qodo provides a multi-agent code review platform (Qodo Merge), a CLI agent framework for SDLC automation (Qodo Command), and an IDE extension — with the open-source PR-Agent at its core.

Alibaba (QwenLM)

Alibaba's open-source agentic CLI coding tool, forked from Gemini CLI and optimised for Qwen3-Coder models, with full support for other major providers and VS Code and Zed integrations.

Replit

Replit's cloud-based AI development agent that autonomously builds, deploys, and maintains full-stack applications from natural-language descriptions, running in Replit's cloud IDE with 160+ service connectors.

Atlassian

Atlassian's agentic coding platform deeply integrated with Jira, Confluence, and Bitbucket — converting Jira issues into implementation specs, reviewing PRs against acceptance criteria, and operating via CLI, IDE, and browser with Atlassian's Teamwork Graph as context.

Hugging Face

Hugging Face's open-source agent framework where agents reason and act through Python code snippets rather than JSON tool calls, achieving 30% fewer steps on benchmarks with a minimal ~1,000-line core that supports MCP and any LLM provider.

Princeton NLP / Stanford

A research-grade autonomous CLI agent from Princeton and Stanford that takes a GitHub issue URL and resolves it end-to-end using a custom Agent-Computer Interface optimised for software engineering.

TabbyML

A self-hosted, open-source AI coding assistant and GitHub Copilot alternative that runs entirely on your own infrastructure with no data leaving your environment, supporting local models via Ollama and cloud providers.

ByteDance

ByteDance's AI-first code editor offering free unlimited access to Claude, GPT-4o, and DeepSeek R1, available as a standalone IDE, VS Code/JetBrains plugin, and CLI agent with a Figma design-to-code mode.

ByteDance SE Lab

ByteDance Software Engineering Lab's open-source CLI coding agent that achieved 75.2% on SWE-bench Verified using a multi-model ensemble with Claude, Gemini, and o4-mini.

Warp

An AI-native terminal emulator that went open source in May 2026, combining a high-performance Rust-based shell with built-in AI coding agents and the Oz cloud orchestration platform for running autonomous background agents.

Cognition (formerly Codeium)

An AI-native VS Code fork with the Cascade agentic engine for deep codebase understanding and multi-file autonomous edits, backed by Cognition's SWE-1 model family and integrated with the Devin ecosystem.

Zed Industries

A high-performance open-source code editor built from scratch in Rust with a GPU-accelerated UI, supporting parallel AI agent threads and the Agent Client Protocol for multi-agent workflows.

For Good AI

An AI coding platform with proprietary Repository Grokking technology for deep codebase analysis, an organisation-wide Zen Agents marketplace for sharing custom agents, and Zenflow Work for automating the 75% of engineering time spent outside writing code.