Companies in the category 'AI Coding Agents'

OpenHands develops open-source AI agents designed to automate repetitive tasks for developers, such as writing code and running commands. Their platform enhances productivity while maintaining security.

Entire is building the world's next developer platform for human-agent collaboration, where agents and humans can collaborate, learn, and ship software together. The company's first open-source product, Checkpoints, is a CLI tool that automatically captures AI agent context—reasoning, prompts, and decisions—on every Git commit, creating a searchable record of how code was written. Founded in 2025 by former GitHub CEO Thomas Dohmke and co-founders Georg Friedrich and Cole Driver, Entire raised a $60 million seed round at a $300 million valuation in February 2026.

Trellis is an open-source, multi-platform AI coding framework and toolkit for Claude Code, Cursor, and other AI coding tools. It provides spec-driven development workflows that auto-inject context and coding standards into AI sessions, enabling structured task management, parallel agent sessions, and team-wide spec sharing.

Superset is a desktop application that enables developers to run multiple AI coding agents in parallel across isolated Git worktrees. It supports any CLI-based coding agent, including Claude Code, OpenAI Codex, and Cursor, and provides a built-in terminal, diff viewer, and one-click IDE integration to streamline multi-agent software development workflows.

Code Machine is an open-source multi-agent orchestration tool that coordinates AI coding agents such as Claude Code, Cursor CLI, and Codex CLI into repeatable, long-running workflows. It enables developers to define complex workflows once and execute them reliably, with agents running in parallel or sequentially to transform specifications into production-ready codebases. The project was built substantially by itself, with 90% of its codebase generated through its own orchestration system.

Magnitude is an open-source, subagent-native coding agent built from the ground up around subagent orchestration. Users chat with a lead agent that coordinates specialized subagents — explorers, planners, builders, reviewers, debuggers, and a browser agent — on their behalf. Subagents are long-lived and resumable, can be run in parallel, and share a common workspace to ensure lossless handoffs between agents. The platform supports most major model providers, including OpenAI, Anthropic, Google Gemini, and local models.

Hamster is an AI-native product delivery platform that helps software teams turn rough ideas into structured briefs, align on scope, and deliver faster. Its open-source Taskmaster CLI gives AI coding agents structured, dependency-aware task lists with full context, enabling teams to ship code that matches requirements without manual context management.

Million Software builds open-source developer tools for React performance and AI-powered coding agents. The company's products include React Scan, which automatically detects performance issues in React apps; Million.js, an optimizing compiler that makes React components significantly faster; and Ami, a desktop coding agent that reproduces bugs, diagnoses root causes, and validates fixes using parallel AI agents.

Emdash is an open-source, provider-agnostic desktop application that enables developers to run multiple AI coding agents in parallel, each isolated in its own Git worktree. It provides a unified dashboard for orchestrating agents across providers such as Claude Code, Codex, and Cursor, with built-in support for issue handoff from Linear, Jira, and GitHub, diff review, and remote project access via SSH.

Manaflow is an open-source applied AI lab building developer tools for managing AI coding agents. The company's flagship product is a universal AI coding agent manager that lets developers run multiple coding agent CLIs—including Claude Code, Codex, Gemini CLI, Amp, and Opencode—in parallel, with each agent running in its own isolated VS Code workspace, either in the cloud or in a local Docker container, complete with a git diff viewer, terminal, and dev server preview.

Potpie AI provides a foundational context layer that converts codebases, logs, tickets, documentation, and reviews into a knowledge graph, enabling AI agents to reason and execute tasks across large-scale software systems. The platform supports spec-driven development, allowing engineering teams to build custom codebase-aware agents for tasks such as debugging, feature development, and architecture reviews.

Bloop is a London-based software company that builds tools for planning, orchestrating, and reviewing the work of AI coding agents. Its primary product, Vibe Kanban, is an open-source kanban-based project management tool that enables software teams to run multiple AI coding agents in parallel, review generated code diffs, and manage pull requests from a single interface.

Kodezi is the developer and provider of Chronos-1, a language model engineered for autonomous bug localization, causal trace analysis, and test-driven patch generation at repository scale. Chronos-1 performs structured reasoning across entire codebases, identifying failure causes and generating test-passing fixes.

ByteRover develops an AI-powered memory layer for coding agents that enables persistent memory across AI IDEs and development teams. The company's flagship open-source project Cipher provides memory management, auto-save and recall capabilities, and team-wide intelligence sharing for AI coding assistants like Cursor, Windsurf, and Claude Desktop.