Agents

Open-source AI operating system where agents work in cloud sandboxes and land changes through approved change requests

Open-source workspace for named AI agents with memory, delegation, routines and approval controls.

Go terminal coding agent with cost-aware routing across LLM providers, shipped as one binary.

Open-source web, desktop and mobile control room for running coding agents such as Claude Code and Codex on your own machines.

Background agent that picks up Linear, GitHub, GitLab and Slack issues and runs Claude Code, Codex or other coding agents on them.

Coding agent built on pi that hands routine decisions to a small judge model, so the main model can focus on the code.

Local-first open-source desktop IDE for long-running agent work, with code, Git, terminal, browser and MCP in one workspace

Open-source Devin alternative that runs Claude Code, Codex, OpenCode or Pi in isolated workspaces you can self-host.

Terminal coding agent with per-request model routing across six cost tiers, a code graph and spend monitoring, served by a hosted router.

Augment's Cosmos platform runs agent loops for code review, ticket-to-PR, vulnerability fixes and incident response, with a CLI and IDE plugins

AI agents inside GitLab for planning, coding, security and pipelines, with optional human checkpoints

JetBrains coding agent that runs in the terminal, inside IDEs and in GitHub and GitLab, with models you bring.

AWS's spec-driven coding agent that turns prompts into requirements, designs and tasks, available in IDE, CLI, web and mobile

Sentry's debugging agent that investigates new issues, finds the root cause and drafts a fix as a pull request.

Agent platform that plans, builds, tests and reviews code, letting you assign different models to each phase

Google's AI coding assistant for IDEs and the terminal, sold as Standard and Enterprise editions through Google Cloud.

Google's asynchronous coding agent that clones your GitHub repo into a cloud VM, plans changes and opens a pull request