# Executor — AI Coding Tool Review & Pricing > Executor is an open-source integration layer and tool gateway for AI agents. You connect each account once, and any MCP-compatible agent (Claude Code, Codex, Cursor, ChatGPT and others) reaches those services through one MCP endpoint without seeing the credential. Since v2, integrations are apps: small TypeScript programs that wrap an OpenAPI spec, proxy a remote MCP server or call an API by hand, and can store data, serve a UI and run on schedules or webhooks. Source: https://ai.dosa.dev/tools/executor · Updated Nov 9, 2026 · Category: Developer Productivity & Workflow · Published by dosa.dev ## At a glance - **Tool**: Executor - **Company**: Useful Software Co (Rhys Sullivan, YC) - **Category**: [Developer Productivity & Workflow](https://ai.dosa.dev/category/productivity) - **Pricing model**: Freemium - **Official website**: https://executor.sh/ ## Key features - One MCP endpoint shared by every agent, with credentials attached inside apps so agents never see API keys or OAuth tokens - Apps written in TypeScript that wrap OpenAPI specs, remote MCP servers or hand-written API calls, with stored data, their own UI and background runs - Code mode: agents get `skills` and `execute` tools and run short programs across many apps instead of single tool calls - Per-tool approvals (always, never, or only when input looks risky), answered in the MCP client, through the agent or on a browser page - Versioned deploys with rollback, plus a catalog of ready-made apps and agents that can write and deploy new ones - Hosted Executor Cloud, local CLI and desktop app, or self-hosting in one Docker container with an embedded database ## Pricing **Model**: Freemium The CLI, desktop app and self-hosted server are MIT-licensed and free. Executor Cloud is free for up to 3 members with unlimited integrations; Team costs $15 per member per month after a 14-day free trial and adds verified domains; Enterprise is custom and adds self-hosted or dedicated cloud deployment support, SSO/SAML, SCIM, audit logs for every tool call and dedicated support. ## Who it is for - **Best for**: Developers and teams who use several coding agents and want one governed place for integrations, credentials and approval policies instead of configuring MCP servers and API keys in every client. - **Not ideal for**: People who want an agent that does the work itself (Executor runs no AI), or teams that need a visual flow builder like Zapier or n8n rather than automations written as code. ## Verdict A well-designed, actively developed gateway that removes repeated integration and credential setup across agents, with a free open-source local option and simple per-member cloud pricing. ## Recent updates Executor v2 launched on November 5, 2026, reworking the product around TypeScript apps, `skills` and `execute` code-mode tools and agent-built automations; new sign-ups moved to v2 while v1 users can opt in. Releases continue in the 2.0.0 beta line, with executor@2.0.0-beta.38 published on November 9, 2026. ## Frequently asked questions ### Is Executor free? Executor is Freemium. The CLI, desktop app and self-hosted server are MIT-licensed and free. Executor Cloud is free for up to 3 members with unlimited integrations; Team costs $15 per member per month after a 14-day free trial and adds verified domains; Enterprise is custom and adds self-hosted or dedicated cloud deployment support, SSO/SAML, SCIM, audit logs for every tool call and dedicated support. Check the official site for current plans. ### Is Executor open source? Yes - Executor is open source. The CLI, desktop app and self-hosted server are MIT-licensed and free. Executor Cloud is free for up to 3 members with unlimited integrations; Team costs $15 per member per month after a 14-day free trial and adds verified domains; Enterprise is custom and adds self-hosted or dedicated cloud deployment support, SSO/SAML, SCIM, audit logs for every tool call and dedicated support. ### How much does Executor cost? The CLI, desktop app and self-hosted server are MIT-licensed and free. Executor Cloud is free for up to 3 members with unlimited integrations; Team costs $15 per member per month after a 14-day free trial and adds verified domains; Enterprise is custom and adds self-hosted or dedicated cloud deployment support, SSO/SAML, SCIM, audit logs for every tool call and dedicated support. Pricing changes often - verify on the official site. ### Who is Executor best for? Developers and teams who use several coding agents and want one governed place for integrations, credentials and approval policies instead of configuring MCP servers and API keys in every client. ### Who is Executor not ideal for? People who want an agent that does the work itself (Executor runs no AI), or teams that need a visual flow builder like Zapier or n8n rather than automations written as code. ### What are the best Executor alternatives? The closest Executor alternatives on ai.dosa.dev are Pieces for Developers, agenttrace, Vibe Kanban - all listed under Developer Productivity & Workflow. ### Who makes Executor? Executor is developed by Useful Software Co (Rhys Sullivan, YC). It is listed in the Developer Productivity & Workflow category on ai.dosa.dev. ## Top alternatives - [Pieces for Developers](https://ai.dosa.dev/tools/pieces-for-developers) (Paid) — Developers who work across multiple tools, IDEs, and environments and need to maintain a persistent, searchable history of code snippets, research, and workflow context. - [agenttrace](https://ai.dosa.dev/tools/agenttrace) (Open Source) — Developers and teams needing to monitor and debug the efficiency, cost, and health of AI coding agents across multiple workflows. - [Vibe Kanban](https://ai.dosa.dev/tools/vibe-kanban) (Open Source) — Software engineers who use multiple AI coding agents and need a structured environment to manage, plan, and review their output in parallel. - [ai-memory](https://ai.dosa.dev/tools/ai-memory) (Open Source) — Developers or teams using multiple AI coding agents who need consistent context and project history persistence across different tools, machines, and sessions. - [smolvm](https://ai.dosa.dev/tools/smolvm) (Open Source) — Running isolated coding agent sandboxes, untrusted code, and persistent local development environments that require a real Linux kernel boundary. - [coop](https://ai.dosa.dev/tools/coop) (Open Source) — Running autonomous AI coding agents that require broad system access while maintaining a strong security boundary for the host machine. - Full alternatives guide: https://ai.dosa.dev/tools/executor/alternatives