# usefulsoftwareco/executor

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/usefulsoftwareco-executor).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,363 stars · 403 forks · TypeScript · MIT

## Links

- GitHub: https://github.com/UsefulSoftwareCo/executor
- Homepage: https://executor.sh
- awesome-repositories: https://awesome-repositories.com/repository/usefulsoftwareco-executor.md

## Description

Executor is an integration layer that connects AI agents to external apps and APIs through a single shared endpoint. Agents get a search tool and a code-running tool, so they can write one short program that calls tools from many apps within a single task. That program runs in a sandboxed environment, and the endpoint is reachable by any client that speaks the Model Context Protocol, such as coding assistants and chat apps.

Credentials and approvals are handled outside the agent. An API key or sign-in is saved once and attached to outgoing calls inside the app layer, so the agent never sees the raw secret. Each tool also carries its own approval rule: ask first, always allow, never allow, or check the input for risk. Approvals can be routed through the agent, a client prompt, or a browser page.

Apps can be created from OpenAPI specs, GraphQL schemas, remote tool servers, or hand-written API calls, which are wrapped as small typed programs. They can be installed from a catalog or added by a remote server's web address, and an agent can write and deploy new versions that are published as immutable versions and can be rolled back.

Executor can run as a hosted service, a local background process with local data, or a single container with an embedded database, all serving the same apps. Groups of people can share connected accounts through browser sign-in in hosted or self-hosted setups.

## Tags

### Artificial Intelligence & ML

- [AI Tool Integration Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/development-runtime-environments/ai-agent-infrastructure/ai-tool-integration-layers.md) — Connects AI agents to external apps, APIs and tool servers through one consistent interface, with credential handling and approval policies outside the agent.
- [Agent Code Execution Across Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-code-execution-across-tools.md) — Give agents a search tool and an execute tool so they write one short program that calls many apps' tools within a single task. ([source](https://github.com/usefulsoftwareco/executor#readme))
- [Tool Execution Approvals](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-action-frameworks/action-approval-gates/tool-execution-approvals.md) — Decides per tool whether to ask first, always allow, never allow, or check input risk before an agent runs it. ([source](https://github.com/usefulsoftwareco/executor#readme))
- [AI Agent Tool Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-agent-integrations/ai-agent-tool-integrations.md) — Connects AI agents to many external apps and APIs, including OpenAPI, MCP, and GraphQL tools, from one place within a task.
- [API Spec to Agent Tool Converters](https://awesome-repositories.com/f/artificial-intelligence-ml/api-spec-to-agent-tool-converters.md) — Wraps OpenAPI specs, GraphQL schemas, remote tool servers, and hand-written API calls as small typed programs that agents can call directly.
- [MCP Gateways](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-gateway-federations/mcp-gateways.md) — Exposes connected apps and tools to any Model Context Protocol client through a single shared endpoint.
- [Multi-Tool Program Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-tool-program-execution.md) — Gives agents a search tool and a code-running tool so one short program can call tools from many apps in a single task.
- [Tool Approval Rules](https://awesome-repositories.com/f/artificial-intelligence-ml/tool-approval-rules.md) — Lets each tool carry its own rule to ask first, always allow, never allow, or check input risk, with approvals via agent, client, or browser.
- [Agent-Authored Tool Apps](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-authored-tool-apps.md) — Installs apps from a catalog, adds remote servers by web address, and lets agents write and deploy new rollback-able app versions. ([source](https://github.com/usefulsoftwareco/executor#readme))
- [Connected App Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/connected-app-tools.md) — Exposes all connected apps and tools to any compatible client, including coding assistants and chat apps, via one shared endpoint. ([source](https://github.com/usefulsoftwareco/executor#readme))
- [Human-in-the-Loop Workflows](https://awesome-repositories.com/f/artificial-intelligence-ml/human-in-the-loop-workflows.md) — Requires a person's confirmation for risky agent actions before they run, via the agent, a client prompt, or a browser page.

### Software Engineering & Architecture

- [MCP Tool Gateways](https://awesome-repositories.com/f/software-engineering-architecture/single-endpoint-architectures/mcp-tool-gateways.md) — Exposes every connected app and tool through one shared endpoint reachable by any Model Context Protocol client, such as coding assistants and chat apps.

### DevOps & Infrastructure

- [Code Execution Sandboxes](https://awesome-repositories.com/f/devops-infrastructure/execution-environments/code-execution-runtimes/code-execution-sandboxes.md) — Runs agent-written programs in an isolated sandbox with restricted access, keeping untrusted code away from the host and secrets.
- [Cloud or Self-Hosted Deployments](https://awesome-repositories.com/f/devops-infrastructure/feature-flags/cloud-or-self-hosted-deployments.md) — Runs as a hosted service, a local background process, or a single container with an embedded database, all serving the same apps. ([source](https://github.com/usefulsoftwareco/executor#readme))

### Security & Cryptography

- [Agent Program Sandboxes](https://awesome-repositories.com/f/security-cryptography/agent-program-sandboxes.md) — Runs short agent-written programs in an isolated sandbox so they can chain calls across many tools without touching the host or secrets.
- [Stored Credential Retrievals](https://awesome-repositories.com/f/security-cryptography/identity-access-management/credential-lifecycle-management/authentication-management/connection-credentials/stored-credential-retrievals.md) — Saves an API key or sign-in once and reuses it across apps, attaching it in the app layer so agents never see it. ([source](https://github.com/usefulsoftwareco/executor#readme))
- [Credential Injection](https://awesome-repositories.com/f/security-cryptography/identity-based-access-brokers/credential-injection.md) — Attaches saved API keys and sign-ins to outgoing tool calls inside the app layer so agents never see raw secrets.
- [Self-Hosted Vaults](https://awesome-repositories.com/f/security-cryptography/secret-storage/self-hosted-vaults.md) — Stores API keys and sign-ins once, in a hosted or self-hosted setup, and injects them into outgoing calls so agents never see the secrets.

### Business & Productivity Software

- [Shared Team Account Access](https://awesome-repositories.com/f/business-productivity-software/shared-team-account-access.md) — Organizes people into groups who share connected accounts through browser sign-in, in hosted or self-hosted setups. ([source](https://github.com/usefulsoftwareco/executor#readme))

### Data & Databases

- [OpenAPI-to-Tool Converters](https://awesome-repositories.com/f/data-databases/openapi-processors/openapi-to-tool-converters.md) — Turns OpenAPI specs, GraphQL schemas, remote tool servers and hand-written API calls into small typed tools that agents can call.

### Development Tools & Productivity

- [MCP Endpoint Grouping](https://awesome-repositories.com/f/development-tools-productivity/developer-toolboxes/mcp-endpoint-grouping.md) — Exposes every connected app and tool through one shared MCP endpoint that coding assistants and chat clients can reach.
