# Telnyx Agent Control Plane — Documentation Index
> Declare an agent in agent.json; the Agent Control Plane deploys it and exposes the API to manage it, Edge Compute hosts it, with memory, tools, and calls and texts one field away. One section of the Telnyx developer docs (https://developers.telnyx.com).
> This file: https://developers.telnyx.com/docs/development/llms/ai-agent-control-plane-beta-llms-txt · Root index: https://developers.telnyx.com/llms.txt

## Subsections

Focused per-subsection index files:

- [Agent Control Plane](https://developers.telnyx.com/docs/development/llms/ai-agent-control-plane-beta-agent-control-plane-beta-llms-txt)

- [Overview](https://developers.telnyx.com/docs/agents.md): The Agent Control Plane: build an agent by declaring it in configuration, or by implementing it in code on the Agent SDK, and run it on Telnyx.
- [Deploy the First Agent](https://developers.telnyx.com/docs/agents/get-started.md): Install the telnyx-acp CLI, create a configuration agent with the wizard and deploy it: the first walk-through of the Agent Control Plane.
- [Beta Limitations](https://developers.telnyx.com/docs/agents/beta-limitations.md): The Agent Control Plane is in beta. This page lists what the current release does not do yet, or does with a constraint.
- [Edge Compute Serverless](https://developers.telnyx.com/docs/agents/runtime-platform/edge-compute-serverless.md): An agent runs on Edge Compute as two things: a function and a stateful actor type.
- [Agents and Conversations](https://developers.telnyx.com/docs/agents/model/agents-and-conversations.md): The agent is the unit of deployment and of compute: one project, one function as the entry point, one actor type as the class.
- [Execution Model](https://developers.telnyx.com/docs/agents/model/execution-model.md): Four rules govern how code runs on an instance. They are the stateful actor's rules.
- [Memory Model](https://developers.telnyx.com/docs/agents/model/memory-model.md): An instance has three kinds of memory, and only one of them is real.
- [Isolation](https://developers.telnyx.com/docs/agents/model/isolation.md): Compute is isolated per agent; state is isolated per instance.
- [Lifecycle](https://developers.telnyx.com/docs/agents/model/lifecycle.md): An instance is activated on demand, kept in memory while it is busy, evicted when idle, and can be restarted or relocated at any time.
- [Project Layout](https://developers.telnyx.com/docs/agents/project-layout.md): telnyx-acp create scaffolds one directory per agent, named after it.
- [Models and Instructions](https://developers.telnyx.com/docs/agents/models-and-instructions.md): model and instructions are two fields of agent.json. model is a Telnyx inference model id.
- [Memory](https://developers.telnyx.com/docs/agents/memory.md): At the start of a conversation the agent reads the profile's summary before it reasons.
- [Overview](https://developers.telnyx.com/docs/agents/tools.md): Tools are declarative. You add what the agent can call with telnyx-acp add tool, which writes it to agent.json, and the platform handles invocation.
- [Web Search](https://developers.telnyx.com/docs/agents/tools/web-search.md): The Web Search API as tools the model calls. Web Search is also available as a standalone product.
- [MCP Servers](https://developers.telnyx.com/docs/agents/tools/mcp-servers.md): Any remote Model Context Protocol server over Streamable HTTP, by URL. This is the simple case, a server and an optional credential.
- [Gateway](https://developers.telnyx.com/docs/agents/tools/agent-gateway.md): Governed connectivity to APIs and MCP servers: authentication in and out, access control, policy.
- [Browser](https://developers.telnyx.com/docs/agents/tools/agent-browser.md): A real browser the agent drives, on Agent Browser: an isolated Chromium session the platform runs, opened for the run and closed after it.
- [Sandbox](https://developers.telnyx.com/docs/agents/tools/agent-sandbox.md): Sandboxed code execution for data analysis and computation. Each sandbox is a container running in its own virtual machine, with files moved in and out.
- [File System](https://developers.telnyx.com/docs/agents/tools/file-system.md): View, create and edit files from the agent. Files live on a CloudFS mount, so they persist beyond one instance.
- [Voice](https://developers.telnyx.com/docs/agents/voice.md): When an agent is configured with a phone number, it answers calls as a real-time agent.
- [Messaging](https://developers.telnyx.com/docs/agents/messaging.md): When an agent is configured with a phone number, it answers texts. Each sender is one conversation, and the reply goes back from the number the text came in on.
- [Local Development](https://developers.telnyx.com/docs/agents/local-development.md): telnyx-acp dev runs the agent on localhost: the managed loop in the CLI's own process, listening on loopback, reloading instructions.md and agent.json on save.
- [Test and Debug](https://developers.telnyx.com/docs/agents/test-and-debug.md): Two commands answer the questions a change raises: traces shows what one run did, step by step.
- [Deploy and Operate](https://developers.telnyx.com/docs/agents/deploy-and-operate.md): The first deploy registers the agent and builds it, which typically takes about ten minutes (deploy waits up to 25); every deploy after that is a new revision.
- [Overview](https://developers.telnyx.com/docs/agents/cli.md): telnyx-acp is the command line of the Agent Control Plane.
- [create](https://developers.telnyx.com/docs/agents/cli/create.md): The telnyx-acp create command: no flags opens the wizard, which Deploy the First Agent walks through.
- [dev](https://developers.telnyx.com/docs/agents/cli/dev.md): The telnyx-acp dev command: on a configuration project, dev runs the managed loop in process on a loopback listener.
- [deploy](https://developers.telnyx.com/docs/agents/cli/deploy.md): The telnyx-acp deploy command: the first deploy registers the function through telnyx-edge new-func.
- [invoke](https://developers.telnyx.com/docs/agents/cli/invoke.md): The telnyx-acp invoke command: posts one text to /rpc/receive on the conversation's address and reads the reply back from the instance's state stream.
- [eval](https://developers.telnyx.com/docs/agents/cli/eval.md): The telnyx-acp eval command: runs the project's saved test conversations against the agent and scores each reply.
- [chat](https://developers.telnyx.com/docs/agents/cli/chat.md): The telnyx-acp chat command: keeps one conversation open in the terminal. Each line typed is one turn on it, the reply is printed, and the prompt comes back.
- [text](https://developers.telnyx.com/docs/agents/cli/text.md): The telnyx-acp text command: sends one SMS to the deployed agent's number from one of the account's own numbers and prints the reply.
- [rpc](https://developers.telnyx.com/docs/agents/cli/rpc.md): The telnyx-acp rpc command: calls one @rpc method on the instance with its arguments and prints the result as JSON.
- [add](https://developers.telnyx.com/docs/agents/cli/add.md): The telnyx-acp add command: with no arguments, add reopens the wizard over this project's agent.json, pre-filled, and asks again about the model, the numbers, email, the channels.
- [remove](https://developers.telnyx.com/docs/agents/cli/remove.md): The telnyx-acp remove command: each form edits agent.json. The next deploy applies the change, except for a secret, which is deleted from the platform at once.
- [set](https://developers.telnyx.com/docs/agents/cli/set.md): The telnyx-acp set command: set <path> [value] changes one field of agent.json, addressed by a dotted path.
- [unset](https://developers.telnyx.com/docs/agents/cli/unset.md): The telnyx-acp unset command: <path> removes one field of agent.json, back to its default, with the same validation as set.
- [tools](https://developers.telnyx.com/docs/agents/cli/tools.md): The telnyx-acp tools command: lists every tool entry of agent.json with the names the model sees, which are the names approvals and the log lines use.
- [status](https://developers.telnyx.com/docs/agents/cli/status.md): The telnyx-acp status command: reports what is deployed and wired.
- [logs](https://developers.telnyx.com/docs/agents/cli/logs.md): The telnyx-acp logs command: reads the deployed agent's lines from both the function and the actor, one per line, with the time, the source, fn or actor, and the level.
- [traces](https://developers.telnyx.com/docs/agents/cli/traces.md): The telnyx-acp traces command: shows what a conversation's runs did, step by step: each model call with its tokens and finish reason.
- [versions](https://developers.telnyx.com/docs/agents/cli/versions.md): The telnyx-acp versions command: every successful deploy is an immutable revision of the agent's function.
- [rollback](https://developers.telnyx.com/docs/agents/cli/rollback.md): The telnyx-acp rollback command: points traffic at an earlier revision. Numbers and webhooks are untouched. A revision whose build failed cannot be rolled back to.
- [delete](https://developers.telnyx.com/docs/agents/cli/delete.md): The telnyx-acp delete command: prints exactly what will change and asks once, and the answer defaults to no. Then it undoes what deploy set up, in order.
- [export](https://developers.telnyx.com/docs/agents/cli/export.md): The telnyx-acp export command: refuses a project that is already code-based and never overwrites existing files.
- [Utilities](https://developers.telnyx.com/docs/agents/cli/utilities.md): The telnyx-acp utility commands: five verbs that stand on their own, outside any one project.
- [Troubleshoot](https://developers.telnyx.com/docs/agents/troubleshoot.md): What the CLI and the platform say when something is wrong, and what it means. Deploy failures have their own section.
- [agent.json](https://developers.telnyx.com/docs/agents/reference/agent-json.md): agent.json is the agent. create writes it, add, remove, set and unset edit it, validate checks it, and deploy generates the deployable function from it.