Chats and agents · LocalAI

Chats

Mon, 01 Jan 0001 00:00:00 +0000

Chats are conversations that the server keeps. You can keep typing while the model works, the model can hand work to sub-agents, long conversations are compacted for you, and the model can use the MCP servers of its model configuration. The chats API sits beside the OpenAI-compatible /v1/chat/completions endpoint, which does not change. Use /v1 when a client brings its own history and needs the OpenAI format. Use /api/chats when the server should keep the conversation.

Saved agents, triggers and inbox

Mon, 01 Jan 0001 00:00:00 +0000

A saved agent is a definition you can start a chat with. It has instructions and four lists: the MCP servers, add-ons, collections and skills the chat may use. Triggers and the inbox build on agents and are described on this page too. Saved agents An agent has: Field Meaning name 1 to 80 characters. Unique for you, ignoring case. description A short note for you. instructions Text added to the system prompt of every turn. At most 32 KiB. model Optional. The chat uses this model. Chat-capable model aliases can also be selected; the agent saves the alias name, not its target name. Without it, the chat is created with the model you choose. mcp_servers Names of servers in the model’s MCP configuration, and your MCP connectors as connector:. The form lists both as a picker; it does not take free text. A save that adds a connector: you have not defined, or, for an agent with a fixed model, a name that is not one of that model’s MCP servers, is a 400 ("… is not one of your MCP connectors"). A name the agent already holds is kept, so an older agent still loads and saves; the form shows it as Not defined with a remove button, the Effective view says it is ignored, and the agent’s chats skip it. addons IDs of installed add-ons. collections Names of your collections. skills Names of skills. The index of skills and the load_skill tool of the chat offer only these. builtins_off Groups of built-in tools the agent’s chats never have: shell, files, web, media, collections, subagents, triggers, changes, localai_client (the inference tools) and localai_admin (the server-management tools). It is a ceiling: a chat with the agent shows the group switched off and cannot switch it on. Empty (the default): the chat has every group it has by default. A group this server does not offer is dropped. builtins_on Opt-in groups of built-in tools that chats with the agent start with: saved_agents and localai_admin. The chat can switch them off. localai_admin is for administrators and is never offered in a messaging chat or a run that starts by itself, whatever the agent says. network The network of the Sandbox commands of the agent’s trigger and connector runs: off (the default), registries (the package registries) or all (every public host), capped by the administrator’s chats_egress_ceiling. A run never shows a card: a host outside it is blocked, and the block is in the run’s output. A chat you start with the agent starts with this preset too; you change it in the chat’s Tools menu. The agent form sets it in the add-ons fold. folders Optional. Up to 8 folders of your files that chats with the agent work in, each with its own mode: read or write. folder is the same with one entry. Without them the agent works on all your files. See Folders of an agent. The agent form shows the same Tools list as the Tools menu of a chat, with a short description under each switch: the built-in tool groups, the add-ons, your connectors, and the skills. What you switch on is saved in addons, mcp_servers and skills; what you switch off among the built-in groups is saved in builtins_off.

Agent tasks and jobs

Mon, 01 Jan 0001 00:00:00 +0000

A task is a saved prompt template. A job is one run of a task: a chat that runs in the background, as the owner of the task, with the same loop as every other chat. Use them to call LocalAI from a script, a CI pipeline or another service: start a job with parameters, poll it, and read the answer, or have LocalAI call a webhook when it ends. The API keeps the paths and the JSON it had before the chats. A job is an ordinary chat with origin job, so you can open it from All chats and read its transcript.

Short memory

Mon, 01 Jan 0001 00:00:00 +0000

Memory is built into LocalAI. It gives your chats a few notes about you. The model reads the note that matches a request before it answers, and by default it saves a new note only after you confirm it. You can change that in your account settings. Nothing needs to be installed. It is for the facts that change what a good answer is: where you live, what you eat, the language and units you use, how you want answers. It is not a store for large documents. Use Knowledge to search many files.

Context compression

Mon, 01 Jan 0001 00:00:00 +0000

Configure automatic compression for long chat histories

LocalAI Assistant

Mon, 01 Jan 0001 00:00:00 +0000

An admin-only chat that installs models, manages backends and checks the status of your LocalAI instance.

Terminal agent

Mon, 01 Jan 0001 00:00:00 +0000

Use local-ai chat, an agent in your shell that reads files and runs commands behind an approval gate.

Model Context Protocol (MCP)

Mon, 01 Jan 0001 00:00:00 +0000

Agentic capabilities with Model Context Protocol integration

Search the web in chats

Mon, 01 Jan 0001 00:00:00 +0000

A chat can search the web and read web pages with two built-in tools, with no add-on and no key.

Make LocalAI yours

Mon, 01 Jan 0001 00:00:00 +0000

You can change how LocalAI looks and behaves for you by asking for it in a chat: the name and the instructions of the assistant, what it knows about you, the shortcuts of the message box, the widgets on Home, the look, and small tools of your own (pages). Every change is a file in your home folder, so it has a history, it can be undone, and the settings pages edit the same files. The settings files are in the LocalAI/ folder of your home; pages are in pages/.