Sublime Text has several third-party ways to add AI help, but no single assistant is established as objectively best. The right fit depends on whether you want inline completions, chat, local-model options, or an AI that can search and edit through Sublime’s editor context. The comparisons below are based on documented package features—not independent code-quality or productivity tests.
Which AI coding assistant fits your Sublime Text workflow?
| Option | Best fit | Documented interaction | Editor requirement |
|---|---|---|---|
| LSP-copilot | GitHub Copilot users who want suggestions and chat in Sublime Text | Inline completion popup, inline phantom, panel completion, and chat | Requires Sublime Text’s LSP package; the listing does not state a minimum build |
| OpenAI completion | Users who want chat and inline responses across hosted or compatible providers | Chat, project histories and settings, file or selection context, streaming, inline phantom responses, and proxy support | Build 4205 or newer for the current release line; builds 4050–4204 are directed to the frozen 6.1.0/Python 3.8-compatible line |
| LLM | Users who mainly want a chat workflow, including local inference through Ollama | Chat with the option to send a code selection | Sublime Text build 4050 or newer |
| AI Bridge | Users who want an external model to access project and editor operations through MCP | Project search, symbol-index access, syntax-aware definition extraction, and in-buffer edits | Build above ST4080 |
| AssistantAI | Users who want configurable prompts and API actions rather than one ready-made assistant | Selection-based prompts and configurable servers, endpoints, credentials, and prompt actions | Not stated in the package documentation cited here |
These are different interaction models, not a tested ranking. Choose by workflow and compatibility, then confirm the package’s current listing and provider requirements before installing; packages and external services can change independently.
As an Amazon Associate I earn from qualifying purchases.
What each option provides
LSP-copilot: inline Copilot completions and chat
LSP-copilot connects GitHub Copilot to Sublime Text through the LSP package. Its documented features include inline suggestions in a popup or phantom, panel completion, and chat. Setup requires the LSP and LSP-copilot packages, a public network connection, and an active GitHub Copilot subscription. Sign in using the command palette. The package listing reported a last update of September 28, 2026.
Crashes, No Sound, or Screen Glitches?
Random freezes, missing sound and display glitches usually trace back to one bad driver. Find and replace yours safely.Free scan · under a minutePC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11One practical wrinkle is the Tab key: Copilot completion and Sublime’s native completion may both use it, so pressing Tab can produce a nondeterministic acceptance result. The package documentation suggests considering a separate key binding or changing commit_completion_on_tab.
#1 Best Overall
OpenAI completion: multi-provider chat and inline help
OpenAI completion documents support for OpenAI Responses, Anthropic Claude, Google Gemini, and OpenAI-compatible APIs, including llama.cpp server and Ollama. Its feature set includes streaming chat, project-specific histories and settings, sending a whole file or selected text as context, inline phantom responses, and proxy support.
The current release line requires Sublime Text build 4205 or newer. Users on builds 4050–4204 are directed to the frozen 6.1.0 release line, which is compatible with Python 3.8. Hosted configurations require provider API credentials; local inference requires the relevant local software. Package Control listed version 6.3.1 for ST4205+ on September 23, 2026. That version and the release guidance are time-sensitive, so check the package page for updates.
LLM: a chat-centered package with hosted and local choices
LLM provides a chat interface for Sublime Text 4 and supports Ollama, Claude, OpenAI, OpenRouter, DeepSeek, and compatible endpoints. You can send a code selection into chat. Its listing describes local inference through Ollama as well as configuration for external providers, and specifies a minimum Sublime Text build of 4050. The listing reported a last update of June 12, 2026.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
AI Bridge: connect an external model to editor operations
AI Bridge takes a different approach from inline-completion packages: it runs an MCP server as a Sublime Text package, exposing project and editor functions such as search, symbol-index access, syntax-aware definition extraction, and in-buffer edits. Its listing says edits made through Sublime APIs remain in Sublime’s undo stack. The stated requirement is a build above ST4080, and the listing reported a latest version dated May 25, 2026.
The package documents 127.0.0.1:8765/mcp as its default local endpoint. Treat that as the documented default, not as a general guarantee about security or exposure; the cited listing does not establish those properties.
AssistantAI: a configurable prompt and API framework
AssistantAI is suited to users who want to configure prompt actions, servers, endpoints, and credentials. Its documentation describes OpenAI edit, completion, and chat-completion endpoints, as well as Gitea-related endpoints. It says an OpenAI API key and sufficient credit are required. This is better understood as a framework for configurable prompts and API actions than as a single plug-and-play coding assistant.
Rank #4
- Pages: 136
- Instrumentation: Piano/Vocal/Guitar
How to choose between them
- For Copilot-style inline suggestions: start with LSP-copilot if you already have an active Copilot subscription and are comfortable configuring LSP. Pay attention to its Tab-key interaction with Sublime’s own completions.
- For multiple providers plus inline responses: consider OpenAI completion if your Sublime build meets the release track you need and you want chat, file or selection context, and streaming in one package.
- For chat with a code selection: LLM is the clearest chat-oriented choice in the package descriptions, with Ollama among its listed options.
- For model-driven project search and edits: consider AI Bridge if you specifically want an external model to use MCP-accessible editor and project operations rather than just return a completion.
- For custom prompt actions: AssistantAI is the configurable route; expect to set up endpoints and credentials yourself.
Local inference, compatible endpoints, and a package’s support for a provider describe connection options; they do not establish equivalent privacy terms. Review the chosen provider’s own policies and configuration details before sending code.
Check compatibility, accounts, and setup before installing
- Confirm your Sublime Text build. LLM lists build 4050 as its minimum; OpenAI completion has separate current and frozen release tracks; AI Bridge requires a build above ST4080. LSP-copilot also requires the LSP package. Check the latest package listing because these requirements can change.
- Check credentials and service costs. LSP-copilot requires an active Copilot subscription. Hosted API configurations may require provider credentials, and AssistantAI’s documentation specifically calls for an OpenAI key and sufficient credit. The package listings do not establish current provider prices.
- Check network and proxy needs. LSP-copilot requires a public network connection. OpenAI completion documents proxy support; verify the relevant package and provider settings if your connection requires a proxy or certificate configuration.
- Plan for completion overlap. Sublime already provides native completions, and another package may introduce a popup or acceptance key. Review key bindings and completion settings if suggestions compete or Tab behaves unexpectedly.
How AI packages interact with Sublime’s own completions
Sublime Text’s built-in completion engine indexes project files in background processes and can use patterns from project code to produce context-aware suggestions. Its completion sources include the current file, context-aware suggestions, completion files, snippets, and plugins. Plugins can provide completions through documented event-listener APIs. AI packages therefore augment an existing completion system rather than replacing an empty editor feature set.
Best Value
For the official description of native completions and plugin extension points, see Sublime Text’s completion documentation. When adding an AI package, check whether it introduces another suggestion popup or shares an acceptance key with native completions.
What the available descriptions can—and cannot—tell you
Package listings are useful for identifying documented features, setup, and compatibility. They do not show which assistant produces the most accurate code, saves the most time, or performs best on a particular language or project. No independent benchmark or code-quality comparison is established here, so treat “best” as a fit to your workflow and requirements, not a measured winner.
For package discovery, Package Control’s AI search lists AI-labeled packages. Verify availability, release details, and provider terms at the package and service pages when you install.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
