Neuron Companion by SADATA (v1.31.0)

Use Neuron directly inside VS Code. Ask questions, understand your project, choose how Neuron works, and keep an eye on your usage — without leaving your editor.

Get started

1. Install Neuron Companion from the VS Code Marketplace.
2. Select the Neuron icon in the Activity Bar.
3. Choose Login with Neuron and finish signing in in your browser.
4. Open VS Code Chat, choose a model from Neuron, and start asking questions.

You do not need to copy an API key into VS Code. Your sign-in is managed securely by VS Code and is removed when you log out.

Use Neuron+ Cloud Memory & Knowledge Layer

Neuron Companion provides Neuron+ Cloud Memory as a native Model Context Protocol (MCP) server in VS Code. Registration happens automatically in the background the first time MCP is used: the extension resolves your authenticated account email via /v1/me, registers an account-bound identifier alongside a per-device client id (vscode-<hash>) at NCM's /v1/keys/signup, stores the returned API key in VS Code SecretStorage, and sends it through the x-api-key header. All devices and desktop apps using your Neuron account share one synchronized long-term memory and knowledge base without evicting each other's credentials.

Cloud Memory is the primary long-term memory Neuron uses. In Neuron's own chat view the editor's local memory tool is withheld, so what Neuron learns is written to one shared store rather than split between a local file and the cloud. Neuron recalls relevant context when a task starts and stores durable facts — decisions, root causes, project conventions — when one is settled.

Team Wiki & Published Skills

Cloud Memory also acts as your team's knowledge repository:

• Team Wiki: Neuron accesses your team's durable product rules, domain vocabulary, and runbooks via wiki_search and wiki_read. When asked about product behavior or business rationale not found in the codebase, Neuron checks the wiki first. Wiki page creation (wiki_write) is gated and only triggers on explicit user request.
• Dynamic Published Skills: Custom procedures published by your team through the Cloud Memory dashboard are automatically discovered via MCP. When a task matches an established procedure, Neuron discovers it via skill_list and executes the steps.
• Mode Safety: Ask and Plan modes can read memory, search the wiki, and use published skill procedures, but can never write memories or publish wiki pages. Read-only skills are preserved even if named after action verbs.

Code Map

Cloud Memory can also answer structural questions about your project: what a file exposes, what calls a given function, what a change would affect, how one module reaches another, and which stored memories describe code that has since changed.

The server never reads your filesystem, so it only knows what you send it. Run Neuron: Index Codebase from the Command Palette to parse your project locally and upload its structure — files, the symbols they define, imports, call relationships, and any HTTP routes. Until you do, those questions come back empty, which reads as "nothing depends on this".

Indexing is manual by design: it describes the shape of your code, so it runs when you ask and at no other time. There is no watcher and no background upload. Re-run it when the structure has moved on — each push replaces the previous map, so deleted files stop being reported as dependents. Only structure is sent, never file contents, comments, or string literals.

Chat with Neuron

Neuron works in VS Code Chat, so you can ask questions while you work. Responses appear as they are generated, and Neuron can use the tools available in VS Code when you allow it. The model list is based on the models available to your Neuron account, so it can be different for each person. It is kept up to date in the background while you are signed in, so Neuron models stay in the Chat model picker without a manual refresh.

Making long conversations cheaper

The largest saving comes from not paying twice for the same text. Everything that repeats on every turn — the instruction preamble, the tool list, the skills index, and the conversation so far — is sent in a byte-identical form each time, which is what lets the service charge a fraction of the normal rate for it. Neuron keeps that part stable on purpose: the tool list is ordered deterministically, and recalled memory is appended once rather than re-inserted, because a single byte moving would undo the discount for everything behind it.

Codebase search results are excerpts rather than whole chunks, for the same reason they cite a file and line range: they are pointers to open, not the file itself.

Neuron can also render the bulky repeated parts of a request into compact images, which cost a model far fewer tokens than the same content as text. That is switched off in this release while it has another look, so requests currently go out in their plain form. Caching, described above, does most of the saving and is unaffected.

Built for long sessions

Neuron is designed to stay responsive during long working sessions:

• Streaming text is delivered in small batches to reduce rendering and extension-host overhead.
• Prompt preparation reuses local context and model work instead of repeatedly scanning the same data.
• Automatic indexing yields between batches, pauses while a prompt is active, and resumes only when there is pending workspace work.
• Sidebar polling and gateway checks pause when VS Code is unfocused or the panel is hidden. Endpoint health checks also stop while you have an endpoint pinned, because there is no route left to choose.
• Timers, watchers, network requests, and background embedding work are cancelled when their panel, request, or extension lifecycle ends.
• Model catalogs and runtime caches avoid duplicate updates and remain bounded during long-running sessions.

Skills Neuron already knows

Neuron ships with a library of expert playbooks — backend architecture, code review, refactoring, documentation, testing, security, cloud, and DevOps. They are active as soon as the extension is installed, with nothing to configure.

You do not need to name one. When your request matches a playbook, Neuron reads it and follows it; the rest stay out of the way. Because only a short index of the available skills travels with each request, having many of them does not slow your conversations down.

To add your own, create a folder per skill under .neuron/skills/ in your project, each with a SKILL.md describing what it is for and when to use it. A skill you write replaces a built-in one with the same name. Reload the window after adding one.

Understand your project

Neuron can search your project by meaning, not only by exact words. This makes it easier to ask questions such as:

“Where is the login flow handled?”

How it works

• A project index is prepared automatically after you open a workspace and sign in. The first pass always runs to completion; later refreshes step aside while you are chatting.
• The index updates after your files change, so you can keep working without rebuilding it manually.
• The Codebase Index row near the bottom of the Neuron sidebar shows the current status.
• Run Neuron: Index Workspace (Semantic Search) from the Command Palette whenever you want to start an immediate refresh.
• You can ask Neuron to find relevant parts of your project directly from Chat.

The automatic index is created on your device by default. If you manually start an index and on-device processing is unavailable, Neuron may use its embedding service as a fallback. In that case, the selected source excerpts are sent to Neuron for processing. You can turn off automatic indexing in VS Code Settings by searching for Neuron: Auto Index.

Personalize how Neuron works

Open the Neuron sidebar to adjust the experience. Endpoint settings remain in the Options tab; the active reasoning setting is now shown above Context Window in the status card.

Reasoning Effort

Choose how much time Neuron should spend thinking from the Reasoning Effort control above Context Window:

• Smart Adaptive — Neuron chooses automatically for each question.
• Low — faster answers for simple requests.
• Medium — a balanced setting for everyday work.
• High — more careful reasoning for complex questions.
• XHigh — strong reasoning for demanding problems.
• Max — the deepest available reasoning.

Smart Adaptive uses a lightweight local heuristic rather than an additional classifier request. It considers prompt length, coding and debugging signals, structured details, conversation depth, and tool history, then adjusts both the reasoning tier and response budget from no extra reasoning through Max. It does not send a second classification request or exceed the model's output limit.

Models that do not support reasoning are skipped entirely. Neuron reads this from its own model list, so no thinking tier is sent to a model that cannot use one, and such a model keeps its full response length instead of being shortened to match a setting it never honours.

During longer conversations, Neuron also enables ephemeral prompt caching for repeated request prefixes when supported by the Neuron Messages API.

Context Window

Neuron follows each model's own context window, so there is nothing to configure. VS Code manages the conversation history it sends, and Neuron shortens an over-long conversation only as a last resort so a request never fails outright — even when the model's rejection names no numbers for Neuron to learn from. Models with larger windows use their full advertised capacity, and Neuron reports that same figure to VS Code — so VS Code does not build a prompt larger than Neuron will actually send.

The Context Window row near the bottom of the sidebar, alongside Codebase Index, shows how much of the usable prompt space your latest request consumed. The bar reads left to right: a striped block for space Neuron holds back on purpose — room for the reply, tool and request overhead, and a small estimation safety margin — then a solid segment for what your last request actually used, then whatever is still free. A thin marker inside the used region shows the session's highest usage for that model, so a single large request no longer leaves the reading pinned at 100%.

Hover the row for the exact breakdown, including the current prompt, the session peak, each protected segment, and whether older turns were trimmed. The row stays visible when you switch between tabs and remembers the last value when you close and reopen the sidebar. The value is available for requests sent through a Neuron model; VS Code does not expose token usage from other providers such as Copilot models.

Explore / Subagent Model

Choose which model should handle work delegated by VS Code’s Explore or subagent experience. Auto [VS Code] uses VS Code’s own model selection; Neuron+ Agent lets Neuron choose automatically. The remaining choices pin a specific Neuron model.

Planner Model

Choose which model should be used by VS Code’s built-in Plan experience. Auto [VS Code] uses VS Code’s own model selection; Neuron+ Agent lets Neuron choose automatically. The available choices depend on the models supported by your account.

Endpoint

Neuron currently runs on a single endpoint, so there is nothing to choose between and the picker is not shown. Requests go straight there, and no endpoint health checks run in the background. The picker and Neuron+ Smart Adaptive routing return when more endpoints are available.

Audit Transcripts

By default, completed chat turns are recorded to Neuron Cloud Memory's audit log in the background for compliance and audit trail analysis (neuronChat.auditTranscripts). This runs asynchronously without delaying chat responses. You can toggle this setting in VS Code preferences at any time.

See your usage

The Neuron sidebar includes four tabs:

• Limits — see your current limits, how much is left in each time window, and use available reset credits to instantly restore your quota on demand.
• Tokens — see today’s, last 7 days’, and all-time usage, plus your most-used models.
• Models — choose the model for Explore/subagent work and the Planner.
• Options — customize model selection and endpoint behavior.

The Reasoning Effort, Context Window, Codebase Index, and Cloud Memory rows sit together near the bottom of the sidebar, so the active reasoning mode, prompt usage, indexing state, and memory connection stay easy to check while you work.

The dashboard refreshes automatically while you are signed in. You can also refresh it manually. Hover over a usage percentage to see the exact count when that detail is available. Limits that reset every minute or less show no reset time, because it would be out of date almost as soon as it appeared.

Updates and helpful shortcuts

• When a newer Neuron Companion version is available, the sidebar shows an update indicator and the panel displays an update notice.
• The update notice includes a button that opens the extension’s update page in VS Code.
• The Web Panel button opens the Neuron web panel in your browser.
• The Status button opens the current Neuron model and service status page.
• A What’s New page opens after an update, and you can reopen it anytime from the Command Palette.

Commands

Open the VS Code Command Palette with ⇧⌘P on macOS or Ctrl+Shift+P on Windows and Linux.

Privacy at a glance

• Chat messages are sent to Neuron so Neuron can answer your questions.
• Completed chat transcripts are asynchronously recorded to Neuron Cloud Memory for audit logging; this can be turned off in VS Code settings (neuronChat.auditTranscripts).
• Sanitized extension-host errors may be sent to Sentry for reliability monitoring. Prompt content, workspace files, request bodies, user identity, and tool data are removed before reporting. This monitoring is independent of VS Code's telemetry setting.
• Automatic project indexing is performed on your device by default.
• Manual indexing can use Neuron’s embedding service as a fallback when local processing is unavailable; only the selected source excerpts needed for that process are sent.
• Your sign-in is stored by VS Code and is removed when you choose Log out.

Requirements

• Visual Studio Code 1.125 or newer.
• A Neuron account.
• An active internet connection for sign-in, Chat responses, usage information, and model/service status.

Feedback and support

If something does not work as expected, open an issue on GitHub Issues or contact SADATA Helpdesk.