Lm

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/houtini-ai-lm

About

Use cases: model-inference, code-review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

3 read · 2 write · 0 delete · 3 not yet classified

Secrets

1 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Node.js package

Tools (8)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• chat

  Send a task to a local LLM - a sidekick running on the user's hardware or a configured OpenAI-compatible endpoint. It does not consume the user's Claude quota. Trades latency for tokens: local inference is typically 3-30× slower than frontier models, so delegation wins when the task is bounded and self-contained. Good fit: • Explain or summarise code/docs you already have in context • Generate boilerplate, test stubs, type definitions, mock data • Answer factual questions about languages, frameworks, APIs • Draft commit messages, PR descriptions, comments • Translate or reformat content (JSON…

• code_task

  Send a code-specific task to the local LLM, wrapped with an optimised code-review system prompt. Temperature is locked low (0.2 or the routed model's hint) for deterministic output. Good fit: • Explain what a function/class does • Find bugs or suggest improvements • Generate unit tests or type definitions for existing code • Add error handling, logging, or validation • Convert between languages or patterns For best results: • Provide COMPLETE source - the local LLM cannot read files. • Include imports and type definitions so the model has full context. • Be specific: "Write 3 Jest tests for …

• code_task_files

  Like code_task, but the local LLM reads files directly from disk - source never passes through the MCP client's context window. Use when reviewing multiple files or a single large file. How it works: • Provide absolute paths. Relative paths are rejected. • Files are read in parallel (Promise.allSettled) - one unreadable file does not sink the call. • Files are concatenated with `=== filename ===` headers and sent to the same code-review pipeline as code_task. • Read failures are surfaced inline with the reason so the LLM can still reason about the rest. • Pre-flight prefill estimate: if measu…

• custom_prompt

  Structured analysis via the local LLM with explicit system/context/instruction separation. The 3-part format prevents context bleed in smaller models - the local LLM acknowledges the context in a fake assistant turn before receiving the instruction. Good fit when prompt structure matters: • Code review - paste full source, ask for bugs/improvements • Comparison - paste two implementations, ask which is better and why • Refactoring suggestions - paste code, ask for a cleaner version • Content analysis - paste text, ask for structure/tone/issues • Any task where separating context from instruct…

• discover

  Check whether the local LLM is online and what model is loaded. Returns model name, context window size, response latency, and cumulative session stats (tokens offloaded so far). Call this if you are unsure whether the local LLM is available before delegating work. Fast - typically responds in under 1 second, or returns an offline status within 5 seconds if the host is unreachable.

• embed

  Generate text embeddings via the local LLM server. Requires an embedding model to be loaded (e.g. Nomic Embed). Returns a vector representation of the input text for semantic search, similarity comparison, or RAG pipelines. Uses the OpenAI-compatible /v1/embeddings endpoint.

• list_models

  List all models on the local LLM server - both loaded (ready) and available (downloaded but not active). Shows rich metadata for each model: type (llm/vlm/embeddings), architecture, quantization, context window, and a capability profile describing what the model is best at. Use this to understand which models are available and suggest switching when a different model would suit the task better.

• stats

  Show user stats: tokens offloaded, calls made, per-model performance - for the current session AND lifetime (persisted in SQLite at ~/.houtini-lm/model-cache.db). Unlike `discover` which includes the model catalog, `stats` returns just the numbers in a compact markdown table - cheap to call repeatedly to see the 💰 offloaded counter climb. Useful for quantifying how much work the local model is genuinely doing, and for noticing when a model's reasoning-token ratio is drifting.

Signals

Stars

121

Forks

26

Open issues

0

Contributors

5

Weekly downloads

175

Last commit

Oct 10, 2026 (18 days ago)

Last release

Oct 7, 2026 (21 days ago)

Last package publish

Oct 7, 2026 (21 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.houtini-ai/lm

Version

3.3.4

Auth

API key

Packages

npm @houtini/lm

License

Apache-2.0

Repository

github.com/houtini-ai/houtini-lm

Website

houtini.com

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql