llmvm

Library Listed Dormant

A protocol and modular application suite for language models.

Checked · Sources

Downloads
78
Dependents
0
Stars
105
Forks
3
Contributors
3
Commits
81
Latest release
0.1.1 ·

About

From the project README ·

A protocol and modular application suite for language models.

Includes a code assistant that automatically retrieves context, powered by LSP.

Overview

llmvm consists of three types of executable applications:

  • Frontends: specialized applications that use language models
  • The core: acts as middleman between frontend and backend; manages state related to text generation, such as:
    • Model presets
    • Prompt templates
    • Message threads
    • Projects/workspaces
  • Backends: wrappers for language models, handles raw text generation requests

The protocol acts as the glue between the above applications. Uses multilink and tower to achieve this.

Available crates
  • Frontends
    • codeassist: A LLM-powered code assistant that automatically retrieves context (i.e. type definitions) from a Language Server Protocol server
    • chat: A CLI chat interface
  • Core
  • Backends
    • outsource: Forwards generation requests to known hosted language model providers such as OpenAI, Anthropic, Hugging Face and Ollama.
    • llmrs: Uses the llm crate to process generation requests. Supported models include LLaMA, GPT-2, GPT-J and more.
IPC details

Each component can interact with a dependency component via three methods:

Read the full README
  • Local child process: the component invokes the dependency component as a child process, and communicates via stdio using JSON-RPC
  • Remote HTTP service: the dependency component acts as a HTTP API, and the dependent component is configured to make web requests to the API
  • Direct linking: The core and backends have library crates which can be used directly. Only works if dependent component is a Rust application.

This allows for some flexible hosting configurations. Here are some examples:

Hosting scenarios

Benefits
  • Single protocol for state-managed text generation requests
  • A frontend or backend can be implemented in any language, only requires a stdio and/or HTTP server/client to be available.
  • Uses Handlebars for prompt templates, allowing powerful prompt generation
  • Saves message threads, presets and prompt templates on the filesystem for easy editing/tweaking
  • Workspace / project management for isolating project state from global state
  • Modular design; any component can by invoked by the user via CLI for a one-off low-level or high-level request.

Installation

cargo is needed to install the binaries. Use rustup to install cargo.

Install the core by running:

cargo install llmvm-core

Install the desired frontends & backends listed under "Available crates". See their READMEs for more details.

Usage / configuration

See the README of each relevant component for more information on usage and configuration.

Model IDs

Model IDs in llmvm are strings consisting of three parts:

<backend name>/<provider name>/<model name>

The provider name must have the suffix -chat or -text

Examples:

  • outsource/openai-chat/gpt-3.5-turbo
  • outsource/anthropic-chat/claude-3-5-sonnet-20240620
  • llmrs/llmrs-text/mpt-7b-chat-q4_0-ggjt

By default, the core will invoke the process llmvm-<backend name> for local process communication.

Presets / Projects / Threads / Prompt Templates

See the core README for more information.

Model weights

See the relevant backend README (i.e. llmrs).

License

Mozilla Public License, version 2.0

Runs on
GPU support unknown
What shows it
  • no dependency or feature matches a backend row
Native code
None found
  • No native code found
Python bindings
No Python binding crate found
License
MPL-2.0

Compare with similar projects

Order: strongest tier first, then most downloads, then name, with unmeasured values last. A library counts downloads over 30 days. An app counts binary downloads per release. An app with none counts its crate downloads over 30 days. ML Rust runs this catalogue, so its closest project always gets a row.

llmvm beside the projects that share a topic with it
ProjectDownloadsDependentsStarsLatest releaseRuns on (GPU)Native codeLicense
llmvm This page Listed Dormant

A protocol and modular application suite for language models.

78 downloads over 30 days 0 105 0.1.1 GPU support unknown No native code found MPL-2.0
rust-genai Featured

Multi-AI Providers Library for Rust. (OpenAI, Gemini, Anthropic, DeepSeek, Ollama, OMLX, AWS Bedrock, Vertex, Xai, Groq, Kimi, GLM and many more)

118,643 downloads over 30 days 81 938 0.7.3 GPU support unknown No native code found Apache-2.0 OR MIT
ChatGPT App Listed Dormant

❄️ ChatGPT Desktop Application (Mac, Windows and Linux)

1,411,000 binary downloads per release Not applicable 54,663 Not measured Not measured None stated
aisdk Listed

An open-source Rust library for building AI-powered applications, inspired by the Vercel AI SDK. It provides a robust, type-safe, and easy-to-use interface for interacting with various Large Language Models (LLMs).

36,877 downloads over 30 days 4 263 0.6.1 GPU support unknown No native code found MIT
oatmeal App Listed Dormant

Terminal UI to chat with large language models (LLM) using different model backends, and integrations with your favourite editors!

5,642 binary downloads per release Not applicable 772 0.13.0 GPU support unknown No native code found MIT

A unified source of truth for LLM providers, models, pricing, and capabilities.

604 downloads over 30 days 4 2 0.14.4 GPU support unknown No native code found MIT
blazr App Listed

Inference server for LLMs, speech and embeddings: OpenAI-compatible routes with streaming, plus speech synthesis (TTS) and transcription (ASR). Serves Llama, Mistral, Qwen, Mamba2, MLA+MoE and hybrid models from SafeTensors, AWQ, GPTQ and GGUF.

8 binary downloads per release Not applicable 7 0.7.1 CUDA, WebGPU Binds native code: ring (feature distributed) Apache-2.0
Why ListedNo archive, New or Featured rule places it, so it is Listed.

What it lacks for Featured

  • It has 0 active dependents and 0 new dependents in 365 days. Featured needs 11 active dependents or 9 new dependents in 365 days. The repository route reads 105 stars, 3 forks and 3 contributors. It needs 4,539 stars, 434 forks and 79 contributors together.
  • Docs are missing: the primary crate publishes no README.
  • The project is dormant and not finished. Dormancy rule

What else the check found

  • The last activity is on 21 Feb 2025, 626 days ago. That reaches the 365 days the rules expect, so the project is dormant. Dormancy rule
  • The oldest outside issue waits 1026 days for a reply, past the limit of 270. No maintainer replied in 365 days. Rot signals rule

Not measured: Latest release fails cargo check.

Exact rules: Listed, Featured library. The check on applied thresholds version 9.

Every rule outcome, as the check records it
  • expected-interval: version 0.1.1 base 300, capped at 1 releases = 50, raised to the 365-day floor: E = 365 days
  • dormancy: last activity 2025-02-21, 626 days ago, E = 365: dormant
  • rot: oldest unanswered issue 1026 days (limit 270), no maintainer reply in 365 days
  • featured: not featured: active_users 0 < 11 and new_adopters 0 < 9 and repository route stars 105 (needs 4539), forks 3 (needs 434), contributors 3 (needs 79); docs missing; dormant and not stable
  • listed: listed: no archive, new or featured rule applies
Crates9 crates

Measurements and sources

Each signal row shows the raw value, its source and the fetch date. The Sources list gathers every distinct source on this page. Movement needs more history.

Sources6 sources
Adoption0 active dependents, 0 new dependents in 365 days1 not measured
Adoption measurements
SignalValueSourceFetchedCounts
Active dependents0crates.io database dumpYes
New dependents (365 days)0crates.io database dumpYes
Peak active dependents0crates.io database dumpYes
Active dependents as a share of the peak1crates.io database dumpYes
Binary downloads per releaseNot measuredYes
MaintenanceLatest human commit: 20 months ago3 not measured
Maintenance measurements
SignalValueSourceFetchedCounts
Latest human commit2025-02-21GitHub repositoryYes
Latest release2024-12-13crates.io database dumpYes
First release2023-08-09crates.io database dumpYes
Latest version0.1.1crates.io database dumpYes
Days the oldest outside issue waits for a reply1026GitHub repositoryYes
Maintainer replies over 365 days0GitHub repositoryYes
Repository archivedfalseGitHub repositoryYes
Repository gonefalseGitHub repositoryYes
Release commit or manifest in the repotruecrates.io packageYes
Published docsfalsecrates.io database dumpYes
Latest release fails cargo checkNot measuredYes
Build check dateNot measuredYes
Build check toolchainNot measuredYes
SecurityUnpatched vulnerabilities: none
Security measurements
SignalValueSourceFetchedCounts
Unpatched vulnerabilities past the grace windownoneRustSec advisory databaseYes
RustSec unmaintained advisorynoneRustSec advisory databaseYes
Deprecation noticenonecrates.io database dumpYes
Deprecated requirementnonecrates.io database dumpYes
Distribution1 releases, 78 downloads over 30 days5 not measured
Distribution measurements
SignalValueSourceFetchedCounts
Releases1crates.io database dumpYes
Downloads over 30 days78crates.io database dumpYes
Binary downloads over the last 3 releasesNot measuredYes
Homebrew installs on request over 365 daysNot measuredYes
Repology repository familiesNot measuredYes
Docker pull growth over 90 daysNot measuredYes
Docker pulls at the growth baselineNot measuredYes
Every version a prereleasefalsecrates.io database dumpYes
Every version 0.0.xfalsecrates.io database dumpYes
Every version yankedfalsecrates.io database dumpYes
Crate deleted from crates.iofalsecrates.io database dumpYes
Repository105 stars, 3 forks, 3 contributors, 81 commits. Stars alone never qualify a project.
Repository measurements
SignalValueSourceFetchedCounts
GitHub stars105GitHub repositoryYes — one part of the repository route
GitHub forks3GitHub repositoryYes — one part of the repository route
Contributors with a GitHub account3GitHub contributorsYes — one part of the repository route
Commits on the default branch81GitHub repositoryNo
Repository's main crate left out of the entrynonecrates.io database dumpYes
Facts that never count
Facts that never count measurements
SignalValueSourceFetchedCounts
LicenseMPL-2.0crates.io database dumpNo
Runs on, from listed crates and their direct dependenciesGPU support unknowncrates.io database dumpNo
What shows each backendno dependency or feature matches a backend rowcrates.io database dumpNo
Native code, from listed crates and their dependenciesNo native code foundcrates.io database dumpNo
Python bindings, from direct dependencies of listed cratesNo Python binding crate foundcrates.io database dumpNo
Crates that depend on a listed crate directly0crates.io database dumpNo

Corrections and review history

Report a correction

No correction applies to this entry.

Judgments

A judgment enters only through an approved issue and a merged pull request.

No judgment applies to this entry.