Directory
Published directory entries matching your search.
ADK-Rust is a GitHub repository for the Rust Agent Development Kit, a flexible framework for building AI agents in Rust. It includes modular components for models, tools, memory, and realtime voice support, is model-agnostic and deployment-agnostic, and is optimized for frontier AI models.
Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...).
Aider LLM Leaderboards presents quantitative benchmarks of LLM code editing skill. The polyglot benchmark tests LLMs on 225 Exercism coding exercises in C++, Go, Java, JavaScript, Python and Rust, and benchmarks evaluate an LLM's ability to follow instructions and edit code without human intervention.
amux is an open-source control plane for AI coding agents, hosted on GitHub by mixpeek. It enables management of parallel AI coding workers including Claude Code, Codex, and Gemini, with features such as a shared task board, atomic task assignment, scheduling, origin-stamped messaging, model switching, self-healing recovery, and access via a dashboard or mobile interface. It is MIT licensed and distributed as a single Rust binary.
A DeepSeek-native terminal coding agent in Rust with OS-level sandboxing, persistent goal mode, background tasks, and verification gates.
Bloop is a fast code search engine written in Rust, distributed through GitHub releases. The repository was archived by its owner on Jan 2, 2025, and is now read-only. Release notes for versions v0.6.0 to v0.6.5 list changes such as explaining files in a user-set language, adding multiple files to code studio, code coloring for COBOL, and alternative input types for Chinese users.
burn is a next-generation tensor library and deep learning framework developed by tracel-ai. It is designed to prioritize flexibility, efficiency, and portability, with available resources covering use with Rust, its ecosystem, supported backends, and training and inference functionality.
Candle is a minimalist machine learning framework for Rust with a focus on performance, including GPU support, and ease of use. It provides examples and online browser demos for models such as whisper, LLaMA2, T5, yolo and Segment Anything.
deeplearn-rs is a Rust library for neural networks and deep learning, described by its author as mostly a proof of concept with a changing API. Implemented models include MNIST handwritten digit recognition and a char-rnn using LSTM, alongside layers such as fully connected, LSTM, softmax, and loss functions, with SGD and RMSProp optimizers. The repository was archived by its owner on Mar 8, 2024, and is read-only.
An open source machine learning framework in Rust Δ.
Deep learning in Rust, with shape checked tensors and neural networks.
goose is an open source AI agent that runs on the user's machine. It is available as a desktop app for macOS, Linux and Windows, a CLI, and an API built in Rust. The agent is general-purpose, covering code, workflows, research, writing and automation. It connects to 70+ extensions via the Model Context Protocol and works with 15+ LLM providers, including API keys or existing subscriptions.
GritQL is a declarative query language from Grit for searching and modifying source code. It lets users search with code snippets and metavariables, define custom lints, and apply auto-fix rules, and it supports rewriting JavaScript/TypeScript, Python, JSON, Java, Terraform, Solidity, CSS, Markdown, YAML, Rust, Go and SQL.
h5i is a workspace for securing web applications through two approaches: finding vulnerabilities with AI agents and proving correctness with formal verification. It provides AI agents a toolkit for browser automation, HTTP traffic manipulation and reconnaissance, and includes h5i-app, an Axum-based Rust framework for verification with Lean 4.
jcode is an open-source terminal coding agent written in Rust. It supports agent swarms, background tasks, and a small RAM footprint, and is installed with one command on macOS, Linux, or Windows. Login flows connect subscription and API model providers, and the agent itself is free while hosted inference plans are available.
Laminar is an open-source observability platform purpose-built for AI agents. It provides OpenTelemetry-native tracing with a one-line SDK setup, plain-English signals that alert in Slack, and an SDK and CLI for running evals. It is written in Rust with 20x trace compression, and can be used via a managed platform or self-hosted with Docker Compose.
Modern columnar data format for ML implemented in Rust.
A comprehensive toolkit to build Machine Learning applications with Rust.
m2cgen is a tool that transforms trained machine learning models into native code across a wide range of programming languages including Java, C, Python, Go, JavaScript, C#, R, PHP, Dart, Haskell, Ruby, F#, and Rust, with zero dependencies. Its codebase is hosted in the BayesWitnesses GitHub repository, which includes navigation for installation, development guidance, supported languages, and supported model types.
Typed graph database where agents branch and merge like Git. S3-native, Rust, traversal + vector + BM25 in one runtime.
Polars is an extremely fast open-source query engine for DataFrames written in Rust, hosted as a GitHub repository under the pola-rs organization. It is built to handle large datasets, including data volumes that exceed available system RAM.
Open-source runtime for numerical computing that executes MATLAB-syntax code. Built in Rust, it provides a compiler, a virtual machine, and JIT tiers, with a GPU backend powered by wgpu. The project targets CPU and GPU hardware and handles tensor allocations and movement automatically.
Python-free Rust inference server with OpenAI API compatibility and hot model swapping.
A pure Rust tokenizer library that reads tokenizers directly from GGUF model files, requiring no Python, C++ or separate tokenizer files. It supports SPM, BPE, WPM, RWKV and UGM tokenizers tested token-for-token against llama.cpp, and offers batch encoding with optional Rayon parallelism. MIT licensed.
