Best tools for Open Source Contribution

AI agent dev environment with parallel git worktrees, magic git commands, and Linear integration.

Jean is an open-source desktop dev environment for AI agents from coolLabs (the team behind Coolify). It runs multiple coding agents — Claude Code, Codex, and others — in parallel inside isolated git worktrees, each with its own chat session and terminal. Magic git commands handle commits, PR descriptions, code reviews, and merge conflicts with AI assistance, while built-in Linear and GitHub integrations load issue context into every session.

Open-source visual editor for React — self-hostable core, optional Puck Cloud

Puck is an open-source visual page builder for React that gives teams a drag-and-drop editor backed by their own components. The MIT-licensed core remains self-hostable and persists plain JSON, while Puck Cloud and Puck AI now add optional hosted and agentic editing layers. With 12.8K+ stars, it is the dev-first visual editor to watch.

Open-source async coding agent you can run in your own sandbox

Open-source framework from LangChain AI for building your organization's internal coding agent — the same pattern Stripe's Minions, Ramp's Inspect, and Coinbase's Cloudbot follow. Built on LangGraph and Deep Agents, Open SWE runs each task in an isolated cloud sandbox (Modal, Daytona, Runloop, or LangSmith), invokes from Slack, Linear, or GitHub, orchestrates subagents, and opens pull requests autonomously — customizable end-to-end for your codebase and conventions.

Open-source i18n and translation platform

Tolgee is an open-source internationalization platform that enables in-context translation directly within applications. Translators hold ALT and click any element to edit strings inline without touching code files. It integrates machine translation from DeepL, Google, and AWS, with SDKs for React, Angular, Next.js, Vue, and Svelte. Self-hostable for data sovereignty with granular team permissions.

Build native Node.js addons in Rust via Node-API

napi-rs is a framework for building compiled Node.js native addons in Rust through the Node-API interface, eliminating node-gyp and C++ toolchains. It provides async/await with Promise integration, extensive type mappings between Rust and JavaScript, and cross-compilation to Windows, macOS, Linux, FreeBSD, and Android across x64, ARM, and RISC-V. Used by major JS tooling projects, napi-rs enables Rust-speed performance in Node.js apps.

Modular AI prompt framework for everyday tasks

Fabric is an open-source framework that organizes AI prompts into reusable patterns for solving everyday tasks like summarizing content, explaining code, extracting insights from videos, and generating social media posts. Written in Go with support for 20+ AI providers including OpenAI, Claude, Gemini, and Ollama, it runs from the command line and can serve as a REST API. With 40,000+ GitHub stars, Fabric bridges the gap between AI capabilities and practical workflow automation.

50x faster LLM gateway with MCP support, built in Go

Bifrost is a high-performance open-source AI gateway built from scratch in Go. Unifies access to 15+ providers and 1,000+ models through a single OpenAI-compatible API with only 11 microsecond overhead per request at 5K RPS — 50x faster than LiteLLM. Features automatic failover, load balancing, semantic caching, and functions as both MCP client and MCP server. Apache 2.0 licensed.

DeepSeek's FP8 general matrix multiplication kernels for efficient inference

DeepGEMM is DeepSeek's open-source library of FP8 matrix multiplication CUDA kernels optimized for LLM inference and training on modern NVIDIA GPUs. It provides efficient GEMM operations using 8-bit floating point precision that reduce memory bandwidth requirements while maintaining model accuracy. Designed for integration into inference engines and training frameworks. Over 6,300 GitHub stars.

DeepSeek's expert-parallel communication library for MoE model training

DeepEP is DeepSeek's open-source communication library optimized for expert-parallel training of Mixture-of-Experts models. It provides efficient GPU-to-GPU data routing for distributing tokens to expert networks across multiple devices during MoE model training and inference. Enables the distributed expert parallelism that powers DeepSeek's competitive model efficiency. Over 9,100 GitHub stars.

DeepSeek's optimized attention kernel for Multi-Head Latent Attention

FlashMLA is DeepSeek's MIT-licensed CUDA kernel library for optimized attention in DeepSeek-V3 and DeepSeek-V3.2-Exp style inference. It includes dense MLA decoding plus sparse attention kernels for DeepSeek Sparse Attention, with README-reported H800/CUDA metrics up to 3000 GB/s, 660 TFLOPS, and sparse 640/410 TFlops paths. It has 12.7K+ GitHub stars.

End-to-end open-source platform for training and evaluating foundation models

Oumi is an end-to-end open-source platform for training, fine-tuning, and evaluating foundation models at any scale. It covers data preparation, distributed training, reinforcement learning from human feedback, evaluation benchmarks, and model deployment in a unified framework. Supports training from scratch to post-training alignment with over 9,100 GitHub stars.

OpenAI's open-source speech recognition model for any language

Whisper is OpenAI's open-source automatic speech recognition model trained on 680,000 hours of multilingual audio data. It supports transcription and translation across 99 languages with robust handling of accents, background noise, and technical vocabulary. Available in multiple model sizes from tiny (39M) to large (1.5B parameters) for balancing accuracy and speed.

Meta's official PyTorch library for LLM fine-tuning

torchtune is Meta's official PyTorch-native library for fine-tuning large language models. It provides composable building blocks for training recipes covering LoRA, QLoRA, full fine-tuning, DPO, and knowledge distillation. Supports Llama, Mistral, Gemma, Qwen, and Phi model families with distributed training across multiple GPUs. Designed as a hackable, dependency-minimal alternative to higher-level frameworks.

Unified framework for fine-tuning 100+ large language models

LLaMA-Factory is an open-source toolkit providing a unified interface for fine-tuning over 100 LLMs and vision-language models. It supports SFT, RLHF with PPO and DPO, LoRA and QLoRA for memory-efficient training, and continuous pre-training. The LLaMA Board web UI enables no-code configuration, while CLI and YAML workflows serve advanced users. Integrates with Hugging Face, ModelScope, vLLM, and SGLang for model deployment.

Benchmark for evaluating AI coding agents on real GitHub issues

SWE-bench is a benchmark from Princeton NLP that evaluates AI coding agents by testing their ability to resolve real GitHub issues from popular open-source projects. Each task provides an issue description and repository state, and the agent must produce a working patch that passes the project's test suite. With 4,600+ GitHub stars, it has become the standard yardstick for comparing autonomous coding tools like Devin, Claude Code, and OpenHands.

CLI that writes your git commit messages with AI

aicommits is a lightweight CLI tool that generates git commit messages using AI by analyzing your staged changes. Supports OpenAI, Anthropic, and local models via multiple providers. Configure message style, language, and conventional commit format. 8,800+ GitHub stars, MIT licensed. Built by Nutlope (Hassan El Mghari), known for popular open-source AI projects. Install via npm and run 'aicommits' to generate a message from your current diff.

AI-generated git commit messages in 1 second

OpenCommit is a CLI tool that generates meaningful git commit messages using LLMs in about one second. It analyzes staged changes and produces conventional commit-style messages following your team's conventions. Supports OpenAI, Anthropic Claude, Ollama local models, and other providers. 7,200+ GitHub stars, MIT licensed, winner of GitHub 2023 Hackathon. Works as a CLI command, git hook, or GitHub Action for automated commit message generation.

AI-native Git client with virtual branches and smart commits

GitButler is a source-available Git client for virtual/stacked branches, AI-assisted workflows, and intelligent conflict resolution. Co-founded by Scott Chacon, it helps developers organize commits and work on multiple changes simultaneously. 21K+ GitHub stars; FSL-1.1-MIT license model.

Official MCP server for GitHub repo operations

GitHub MCP Server is the official Model Context Protocol server from GitHub that connects AI assistants to repositories, issues, pull requests, workflows, and code search. It exposes 100+ operations with toolset filtering, permission scoping, and audit logging, available in both remote-hosted and self-hosted Docker deployment modes.

Pull Requests as a Service with AI + developers

GitStart is a YC-backed platform that delivers merge-ready pull requests by combining AI coding agents with human developer oversight. Teams assign sprint-sized tickets and the AI Ticket Studio converts vague requirements into well-scoped specs, then hybrid agents generate production-ready code through a five-stage quality process with a 98% merge rate reported across customer teams.

Visual Git client with built-in collaboration

GitKraken is a cross-platform visual Git client providing an intuitive graph visualization of repository history, branches, and merges. Features include drag-and-drop branch management, interactive rebase, merge conflict editor, built-in code editor, GitFlow support, and integrations with GitHub, GitLab, Bitbucket, and Azure DevOps. Includes GitLens for VS Code providing inline blame annotations, code authorship, and commit history. Free for public repos, paid for private repositories.

Open-source LLM observability and evaluation

Phoenix by Arize is an open-source AI observability platform for tracing, evaluating, and debugging LLM applications. It captures prompt-response pairs, retrieval context, agent tool calls, and latency data through OpenTelemetry-based instrumentation. Provides experiment tracking, dataset management, and evaluation frameworks for systematically improving AI application quality. 10K+ GitHub stars.

Self-hosted AI platform with ChatGPT-like interface for local and cloud LLMs.

Extensible, self-hosted AI platform with 290M+ Docker pulls and 124K+ GitHub stars. Supports Ollama, OpenAI-compatible APIs, and any Chat Completions backend. Features built-in RAG, multi-user RBAC, voice/video calls, Python function workspace, model builder, and web browsing. Runs entirely offline with enterprise features including SSO and audit logging.

AI-driven development workflow template

A template system that bootstraps AI-driven development workflows for your projects. Provides structured workflows, templates, and configurations for integrating AI agents into your development process. Reduces setup time by giving teams a proven starting point for organizing AI-assisted coding, task management, and quality assurance in new and existing repositories.