LibreAI ENESPTDEFRRUJA
← All categories// devtools

Best Open-Source AI Dev Tools

AI coding assistants, CLIs, and developer tools.

259 tools · 💎 90 hidden gems

// start here

Start here

The most-starred projects in this category, plus a rotating pick of three more from deeper in the list — refreshed so the whole catalogue gets its turn in the window.

Dev Tools

OpenCode

The open source coding agent

★ 211.6k starsMIT
View guide →
Dev Tools

Transformers

The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.

★ 166.9k starsApache-2.0
View guide →
Dev Tools

claude-code

Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase

★ 149.7k starsNOASSERTION
View guide →
Dev Tools

paperjury

Stress-test your research paper with an AI reviewer before submission.

★ 1.2k starsMIT
View guide →
Dev Tools

rockpack

Zero-config React with SSR, quality gates and an AI-ready project structure.

★ 1.1k starsCustom
View guide →
Dev Tools

pydantic-deepagents

Self-hosted terminal AI assistant and Python agent framework on Pydantic AI.

★ 1.1k starsMIT
View guide →

More categories: VideoImageAudioAI MusicAI 3DClippingLocal LLMAI ChatAI AgentsRAG & KnowledgeAutomationProductivityDesignWritingSelf-HostedEasy Install

// about this category

About Best Open-Source AI Dev Tools

Developer tools are where open-source AI is most mature: coding assistants that complete and refactor code, terminal agents that work a repository end to end, review bots, documentation generators, and the MCP servers and CLIs that connect models to a toolchain.

Because these tools run inside real projects, the guides focus on how each one is actually used — inside the editor, in the terminal, or in CI — and what it can touch. The safest pattern in this category is suggestion-first: the tool proposes, you review, then it applies.

How to choose

  • Match the tool to your surface: editor plug-in for flow, terminal agent for batch work, bot for team review.
  • Check which models a tool can use; bring-your-own-model tools age better than single-provider ones.
  • Any tool that can run commands deserves a test repository first.
// faq

Questions, answered

Which open-source Dev Tools tools are listed here?

This page collects 259 open-source Dev Tools projects curated by LibreAI — AI coding assistants, CLIs, and developer tools. Each one is verified on GitHub and has its own guide page with an overview, install steps, use cases, and an FAQ, so you can judge fit, requirements, and licensing before you download anything.

Are these Dev Tools tools free to use?

Yes. Every tool here is open source and free to download and use under its own license — most use MIT, Apache-2.0, or GPL-3.0, and any custom source-available license is flagged on the tool's page. Check the LICENSE file before commercial use.

Does LibreAI host these tools?

No. LibreAI publishes guides only — no downloads are served from this site, and no tool here is mirrored or repackaged by us. Every install comes from the project's official GitHub repository, which each guide links to directly, so you always get the genuine, current release from the people who build and maintain the tool.

How do I install a Dev Tools tool from this page?

Open the tool's guide and follow its 'Run it yourself' section — the steps come from the project's own documentation — or use the 'View on GitHub' button to go straight to the official repository. Each guide also states the tool's requirements first, so you can check your machine qualifies before downloading anything.

How were these tools chosen?

Every project is verified live through the GitHub API — stars, forks, license, and recent activity — and listed only if it has real momentum and an active community. Projects are re-checked as the catalogue is refreshed, and any project that goes quiet or changes its licensing terms has that noted on its page.

Will an AI coding assistant work with my editor and language?

Most assistants here cover the mainstream editors and languages, and many are model-agnostic so you can point them at local or hosted models. Niche languages get thinner support — the project documentation is the source of truth, and the guides link straight to it.

Can these tools change my code on their own?

Some terminal agents apply edits and run commands directly; editor assistants usually suggest first. Either way, version control is the safety net: work on a branch, review the diff, and let the tool earn broader access over time. Start read-only if the tool allows it, and widen permissions only after its suggestions prove reliable on your codebase.