Gitingest: Turn Any Git Repo Into One Prompt for an LLM (GitHub, Scanned)
Turn any Git repository into a single text digest you can paste into an AI chat.
Scanned 3 min read
Loading…
/** @github-tools */
Best AI Coding Agents on GitHub
These are AI tools that write and edit code: terminal agents, editor extensions, and the servers and helpers that make agents more accurate. Good ones work with many models, show you each change before applying it and are updated often. Pick a terminal agent if you live in the command line, an editor extension if you prefer VS Code, and add helper tools like documentation servers once your main agent is set up.
5 repos, each cloned and scanned
// top 10, ranked
Updated 30 October 2026 · moves since 26 October 2026 · re-ranked every 3 days on what readers use, never sponsored
- 1
OpenCode: The Open-Source Coding Agent for Any Model (GitHub, Scanned)
no changeA terminal coding agent that works with any model, with a desktop app and a read-only plan mode; the most popular open option.
- 2
OpenAI Codex CLI: A Coding Agent in Your Terminal (GitHub, Scanned)
no changeOpenAI's open-source terminal coding agent written in Rust, with sandboxing built in, best for people already using OpenAI models.
- 3
Gemini CLI: Google's Coding Agent for the Terminal (GitHub, Scanned)
up 2Google's terminal agent for Gemini models with a large community, a good fit if you already have a paid Gemini key.
- 4
Cline: An Open-Source Coding Agent for Your IDE (GitHub, Scanned)
down 1A coding agent for VS Code, JetBrains and the terminal that asks before each change, ideal for people who prefer working in an editor.
- 5
OpenHands Agent Canvas: Run Coding Agents Yourself (GitHub, Scanned)
down 1A self-hosted control centre for running and automating coding agents locally or in Docker, suited to teams handing off whole tasks.
- 6
Kilo Code: An Open Source AI Coding Agent for VS Code, JetBrains and the Terminal (GitHub, Scanned)
no changeAn editor and terminal coding agent with hundreds of models and an unusually large contributor base.
- 7
Spec Kit: Make AI Coding Agents Work From a Spec (GitHub, Scanned)
no changeGitHub's toolkit that has your coding agent write a spec, plan and tasks before code, for steadier results on bigger features.
- 8
Screenshot to Code: Turn Any Screenshot Into Working HTML or React (GitHub, Scanned)
up 2Turns a screenshot, mockup or screen recording into working HTML, React or Vue code, great for quickly rebuilding a design.
- 9
Context7: Up-to-Date Library Docs for AI Coding Agents (GitHub, Scanned)
down 1Feeds coding agents current, version-specific documentation so they stop inventing APIs; a quick upgrade for any agent.
- 10
Chrome DevTools MCP: Let Your Coding Agent Debug a Real Chrome (GitHub, Scanned)
down 1Google's MCP server that lets coding agents inspect a real Chrome page, including network, console and performance traces, for web developers.
// all 26 in Coding Agents
Dyad: Build Apps With AI on Your Own Machine (GitHub, Scanned)
A desktop AI app builder like Lovable or Bolt that runs locally with your own keys or local models.
Scanned 7 min read
Repomix: Pack a Whole Repo Into One File for AI (GitHub, Scanned)
Packs a codebase into one AI-friendly file with token counts, ready for Claude, ChatGPT or Gemini.
Scanned 6 min read
OpenCode: The Open-Source Coding Agent for Any Model (GitHub, Scanned)
An open-source terminal coding agent that works with any model, with a desktop app and a read-only plan mode.
Scanned 5 min read
OpenHands Agent Canvas: Run Coding Agents Yourself (GitHub, Scanned)
A self-hosted control centre for coding agents: run OpenHands, Claude Code or Codex locally or in Docker, and automate them.
Scanned 6 min read
// How we scan
Before a repository gets a post here we clone it and run the same checks on every one. The scanner is a script in this site's own repository, its findings are written out with file and line, and a person reads every hit before writing the verdict in the post. The last full run was on Oct 28, 2026.
- Pinned commit
- A fresh clone of the default branch. The commit and date are on every report, so the findings are about one snapshot, not the repository in general.
- Secrets
- Credential patterns with a known shape: cloud access keys, API tokens for OpenAI, Anthropic, Slack, GitHub, Google and Stripe, chat webhooks, private key blocks.
- Suspicious code
- Code that decodes a string and then executes it, pipes a download straight into a shell, opens a raw socket to a shell, reaches a known exfiltration service, mines cryptocurrency, or looks packed.
- Install-time code
- npm lifecycle scripts, setup.py command classes, Cargo build scripts, and installer shell scripts: whether they use sudo, edit your shell profile, or fetch and run remote code.
- Committed binaries
- Executables and compiled objects identified by their bytes, not their file extension, so a renamed binary still shows up.
- CI workflows
- GitHub Actions that run on pull_request_target and check out the pull request head (a classic way to leak secrets), write-all permissions, and third-party actions pinned to a tag instead of a commit.
- Network hosts
- Every host the source code talks to, so an unexpected one stands out.
- Known vulnerabilities
- Every pinned dependency in the repository's lockfiles looked up in OSV.dev, counted by severity. Includes development dependencies, which is why the counts are not zero for a large web app.
- Project hygiene
- A security policy, automated dependency updates, CodeQL, a licence, contributing guidelines.
- OpenSSF Scorecard
- The Open Source Security Foundation's independent score, where the project has one.
Safe means no credential patterns, no decode-and-execute code, no exfiltration hosts, no undocumented install-time behaviour, no risky workflow, and nothing in the findings a reviewer could not explain. Anything you should know before installing (an installer that pipes to a shell, a tool that reads a credential you already have, a licence with conditions, or a lockfile with unpatched advisories) is the note beside the badge.
Not covered: we do not run the software, audit its logic, or review commits made after the scan. The date and commit are on every report. Check them, and read the code yourself before you trust it with anything that matters.
// Questions
- Are these GitHub AI tools free to use?
- All of them are free to download, run and modify. The licences differ: most are MIT or Apache 2.0, ComfyUI is GPL-3.0, and Open WebUI and Dify ship their own licences with conditions on rebranding and multi-tenant hosting. Each post says which licence applies and what it asks of you.
- What does it mean that a repository was scanned?
- We cloned it at a specific commit and ran the checks listed under How we scan: credential patterns, decode-and-execute code, install-time scripts, committed binaries, risky CI workflows, every host the code talks to, known vulnerabilities in pinned dependencies, and project hygiene. Every hit was read by a person before the verdict was written, and the findings are in each post.
- Why do known vulnerabilities show up in a scan marked safe?
- Because a lockfile pins development dependencies too. A large web app carries thousands of packages and OSV knows of advisories in some of them; most affect build tooling and never reach a user. Each post shows the counts per lockfile and the worst entries so you can see where they sit, and the notes say whether any of it ships to you.
- How current is a scan?
- The date and commit are printed in every post. Active projects merge dozens of commits a week, so treat a report as a snapshot of that commit, not a standing guarantee, and re-check the repository before installing anything on a machine you care about.
- Which of these should I start with?
- To run a model on your own computer, install Ollama and add Open WebUI for a chat interface. For images and video, ComfyUI. To build an app or agent without much code, Dify. To let an agent write code or use a browser, OpenHands, Codex or browser-use. If you already use Claude Code or Codex, cost-xray shows what each session actually costs.