Prompt Optimizer: Rewrite and Test Prompts for Better AI Output (GitHub, Scanned)
Rewrites your prompts with an AI model, then lets you test and compare the results side by side.
Scanned 5 min read
Loading…
/** @github-tools */
Best AI App Builders on GitHub
These are platforms and frameworks for building your own AI apps: visual builders, document question answering (RAG), agent frameworks, and the tools that route, remember and test model calls. Good ones are well documented, actively maintained and widely adopted, so answers and examples are easy to find. Non-coders should start with a visual builder; developers can pick a framework, then add memory, a model gateway or tracing as the app grows.
3 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
Dify: Build LLM Apps Without the Plumbing (GitHub, Scanned)
no changeBuild and ship AI apps and agents from a visual workspace with prompts, tools, data and logs together; the best start for most teams.
- 2
Langflow: Build AI Agents on a Visual Canvas (GitHub, Scanned)
no changeA drag-and-drop builder for agents and RAG flows that deploys each flow as an API, good for prototyping visually.
- 3
RAGFlow: Chat With Your Hardest Documents (GitHub, Scanned)
no changeA self-hosted RAG engine with deep document parsing and cited answers, ideal for reliable question answering over messy files.
- 4
LangChain: The Standard Kit for LLM Apps (GitHub, Scanned)
no changeThe most widely used Python framework for LLM apps and agents, with one interface to hundreds of models and tools.
- 5
LiteLLM: One API for 100+ Language Models (GitHub, Scanned)
no changeCalls over 100 model providers through one OpenAI style API with keys, budgets and logs, essential when an app uses several models.
- 6
DeerFlow: ByteDance's Open-Source Super Agent for Research and Code (GitHub, Scanned)
no changeByteDance's self-hosted harness for long agent tasks, with sub-agents, sandboxes, memory and skills; suits deep research style work.
- 7
CrewAI: Teams of AI Agents That Work Together (GitHub, Scanned)
no changeA Python framework for teams of role-playing agents plus event-driven Flows, an approachable way to build multi-agent apps.
- 8
Mem0: Long-Term Memory for AI Agents (GitHub, Scanned)
no changeAdds long-term memory to AI agents by extracting facts from conversations and recalling the relevant ones later.
- 9
Langfuse: See What Your LLM App Is Actually Doing (GitHub, Scanned)
no changeSelf-hostable tracing, prompt management and evaluations, the tool to reach for once your AI app has real users.
- 10
Onyx: Self-Hosted AI Chat and Search Over Your Team's Apps (GitHub, Scanned)
no changeSelf-hosted AI chat that searches a team's docs, tickets and chats across 50 plus connected apps, a ready-made internal knowledge assistant.
// all 18 in Build AI Apps
Langflow: Build AI Agents on a Visual Canvas (GitHub, Scanned)
Drag-and-drop builder for AI agents and RAG flows that deploys each flow as an API or an MCP server.
Scanned 6 min read
Dify: Build LLM Apps Without the Plumbing (GitHub, Scanned)
Build and ship LLM apps and agents from a visual workspace, with the prompts, tools, data and logs in one place.
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.