AI Helpers
Since April 2024
15 Python libraries — BSD-3-Clause — local-first
Introduction
AI Helpers is a suite of 15 Python libraries, licensed under BSD-3-Clause (same as scikit-learn / numpy / scipy), designed to simplify AI development across audio/video processing, live speech transcription, media acquisition, capture, secure storage, caching, vector search, and hardware-aware local-model selection. The suite is organized into groups, so you install only the corner you need: Core (OS Helper), Audio & voice (Audio, Vocal), Video & capture (Video, Capture), Media acquisition (YouTube, Podcast), Storage & transfer (Bucket, SFTP), Documents (md2star), Cache (Wallet), and Misc (Standpoint, Best Engine AI, ANN Router, Elbow Helper).
Every bundled helper exposes the same surfaces: a Python API, two CLIs (argparse + click), a FastAPI HTTP server, and an MCP tool set. Where it earns its place, it also adds a minimal browser GUI at /gui. Each also ships as an installable Claude Code / OpenCode skill. The suite is local-first by design: your files, audio, camera/mic and documents are processed on your machine with open-source tooling, with no SaaS, no telemetry, no account. The two remote-transfer helpers, Bucket and SFTP, are the honest exception; their job is to move data to storage / servers you choose.
Install just the group you need — every helper is its own package and all of them are on PyPI, so you install by name (each pulls in os-helper automatically):
# 🔊 Audio & voice
pip install audio-helper vocal-helper
# 🎬 Video & capture
pip install video-helper capture-helper
# 🌐 Media acquisition
pip install youtube-helper podcast-helper
# 🗄️ Storage & transfer
pip install bucket-helper sftp-helper
# 🧩 Misc (docs, cache, positioning maps, local-model
# selection, vector-search routing, knee detection)
pip install md2star wallet-helper standpoint best-engine-ai-helper ann-router elbow-helper
# 🧱 Core only (foundation utilities)
pip install os-helper
You still need ffmpeg on PATH for the media helpers (audio / video / youtube / podcast / capture / vocal); brew install ffmpeg on macOS 🍎.
Contents
- Introduction
- 🔒 The Promise
- Composed example
- 🧱 Core
- 🔊 Audio & voice
- 🎬 Video & capture
- 🌐 Media acquisition
- 🗄️ Storage & transfer
- 📄 Documents
- ♻️ Cache
- 🧩 Misc
- Links
🔒 The Promise
The tools you build AI with should run on your machine, keep your data under your control, and never make you rent access to your own workflow.
No SaaS, no telemetry, no account, no cloud lock-in, and every line is BSD-3-Clause, so you can read it, fork it, and trust it. We hold ourselves to that honestly, and we are explicit about exactly where it does (and does not) fully apply.
- Guaranteed local. os-helper, audio-helper, video-helper, capture-helper, vocal-helper, md2star and wallet-helper run entirely on your machine — ffmpeg, whisper.cpp, pyannote/NeMo, Pandoc, a local Ollama model — never leaving it.
- Fetches only what you ask for. youtube-helper and podcast-helper must contact the sites and feeds you point them at, but upload nothing about you and keep everything else local. A few helpers download a model or template once, then work offline.
- Deliberately not local-first. bucket-helper and sftp-helper move your data to remote storage and servers. Sovereignty here means you choose the endpoint: your own MinIO/SFTP box, never a hidden default.
How we applied it, concretely. Every bundled helper ships the same surfaces so you own the whole stack: a Python API, two CLIs, a FastAPI HTTP server, an MCP tool set for agents, and (where auditing the output in a browser genuinely helps) a minimal GUI at /gui, served by the same local FastAPI app with no build step, no framework, and no external calls. Each helper documents its exact trigger conditions in a TRIGGERS.md. The two remote-transfer helpers wear the exception openly instead of pretending otherwise.
Composed example
The helpers are designed to chain. Here the suite turns a YouTube talk into a shareable Word document and PDF — acquisition with 🌐 youtube-helper, decoding with 🔊 audio-helper, speech-to-text with 🗣️ vocal-helper, and typesetting with 📄 md2star:
import youtube_helper as yth # 🌐 acquisition
import audio_helper as ah # 🔊 decode to PCM
import vocal_helper as voh # 🗣️ speech-to-text (Whisper)
URL = "https://www.youtube.com/watch?v=YE7VzlLtp-4"
# 1) Acquire: pull the talk's audio (16 kHz mono is ideal for ASR).
yth.download_audio(URL, "talk.mp3", target_sample_rate=16000)
# 2) Transcribe: Whisper on the decoded PCM (to_numpy=True → float32 array).
pcm, sr = ah.load_audio("talk.mp3", target_sample_rate=16000, to_mono=True, to_numpy=True)
transcript = voh.transcribe_pcm(pcm, sr, language="en")
# 3) Hand off to md2star: write a titled Markdown file for typesetting.
with open("talk.md", "w", encoding="utf-8") as fh:
fh.write(f"# Talk transcript\n\n_Source: {URL}_\n\n{transcript}\n")# 4) Typeset the transcript as a Word document and a PDF (md2star CLIs).
md2docx talk.md # → talk.docx
md2pdf talk.md # → talk.pdf
Because md2star's md → docx → pdf render is faithful and reversible (see the md2star round-trip identity), the resulting documents read straight back to Markdown without losing the transcript's text.
🧱 Core
OS Helper
OS Helper is a Python library that provides utility functions for working with different operating systems — file handling, hashing, config and timing: the shared foundation every other helper builds on.
🔊 Audio & voice
Audio Helper
Audio Helper is a Python library that provides utility functions for processing audio files: loading audio, converting formats, separating audio sources, and splitting and concatenating audio files.
🔈 GitHub · 📦 PyPI · 📃 Docs · 🦀 Also in Rust
Vocal Helper
Vocal Helper turns audio into diarized, transcribed utterances, and optionally a rolling LLM summary of the conversation. It runs as an async producer/consumer pipeline in two modes — online streaming and offline batch — chaining voice activity detection, speaker diarization, speech-to-text and optional summarization. Built on Silero VAD, whisper.cpp, pyannote / NeMo diarization backends and Ollama-served language models.
🎬 Video & capture
Video Helper
Video Helper is a Python library that provides utility functions for processing video files: multi-backend frame extraction (VidGear / PyAV / ffmpeg-pipe), loading, converting, and working with subtitle formats.
Capture Helper
Capture Helper is the live input layer for the AI Helpers stack: cross-platform camera and microphone enumeration and capture, yielding (H, W, 3) BGR frames and PCM. It ships a live multi-source scene configurator GUI at /gui — pick cameras and mics, preview them live in the browser, arrange a scene, save/load it as JSON. Camera and microphone data never leave your machine.
🎥 GitHub · 📦 PyPI · 📃 Docs · 🦀 Also in Rust
🌐 Media acquisition
YouTube Helper
YouTube Helper is a Python library that provides utility functions for downloading videos, audio, and thumbnails from platforms like YouTube, Vimeo, DailyMotion, SoundCloud and Twitch using yt-dlp. It also supports post-processing with ffmpeg, browsing video stream catalogs, and pulling no-API engagement metadata.
📹 GitHub · 📦 PyPI · 📃 Docs · 🦀 Also in Rust
Podcast Helper
Podcast Helper is universal audio stream consumption: URL-in to PCM-out. It accepts local files, direct audio URLs, RSS/Atom feed URLs (auto-picks the latest episode), and any yt-dlp-supported source. Built on youtube-helper + ffmpeg + feedparser + podcastparser, with Shannon-correct resampling.
🎙️ GitHub · 📦 PyPI · 📃 Docs · 🦀 Also in Rust
🗄️ Storage & transfer
Bucket Helper
Bucket Helper covers AWS S3 and any S3-compatible object storage (MinIO, Backblaze B2, DigitalOcean Spaces, Cloudflare R2, Wasabi) via boto3. Same shape as SFTP Helper: credentials loader, upload / download / delete / exists / list_prefix, and a remote_tempfile context manager.
SFTP Helper
SFTP Helper is a Python library that provides utility functions for interacting with SFTP servers, with strict host-key verification and a remote_tempfile helper, once you specified your SSH Key Credentials.
📄 Documents
md2star
md2star is a Markdown → DOCX / PPTX / PDF bridge built on Pandoc, with curated branded templates, Mermaid diagram rendering and bibliography support.
⭐ GitHub · 📦 PyPI · 📃 Docs · 🦀 Also in Rust
♻️ Cache
Wallet Helper
Wallet Helper makes sure you never run the same heavy call twice — a paid API request, a slow model, any expensive function. Results are persistent and content-addressed, served from a local store instead of recomputed, even across process restarts. Two identical calls in flight collapse into one via single-flight, in-process or across processes/hosts via a fenced SQLite lease or an optional HTTP dedup server.
🧩 Misc
Standpoint
Standpoint turns a comparison table (options as rows, criteria as columns) into a labelled 2D positioning map, a short written analysis, and a YAML of coordinates, in a single command. Ordinary PCA under the hood; Standpoint adds the hand-work — orients the map around a reference option, names the axes in plain words, colours and labels the points.
Best Engine AI Helper
Best Engine AI Helper picks (and pulls) the best local LLM or VLM for the machine it runs on. It detects available memory (Apple Silicon unified memory, NVIDIA VRAM, system RAM), consults a bundled model catalog, selects the highest-scoring model that fits a safety headroom, pulls it via Ollama, and writes an env file downstream projects can source.
ANN Router
ANN Router is the vector-search sibling of Best Engine AI Helper: measure the criteria → select the engine → return a discussable rationale, applied to approximate-nearest-neighbour search. It selects, justifies, and can instantiate the right backend among exact, turbovec, HNSW, FAISS, Annoy, Qdrant and pgvector — an indispensable component for RAG.
Elbow Helper
Elbow Helper answers a harder question than "where might a knee or elbow be?" — an algorithm asked that will always return something, even on noise. Instead: is any candidate knee strong, unique, persistent, reproducible, and unlikely under a no-knee model? If not, it abstains. A from-scratch, NumPy-only knee locator; robust_knees covers the multi-knee case.
Links
GitHub (the suite) · PyPI · 📃 Documentation · 📡 Releases feed (Atom) · llms.txt · sitemap.xml
BSD-3-Clause License — Warith Harchaoui, Mohamed Chelali & Bachir Zerroug.