search · names, descriptions, topics, READMEs
Results for “llm”
Repositories 11
-
llmindex
TypeScript
The discriminative, contamination-resistant, fully transparent LLM ranking — updated live.
- polyllm TypeScript
-
modelmap
Python
Internal cartography of local LLMs on Apple Silicon — registered, gated, negative-first. Public atlas at modelmap.io.
-
forge
C++
Forge — LLM training from scratch in pure C++20 + Metal on Apple Silicon.
-
zyquo-router
Swift
One local endpoint, every AI provider — a private OpenAI-compatible LLM gateway for your Mac (170 models, 12 providers).
-
zyquo-local
Swift
Native macOS AI chat that runs LLMs 100% locally on Apple Silicon with MLX — no cloud, no API keys.
- llm-api
-
poche
Swift
Agent personnel 100 % on-device — SwiftUI + Apple Foundation Models + EventKit + SwiftData. Aucune API, aucun serveur.
-
chat-spboucher
TypeScript
Private universal chat interface over the OpenRouter ecosystem — 400+ models, branching, streaming, usage tracking. Next.js 16 + SQLite, PWA, deployed on m4m64a at chat.spboucher.ai
-
localvm-research
Python
Running LLMs larger than memory on a consumer Mac — falsification-driven research: margin-gated deferred refinement, out-of-core verification on Apple Silicon. TR-01 published.
-
forge-studio
Swift
The Instruments of LLM training — a native macOS cockpit for Forge. Train language models from scratch on Apple Silicon without a terminal.
README content 20
-
llmindex
…t est désormais la seule source de vérité du projet. Ancienne URL : https://www.llmindex.io LLM Index The discriminative, contamination resistant, fully transparent LLM ranking — updated live. www.llmindex.io · Methodolo…
-
polyllm
PolyLLM One interface. Every model. Bring your own keys. — https://www.polyllm.io PolyLLM is a mobile first, multi model AI workspace — an "AI operating system" rather than a chat box: connect your own OpenAI, Anthropic,…
-
modelmap
…discovers, measures, and maps the internal structure of pretrained open weight LLMs entirely on consumer Apple Silicon — and publishes the results as a reproducible, confidence labeled public atlas at modelmap.io . Ever…
-
forge
🔥 Forge LLM training from scratch — pure C++20 + Metal on Apple Silicon No PyTorch. No MLX. No ML dependencies. Just C++, Metal kernels, and a JSON parser. 📄 Paper · 🔬 Research notes · 📐 Spec ✨ What this is A complet…
-
zyquo-router
…One local endpoint. Every AI provider. Spec exact. Turn your Mac into a private LLM gateway — 170 models from 12 providers behind a single OpenAI compatible API. · · · · · · · · · · · 📖 Table of Contents Why Zyquo Route…
-
zyquo-local
…, Mistral/Mixtral, Gemma 1–4, Phi 3/4, DeepSeek V3 distills, gpt oss, GLM 4, SmolLM3, LFM2, OpenELM, StarCoder2, Granite, and more — with a compatibility check before you download anything. True token streaming with a li…
-
poche
…État Écran Action Chat — Mur définitif, soigné, sans culpabilisation Jamais de LLM de remplacement Explication Bouton « Ouvrir Réglages » Téléchargement en cours Bouton « Réessayer » ⚠️ Limitations connues Limitation Dé…
-
localvm-research
…ated: 2026 08 11 modified: 2026 08 12 status: reviewed localvm research Running LLMs larger than memory on a consumer Mac Live research platform: www.localvm.dev — every hypothesis, result, figure, and failure, browsable…
-
forge-studio
🔥 Forge Studio The Instruments of LLM training — a native macOS cockpit for Forge Train language models from scratch on Apple Silicon without ever opening a terminal. Pick a dataset, shape an architecture, hit Start — a…
-
lou-ka
…tes les photos, digest structuré de la description (text mining regex FR, aucun LLM), badge marché, historique de prix ( ), fiche PDF avec QR code. Couches de données de quartier — recensement 2021, registre des loyers (…
-
cancerindex
…d with mappings, locations, publications; per cancer trial metrics (growth, enrollment, sponsor and country concentration, termination share, trials per 1 000 deaths); failure tracking with registrant stated reasons clas…
-
company-atlas
…0 sections) · repo guide Architecture · crawl · connectors · events · scoring · LLM · seeds API ( , SSE , exports, admin) — live docs at Web (Next 16) — Deploy / ops · Stack Python 3.12 ( , CLI : FastAPI · SQLAlchemy Cor…
-
websensor
…extraction confidence, diff clarity, structured vs free text, confirmations and LLM/heuristic agreement. Impact (0–100) weights the event type's user impact, entity importance, magnitude and the largest numeric delta amo…
-
ai-atlas
…, prices and benchmark results are append only, every change is an event. Local LLM factory : large scale extraction runs on MacLustr's own inference servers through an engine agnostic gateway. Interfaces : the website,…
-
social-runtime-crawler
…tion gain scoring, lexical novelty, loop detector, heuristic planner + optional LLM planner (Anthropic or local OpenAI compatible) Media video detection (DOM + manifests/segments + video entities), frame sampling at LEVE…
-
qc26
…), momentum borné (prime au chef, attention Wikipédia, ton de presse classé par LLM), élections partielles depuis 2022 (excès de swing local). La vue « sondages seuls » reste publiée. Refonte visuelle « Editorial Data In…
-
uqo-chat
…lint, CI 14. Déploiement sur le cluster MacLustr ( ) 15. Exploitation 16. Coûts LLM 17. Vie privée, sécurité, Loi 25 18. Écarts assumés par rapport à la spécification 19. Feuille de route 20. Historique des versions 21.…
-
trawls
…awls cartographie et extrait n'importe quel site et renvoie du Markdown propre, LLM ready . Ne crashe jamais : une page qui échoue produit un avec une erreur typée. Le crawl continue. Escalade automatique : HTTP pur (cur…
-
resto-ka
…et alertes de dérive ; enrichissements inspections/permis/heures. Structuration LLM ( ) : menus maison structurés par Claude (API Anthropic). Frontend React 18 + Vite + TypeScript ( ), design « éditorial premium » Groupe…
-
trouve-ka
…isations connues (Hydro Québec, RAMQ, UQAM…), JSON LD, langue française — aucun LLM dans le chemin chaud. Héritée de la phase « web ouvert », toujours active ( dans la config restaure le comportement web québécois ouvert…