Stars
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
The context API to search, scrape, and interact with the web at scale. 🔥
Spec-driven development (SDD) for AI coding assistants.
A FastAPI wrapper for NVIDIA's new parakeet 0.6b v3 TTS 600m model designed for high-quality multilingual speech recognition, beating Whisper Large v3 and Whisper Large v3 turbo with blazing fast s…
Uzbek/Russian PII detection and masking using ML (rubai) + rule-based (Presidio) models
The most advanced free and open-source browser fingerprinting library
Simultaneous speech-to-text models
Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deplo…
A simple cheatsheet for telegram mini apps
All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.
Build Real-Time Knowledge Graphs for AI Agents
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
A collection of inspiring lists, manuals, cheatsheets, blogs, hacks, one-liners, cli/web tools and more.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
Deploy headless browsers in Docker. Run on our cloud or bring your own. Free for non-commercial uses.
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
OpenSPG is a Knowledge Graph Engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework. Core Capabilities: 1) domain model constr…
DSPy: The framework for programming—not prompting—language models
ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation (CVPR20)
Generation of handwritten cyrillic text using fonts
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Code and data for paper "Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation" accepted by ACL 2024.
A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)