Stars
🤖 Kubernetes for AI Agents. Self-hosted, production-grade runtime for orchestrating LLM swarms and autonomous agents. TypeScript-native.
Hindsight: Agent Memory That Works Like Human Memory
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
A framework for agentic tool use training with reinforcement learning
The absolute trainer to light up AI agents.
Laminar - open-source observability platform purpose-built for AI agents. YC S24.
Completed research on semantic retrieval augmented generation through novel semantic similarity graph traversal algorithms.
Brahmand is an open-source graph query engine built on top of ClickHouse.
Accelerated Sparse Linear Algebra with Postgres and SuiteSparse
Orchestrator Kit for Agentic Reasoning - OrKa is a modular AI orchestration system that transforms Large Language Models (LLMs) into composable agents capable of reasoning, fact-checking, and const…
A Comprehensive Speech Processing Algorithms Library for research and production use
Code for "HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking"
SmartChunk is a lightweight, structure-aware semantic chunking toolkit designed to supercharge RAG (Retrieval-Augmented Generation) and LLM pipelines. Unlike naive splitters that break text arbitra…
Cutting-edge tool that unlocks the full potential of semantic chunking
An advanced retrieval system that combines semantic vector search with token-based search, using contextual chunking and knowledge graphs to improve accuracy. It ensures precise query responses wit…
A new chunking strategy developed by ZeroEntropy for general semantic chunking using Llama-70B.
Efficient RAG pipeline with hierarchical chunking for improved context retrieval and LLM generation.
An intelligent chunking system that automatically chooses between hierarchical content-aware chunking and fixed-length chunking with overlap based on document structure.
this package utilise the technique of late chunking together with hierarchical chunking
Memento MCP: A Knowledge Graph Memory System for LLMs
A powerful tool for creating fine-tuning datasets for LLM
Fullstack SaaS Boilerplate built with tRPC, Fastify and React
Lightweight fullstack turborepo with modular components, shared configs, containerised deployments and 100% type-safety.
Vision infrastructure to turn complex documents into RAG/LLM-ready data