Starred repositories
Chrome DevTools for coding agents
Turning LLM architecture exploration into reusable knowledge for the community. 🌳
Single Sign-On for Your Self-Hosted Universe
Wrapper to use boto3 resources with the aiobotocore async backend
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.
Agent workspace built on Cloudflare Workers for creating documents, building apps, and running agents with your company’s context and systems.
Samples and documentation for using the Amazon ElastiCache Redis and Memcached
Mixture-of-experts (MoE) training megakernel for NVL72s
A minimal autonomous code-agent CLI built with Qwen Code
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
Benchmarking STT service TTFB and semantic WER for real-time AI applications
A web editor UI for managing pipecat flows
Open-source speech AI models from KRAFTON, including Raon-Speech and Raon-SpeechChat for speech understanding, generation, and real-time full-duplex conversation.
C++ examples for the Vulkan graphics API
Inflect is a lightweight, high‑quality text‑to‑speech model designed to deliver surprisingly natural audio with a minimal footprint. It’s an active work‑in‑progress focused on fast iteration, stron…
Native and Compact Structured Latents for 3D Generation
Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.
Everything you need to know about LLM inference
OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
A unified, torch-native training framework for MTP and block-parallel speculative decoding.
A minimal MiniCPM5-1B model inference engine built purely in Rust
MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts
Better Harness turns project and session evidence into loop-level insights, prioritized improvements, and verifiable next steps—inside the coding agent you already use.