-
Stealth
- California, United States
-
16:44
(UTC -07:00) - https://hershrajn.com
Starred repositories
A 5-20x faster experimental Homebrew alternative
Algorithm powering the For You feed on X
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
A refreshingly simple data-driven game engine built in Rust
An extremely fast Python package and project manager, written in Rust.
AI powered open source recommender system engine supports classical/LLM rankers and multimodal content via embedding
A high-throughput and memory-efficient inference and serving engine for LLMs
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
[AAAI 2026] The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while control…
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Lean 4 programming language and theorem prover
Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs
An extension of XGBoost to probabilistic modelling
AirPods liberated from Apple's ecosystem.
Extremely fast Query Engine for DataFrames, written in Rust
[ICLR 2025] Automated Design of Agentic Systems
Open-source implementation of AlphaEvolve
Open Source AI Platform - AI Chat with advanced features that works with every LLM
A free book: "The Science of Functional Programming"
Empowering everyone to build reliable and efficient software.
ValueCell is a community-driven, multi-agent platform for financial applications.
Open-source vector similarity search for Postgres
"RAG-Anything: All-in-One RAG Framework"
An alignment auditing agent capable of quickly exploring alignment hypothesis