Skip to content
TechIndexSubmit
Back to directory

aarambh-studio

πŸ¦€ Decoder-only LLM built from scratch in pure Rust using Candle β€” no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE, native video/document understanding, long-horizon tool agents, quantization-aware training. Scales: Tiny (25M) to Large (1.3B).

Similar tools

  • High-scale LLM gateway, written in Rust. OpenTelemetry-based observability included

    Dev Tools
  • The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

    Models
  • βš™οΈπŸ¦€ Build modular and scalable LLM Applications in Rust

    Models
  • Offline AI assistant with RAG β€” air-gapped local LLM deployment (llama.cpp, Qwen 2.5 3B). No internet, no cloud, no data leaves the device. Scripted VM deployment for sensitive/regulated data.

    Models
  • Self-hosted AI/LLM gateway built with Java & Spring Boot for running open-source LLMs locally via llama.cpp, with RAG, AI agents, vision, embeddings, web search, RBAC, and a React playground.

    Models
  • Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust πŸ¦€

    AI Apps