A reactive runtime for building durable AI agents

LLMTrace is a transparent proxy that captures, analyzes, and secures your LLM interactions in real-time. Drop it between your app and any OpenAI-compatible API to get instant visibility into prompt injection attacks, PII leaks, cost overruns, and performance bottlenecks.

Burgonet Gateway is an enterprise LLM gateway that provides secure access and compliance controls for AI systems

Model executor runtime 💬 written in Rust

Tokei-backed repo inventory receipts (Markdown/JSONL/CSV) for PRs, CI, and LLM workflows.

A Cookbook of recipes from batuta

A QA playbook system for running through scenario testing

A Lazy, high throughput and blazing fast structured text generation backend.

Burgonet Gateway is an enterprise LLM gateway that provides secure access and compliance controls for AI systems

Prompt-centric framework for developing LLM applications in Rust

Robot VLM and VLA (Vision-Language-Action) inference API helping you manage multimodal prompts, RAG, and location metadata

🧭🧭 An intelligent load balancer with smart scheduling that unifies diverse LLMs.

🧬 The adaptive model routing system for exploration and exploitation.

Simple, Composable, High-Performance, Safe and Web3 Friendly AI Agents and LazAI Gateway for Everyone

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

Govern & Secure your AI

Fast, streaming indexing, query, and agentic LLM applications in Rust

🧠 Motorhead is a memory and information retrieval server for LLMs.

A reactive runtime for building durable AI agents

Open-source LLM load balancer and serving platform for self-hosting LLMs at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.