TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

⚙️🦀 Build portable, modular & lightweight Fullstack Agents

The AI-native proxy server for agents. Arch handles the pesky low-level work in building agentic apps like calling specific tools, routing prompts to the right agents, clarifying vague inputs, unifying access and observability to any LLM, etc.

BionicGPT is an on-premise replacement for ChatGPT, offering the advantages of Generative AI while maintaining strict data confidentiality

AICI: Prompts as (Wasm) Programs

A reactive runtime for building durable AI agents

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

Stateful load balancer custom-tailored for llama.cpp 🏓🦙

Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.

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

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

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

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

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

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

Prompt-centric framework for developing LLM applications in Rust

Model executor runtime 💬 written in Rust

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