Directory
Published directory entries matching your search.
Self-hosted control plane that sits between connected AI clients, model providers, and tools. It applies access rules to users and agents, routes supported model requests through a gateway, checks governed tool calls before execution, and records policy decisions, execution records, and usage in the operator's environment. It deploys a Rust runtime with PostgreSQL on infrastructure the operator controls.
Text Generation Inference is a toolkit for deploying and serving large language models, implemented as a Rust, Python and gRPC server. It supports models including Llama, Falcon, StarCoder, BLOOM and GPT-NeoX, with features such as token streaming, continuous batching and quantization. The repository is archived, read-only, and in maintenance mode, with pull requests limited to minor bug fixes and maintenance.
Vearch is a cloud-native distributed vector database for similarity search of embedding vectors in AI applications. It supports hybrid vector search and scalar filtering, replication, elastic scaling, RESTful APIs, and SDKs for Python, Go, Java and Rust. It integrates with frameworks including LangChain and LlamaIndex and can be deployed via Kubernetes or Docker Compose.
ZeroClaw is an agent runtime distributed as a single Rust binary that users configure and run. It connects to LLM providers such as Anthropic, OpenAI and Ollama, reaches users through channels including Discord, Telegram, Matrix, email, voice and webhooks, and acts through tools including shell, browser, HTTP, hardware and custom MCP servers. A quickstart command performs one-shot setup to pick a provider and write a working config.
