Open-source platform for deterministic, token-aware context selection for AI agents and LLMs
Core library: scoring, selection, and caching for the Context Engine
A context database for AI agents. Multi-channel retrieval (semantic, lexical, structural) with MMR selection and token budget management. Built in Rust. Apache 2.0.
CLI for building, resolving, and inspecting context caches
Token budget manager for LLM apps — track usage, enforce limits, estimate costs per user/session. Zero dependencies. OpenAI, Anthropic, Groq, Ollama.
🚀 Optimize AI context retrieval with OrionGraphDB, a powerful engine that respects token budgets and delivers diverse, relevant information seamlessly.
Add a description, image, and links to the token-budget topic page so that developers can more easily learn about it.
To associate your repository with the token-budget topic, visit your repo's landing page and select "manage topics."