Open-source edge engine to control API request budgets and enforce fair usage.

Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.

Cross-agent skill quality gate for SKILL.md files. Validates frontmatter, scores description discoverability, checks file references, enforces three-tier token budgets, and flags compatibility issues across Claude Code, VS Code/Copilot, Codex, and Cursor.

Context engineering toolkit for LLMs — pack, cache, debug, red-team, and orchestrate context windows. Council of Experts, adversarial testing, immune system, context compiler, drift detection, multi-agent entanglement. TypeScript + Python.

Open source AI cost tracking. Know exactly what your AI costs — per feature, per user, per project.

AI agent harness engineering tool — visualize CLAUDE.md, AGENTS.md, skills, and agent config structure

Core library: scoring, selection, and caching for the Context Engine

Build optimal LLM context windows. Priority-based assembly, token budgeting, smart truncation (HEAD/TAIL/MIDDLE). Zero mandatory dependencies. Drop into any RAG pipeline in 3 lines.

Enforce real-time token budgets and spending limits for OpenAI, Anthropic Claude, and Google Gemini API calls in Node.js

🚀 Optimize AI context retrieval with OrionGraphDB, a powerful engine that respects token budgets and delivers diverse, relevant information seamlessly.

Optimal context window selection for LLM coding tools. Treats context as a constrained optimization problem, not retrieval. Beats RAG, grep, and LLM-triage baselines on real GitHub issues.

Governance layer for token-scoped authority and policy enforcement.

Open-source platform for deterministic, token-aware context selection for AI agents and LLMs

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

Lightweight reverse proxy for OpenAI API with per-key token budgets, rate limiting, cost dashboards, model downgrade, and caching — deploy in 5 minutes with Docker