← all releases
Microsoft·Oct 30, 2026·v0.1.0·open source
TokenEconomizer
TokenEconomizer is an experience-driven, black-box cost control layer designed for AI coding agents. It optimizes token usage by learning from finished sessions within a repository to inject micro-skills, prune unused tools, and interrupt failure loops without modifying the underlying agent models.
LLMsInfrastructureML
overview
TokenEconomizer is an experience-driven, black-box cost control layer designed for AI coding agents. It optimizes token usage by learning from finished sessions within a repository to inject micro-skills, prune unused tools, and interrupt failure loops without modifying the underlying agent models.
key features
- 01Micro-skill synthesis and injection based on recurring session evidence
- 02Automated tool pruning to remove unused capabilities
- 03Failure-loop intervention to prevent repetitive, unproductive agent cycles
- 04Repository-specific adaptation that learns from past task performance
- 05Compatible with Claude Code, Codex, GitHub Copilot CLI, and Pi
related productsbrowse all →
SINQopen sourceSINQ (Sinkhorn-Normalized Quantization) is a novel, fast, and high-quality quantization method designed to make any Large Language Model (LLM) smaller while preserving accuracy. It offers a plug-and-play, model-agnostic technique that delivers state-of-the-art performance for LLMs without sacrificing accuracy.DetectFlowopen sourceDetectFlow is an open-source cybersecurity detection platform developed by SOC Prime. It leverages artificial intelligence to enhance the detection of cyber threats in real-time, enabling security operations teams to identify and respond to attacks more effectively.SkyRL txopen sourceSkyRL tx is an open-source library that implements a backend for the Tinker API, enabling users to set up their own Tinker-like services on personal hardware. It supports end-to-end reinforcement learning (RL) and offers significantly faster sampling. The library is designed to be modular, allowing easy prototyping of new training algorithms, environments, and execution plans without compromising usability or speed.