* [Headroom v0.40.0](https://github.com/headroomlabs-ai/headroom) – Headroom compresses tool outputs, logs, RAG chunks, files, and conversation history before they reach an LLM to reduce tokens while preserving answers.

* [GSD Core v1.16.0](https://github.com/open-gsd/gsd-core) – Lightweight meta-prompting, context-engineering, and spec-driven framework that runs AI coding agents in a disciplined phase loop to avoid context rot.

* [OpenSpec v1.14.1](https://github.com/Fission-AI/OpenSpec) – Spec-driven workflow aligning humans and AI coding assistants to agree on requirements before coding.

* [BKN Foundry v0.1.4](https://github.com/openbkn-ai/bkn-foundry) – BKN Foundry is a backend framework that provides unified data access, safe execution, and governance for an ontology-driven business knowledge network.

* [ThoughtDAG v0.5.17](https://github.com/chenxiachan/thoughtdag) – ThoughtDAG provides an editable thought-graph canvas to map LLM conversations, select what models see next, and pinpoint matching context across agents.