* [Ollama v0.33.0](https://github.com/ollama/ollama) – Tool for running and managing large language models.

* [LLM Gateway v1.14.0](https://github.com/theopenco/llmgateway) – API gateway that routes and manages requests across multiple LLM providers with an OpenAI-compatible API, usage analytics, and cost tracking.

* [Crush v0.91.0](https://github.com/charmbracelet/crush) – Terminal-based AI coding assistant supporting multiple LLMs, sessions, and extensible capabilities.

* [DSPy-Go v0.88.0](https://github.com/XiaoConstantine/dspy-go) – Native Go framework providing systematic prompt engineering, composable modules, and automated reasoning for building LLM applications.

* [llm-docs-builder v1.0.0](https://github.com/mensfeld/llm-docs-builder) – Transforms markdown documentation to reduce token usage and optimize content for large language models and retrieval-augmented generation systems.

* [NestJS MCP Server Module v2.0.1](https://github.com/rekog-labs/MCP-Nest) – NestJS module that exposes tools, resources, and prompts using the Model Context Protocol.

* [HashCortX v2.5.0](https://github.com/Hash-7777/HashCortX) – Local-first macOS AI workspace combining multi-provider chat, autonomous coding agents, multi-agent swarms, specialist agents, and financial and security tools.

* [sqz v1.6.0](https://github.com/ojuschugh1/sqz) – Compress LLM context to save tokens and reduce costs

* [Stagehand stagehand-server-v3/...](https://github.com/browserbase/stagehand) – AI-enhanced browser automation framework combining code and natural language for reliable production use.

* [Thunderbolt v0.1.123-nightly.202...](https://github.com/thunderbird/thunderbolt) – Cross-platform AI client for on-prem and local models with enterprise features and self-hosting support.