Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.

Artificial Intelligence Infrastructure-as-Code Generator.

MCP Toolbox for Databases is an open source MCP server for databases.

Embeddable vector database for Go with Chroma-like interface and zero third-party dependencies. In-memory with optional persistence.

Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.

Production-grade planning and orchestration for complex multi-agent workflows.

DevQualityEval: An evaluation benchmark 📈 and framework to compare and evolve the quality of code generation of LLMs.

[deprecated] AI Gateway - core infrastructure stack for building production-ready AI Applications

Dive is an AI toolkit for Go that can be used to create specialized AI agents, automate workflows, and quickly integrate with the leading LLMs.

ACP is the Agent Control Plane - a distributed agent scheduler optimized for simplicity, clarity, and control. It is designed for outer-loop agents that run without supervision, and make asynchronous tool calls like requesting human feedback on key operations. Full MCP support.

Run multiple resource-heavy Large Models (LM) on the same machine with limited amount of VRAM/other resources by exposing them on different ports and loading/unloading them on demand

MaK(Mac+Kubernetes)llama - Running and orchestrating large language models (LLMs) on Kubernetes with macOS nodes.

DSPy Go implementation

quickly translate epub books into a bilingual book using Anthropic LLMs

🤖 Automatic financial news feed powered by AI.

A command line tool for journaling daily accomplishments and summarizing them to create a bragging document.

A framework for building multi-agent AI systems. Enables LLMs to collaborate through hierarchical organization, parallel task execution, and extensible tools.

🐙 Transform GitHub repositories into structured JSON for LLMs and AI-powered code analysis.

Props AI provides this open source proxy for Open AI that allows you to track token usage and send it into a kafka stream

Conversational assistant for openai services, with this tool you can test all the models available and includes advanced modes to modify the contextual information for specifical uses, engine, results, probabilities, topp, temperature, penalty and frequency according to the ammount or words, tokenized strings with real-time online results.