flux/rust
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies - rtk-ai/rtk

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models - tailcallhq/forgecode
EdegQuake 🌋 High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation - raphaelmansuy/edgequake

Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. 🦀 - stakpak/agent

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/ - qdrant/qdrant

Fast, flexible LLM inference. Contribute to EricLBuehler/mistral.rs development by creating an account on GitHub.

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible) - BoundaryML/baml

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models - antinomyhq/forgecode

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more. - sigoden/aichat

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration - mikeyobrien/ralph-orchestrator