llm

Context intelligence layer for LLM agents: persistent memory with write-time dedup, sensitivity tagging, conflict detection, and hierarchical decay. ~12ms. No LLM calls. MIT.

[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

Your voice is the fastest keyboard. Speak freely, let AI polish, and paste right at your cursor. Free forever offline speech-to-text for macOS, Windows & Linux.

Ollama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.

Real-time guardrail that shows token spend & kills runaway LLM/agent loops.

Beginner's Guide to reComputer Jetson

mcp-use is the framework for MCP with the best DX - Build AI agents, create MCP servers with UI widgets, and debug with built-in inspector. Includes client SDK, server SDK, React hooks, and powerful dev tools.

GraphRAG / From Local to Global: A Graph RAG Approach to Query-Focused Summarization

c4 GenAI Suite

Aiming to provide a seamless and privacy driven chatting experience with open-sourced technologies(Ollama), particularly open sourced LLM's(eg. Llama3, Phi-3, Mistral). Focused on ease of use. Available on both Windows and Mac.

Prompt packs that make any AI agent a LaTeX expert — fix errors, polish writing, format for venues, read papers, recover source

Knowledge work automation with AI agents

Evaluation tools for Retrieval-augmented Generation (RAG) methods.

Cognitive memory database for AI agents — consolidates duplicates, detects contradictions, fades stale memories via temporal decay. Rust, Apache-2.0, ships as library / MCP server / HTTP cluster.

A Python Telegram bot powered by Google's gemini-pro LLM API

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

Multi-agent LLM system for intelligent replenishment decisions in manufacturing supply chains

Run any Large Language Model behind a unified API

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

An MCP Server for Ollama