Interactive architecture diagrams for codebases

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Compress LLM context to save tokens and reduce costs

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

The Ultimate "Token Saver"

Autoscaling components for Kubernetes

Custom kube-scheduler for binpacking targeting Spark on EKS and other jobs workloads

🛰️ A CLI tool for tracking token usage from OpenCode, Claude Code, 🦞OpenClaw (Clawdbot/Moltbot), Pi, Codex, Gemini, Cursor, AmpCode, Factory Droid, Kimi, and more! • 🏅Global Leaderboard + 2D/3D Con…

Squad: AI agent teams for any project

A privacy-focused, self-hosted WhatsApp archiving tool. It captures messages (including deleted ones) via a linked device connection and stores them in your own Firebase Firestore database.

Sandbox any AI agent in seconds - zero setup, zero latency.

The open agent skills tool - npx skills

"Unit tests" for your agent skills

A bridge between Streamable HTTP and stdio MCP transports

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, h…

Runs AI agents in complete isolation

Compute substrate for AI agents: lightweight enough to live on your laptop, elastic enough to scale into the cloud and unleash unlimited resources.

https://nuetzlich.net/gocryptfs

A minimal mood logger and journal.

Docs for agents. No RAG

// Converts Thunderbird email filter rules to Sieve rules

This is a website that lists all type of social services in Berlin. It's supposed to give an easy access to services. Details can be read on the services' sides.

An MCP server who knows a development process and helps vibing the structured way

This repository features an Energy Optimization System (EOS) that optimizes energy distribution, usage for batteries, heat pumps& household devices. It includes predictive models for electricity pr…

A tool for mocking HTTP services

Codespaces but open-source, client-only and unopinionated: Works with any IDE and lets you use any cloud, kubernetes or just localhost docker.

An extremely fast bundler for the web

SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.