Projekte.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

🪓 An orchestration engine for background tasks, AI agents, and durable workflows

AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist Claude agents (FastAPI + Next.js).

TSP自托管、零运维的 A 股「选股 + 监控 + 回测」量化工作台 | LLM能力驱使策略定制+个股分析+复盘 | 自由接入第三方数据源与个性化扩展数据 | 个人开源 ,非第三方官方项目

Restish is a CLI for interacting with REST-ish HTTP APIs with some nice features built-in

Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.

🎙️ Speaker recognition service for Home Assistant using voice embeddings - train on voice samples and identify speakers.

Aplicação fullstack de gerenciamento de cardápio com frontend web, API REST em FastAPI, banco de dados SQLite e interface CLI para operações CRUD.

A FastAPI service that fronts the rate-limited football-data.org API with a Redis cache, turning a 10-requests-per-minute upstream budget into unlimited reads. The interesting problem is the cache: TTL by data volatility, stampede control, stale-while-revalidate, and explicit failure behaviour, all observable from curl via an X-Cache header.