A lightweight knowledge system for small‑and‑medium teams tailored to AI Agents. It compiles Feishu Docs, local Markdown, code structures and curated business data into structured, traceable knowledge, guiding Agents to retrieve high‑quality content via pattern‑driven reasoning and exploration.
Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.
MySQL archiver for related tables: archive, copy, or purge a parent row with every child row, across foreign keys and application-managed relations. Dependency-ordered, verified before delete, crash-recoverable
A pure Go, cross-platform APFS and HFS+ toolkit: read, mount and write disk images without macOS. Reads DMGs and raw images, unlocks FileVault volumes, and writes populated volumes, snapshots, volume groups and transparent compression. Validated against Apple's fsck_apfs, hdiutil and Linux apfsck.
A pure Go, cross-platform toolkit for acquiring and building Windows installation media, without external tools (no wimlib, DISM, oscdimg, or cabextract). It provides an SDK plus a CLI.
A fully-featured ⚡️ HTTP/GraphQL/gRPC/Websocket-client 🐼 interface 🖥️ for your command-line ❤️, that supports the Jetbrains .http spec (with full scripting support).
Rust library wrapping 12 AI CLI tools as pluggable LLM providers — with OpenAI API client, ACP headless mode, agent loop, MCP server, and OpenAI-compatible REST API
A GitHub-like local viewer for the AI coding era — browse code, read Markdown, review changes, and preview PDF, SVG, CSV, Excel, and PowerPoint files, with an integrated terminal and no full IDE.