A lightweight MCP server that enables querying a project's corpus (docs, decisions, issues, skills) with cited answers and typed refusals via stdio JSON-RPC 2.0.
Local-first MCP server that puts your own LINE and Telegram chats behind one data layer — a daemon on your machine logs in with your own account, stores messages to JSONL + SQLite/FTS5, and exposes 6 MCP tools over streamable HTTP on 127.0.0.1. Not a hosted service and not an npx one-liner: you clone the repo, run the daemon, and log in yourself.
Compresses multi-turn conversation history by stripping verbose boilerplate and filler tokens while preserving critical tool parameters and named entities, deterministically cutting inference costs by 40-60%. Runs as a zero-dependency Python MCP server or importable module, compatible with Claude Desktop, Cursor, and other MCP runtimes.
Enables AI coding agents to retrieve cited git-history explanations for files and tickets, compile a Team Engineering Contract from repository artifacts, and follow guided Understand/Build workflows over MCP stdio. It lets clients such as Grok, Claude Code, Codex, Kiro, and Cursor share the same tools for evidence-backed repository understanding.
Enables MCP clients to search, record, correct, and review the provenance and version history of memories, and to obtain answers composed from guarded context in which private values are replaced by placeholders and resolved locally on the device. Exposes these capabilities through dependency-free tools over stdio.
Connects an LLM to specialized MCP servers via stdio, enabling authenticated GitHub repository, issue, file, and code operations alongside TF-IDF retrieval over employee PDF records and QA test-case generation and result validation. It exposes tools, a read-only resource, and reusable prompt templates so a client can discover and orchestrate multiple capabilities in one workflow.