Vector Search

Semantic boundary preserving text chunker maintaining markdown headers, code fences, and paragraphs

Local multi-client RAG server over the Model Context Protocol.

面向企业交付的飞书多维表格 MCP Server —— 让 Claude Code / Cursor 安全读写业务台账

Crawl any documentation site and return heading-bounded, LLM-ready chunks with source metadata.

Local code exploration with progressive zoom and measured token budgets.

Let coding agents browse code across all your local, GitHub and Bitbucket repos, offline

Guardrails for LLM answers: exact checks against sources, PASS/REVIEW/FAIL, signed records.

Financial news as sourced statements with sentiment and tickers, grouped into developments.

Local vector and raster editing engine for agents: layered documents, saved sessions and exports.

Inspectable, correctable project memory in git-versioned Markdown for AI agents.

Self-hosted, uncensored AI agent: ask it tasks, search its long-term memory and your documents.

Biomedical evidence from PubMed, trials and FDA labels, with citations an audit can check.

Repository intelligence, code graph, history, papertrail, and cross-agent memory for coding agents.

Local hybrid-search memory for AI agents over plain Markdown. Multi-tenant, offline, no LLM.

Local Markdown search, navigation and editing via MCP, with optional vector embeddings.

Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.

Role-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.

Read large logs, JSON and docs in a fraction of the tokens. Offline, fact-preserving optimizer.

Persistent, local-first memory for AI coding agents. Remember, recall and forget across sessions.

Code context for AI dev tools: pack-scoped, cited code retrieval over MCP.