Vector Search

Recognition-first cross-agent memory federation. One shared memory across all your agents.

Local AI studio on your GPU: images, video, music, voice, RAG. Needs the Guaardvark app installed.

Local-first, cloud-friendly memory — 100+ tools, 99.2% LongMemEval-S retrieval@8, hybrid search.

Guardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.

Local MCP server exposing codepreproc's code-context tools to Claude Code

Private on-device memory & retrieval for AI assistants — offline vector + lexical search.

Dev intelligence layer: 7 MCP tools for graph-powered codebase reasoning.

Governance-grade knowledge-base format (OKF-compatible) plus CLI and single-writer MCP server

Local emulator for Slack, Gmail, Drive, GitHub, Jira, Notion, S3 and more, with per-document ACLs

Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option

Give your coding agent the right code: graph + hybrid search, packed into a token budget. Local.

PowerPoint (.pptx) MCP server: editable vector diagrams, tables, budgeted reads, render-to-verify

Let Claude create and edit fully editable vector nodes on the Figma canvas.

Answer questions from PDFs converted to .htpd: exact text with pages, or 'Not found in this file.'

Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.

Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.

One shared, durable memory for your AI coding agents — local-first, zero-dependency.

Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.

High-dimensional vector embedding semantic SimHash deduplication sentinel with LRU cache simulation

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