By EconLab-AI
Semantic memory plugin for Claude Code - LanceDB-powered vector search with intelligent context injection
Matches all tools
Hooks run on every tool call, not just specific ones
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Persistent semantic memory for Claude Code. Native. Fast. Zero Python. Free.
Website · X / Twitter · Issues · Contributing · Discussions
UltraBrain gives Claude a persistent memory — across sessions, across days, across weeks. It automatically captures what you work on, compresses it into semantic observations, and injects the right context when you need it. Claude remembers your architecture decisions, bug fixes, project history, and brainstorming sessions.
The first tool that bridges Claude Desktop and Claude Code through shared knowledge.
Claude is powerful — but it forgets everything when a session ends. Every new conversation starts from zero. You re-explain your architecture, re-describe your conventions, re-contextualize your bugs.
UltraBrain fixes that. It runs silently in the background, building a semantic knowledge base of everything you work on. When a new session starts, the right context is already there.
With the Claude Desktop Integration, you can brainstorm in Claude Desktop, save that knowledge to UltraBrain, and have it automatically available in your next Claude Code session. No copy-pasting. No context loss.
npx claudepluginhub econlab-ai/ultrabrain --plugin ultrabrainComplete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Give your AI a memory — mine projects and conversations into a searchable palace. 33 MCP tools, auto-save hooks, and guided setup.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).