A toolkit that makes Claude Code better at engineering — session memory, dependency analysis, large file navigation, 18 specialist agents, and crew teams for parallel multi-branch work.

Multi-agent AI platform with voice and text control. Visual workflows, web interface, and chat integrations (Telegram, Discord, Slack). Long-term memory, any LLM backend, extensible via MCP tools.

Persistent memory for Cursor IDE — like claude-mem, but for Cursor. Zero-config, no API key.

Shared memory and identity for your AI agents — Git-native, self-hosted, no vendor lock-in

AI Engineering Governance Platform — Session memory, feature registry, code intelligence, and rule enforcement for AI coding assistants.

Provide ready-to-use AI agent personas for Claude Code to deliver expert-level output with minimal setup and clear specialization.

Session memory for Claude Code — teaches Claude to maintain MEMORY.md, injects it at every session start

Session memory for Claude Code, Codex, and Gemini CLI — search past sessions, track failures, and resume work across context limits

A chatbot app using FastAPI, LangChain and OpenAI, with session-based memory and a simple HTML/JS frontend.

ContextIQ : Enterprise semantic firewall that scores query ambiguity locally before any LLM call. Detects Hinglish/mixed-language input via franc, fuzzy-matches unknown terms with fuse.js, and blocks Gemini until meaning is fully resolved using department context and session memory.

Persistent Memory Cortex for AI Coding Agents

Cross-tool session memory for AI coding assistants. One chronicle, every tool. Zero dependencies.

Team decision trail for AI-assisted development

MCP server for AI agents: intelligent code exploration (AST-based symbol search, architectural blueprints, call graphs, 90%+ token reduction) + persistent session memory (global preferences, project decisions)