Memory middleware
-
agent-memory-daemon
Manage AI agent memory with a filesystem-native daemon that consolidates, extracts, and organizes markdown memories through pluggable LLMs
-
ai-mind-map
🧠 MCP Server that reduces AI coding agent token usage by 80-99%. Knowledge graph + persistent memory + smart compression for Claude, Cursor, Copilot, and any MCP-compatible agent.
-
Chroma
Open-source embedding database (vector store) for building AI apps with memory and retrieval.
-
CodeRAG
Build semantic vector databases from code and docs to enable AI agents to understand and navigate your entire codebase effectively.
-
contextmemory
Track and save AI coding context across sessions and team members to maintain intent history and reduce repeated explanations.
-
contextual-workspace
🛠️ Build a modern, full-featured workspace with Next.js, offering authentication, payments, and real-time data integration for enhanced productivity.
-
CrewLoop
A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.
-
crm-with-blockchain-ai-rag
AI-native CRM with RAG pipeline, blockchain-verified deals, and programmable financial rails for modern sales teams
-
DecisionNode
Store and query shared structured memory across Claude Code, Cursor, Windsurf, and any MCP client with a local CLI and MCP server
-
Do-SOUL-Alaya
The local-first memory plane for CLI coding agents. Codex and Claude Code attach via MCP; SQLite-backed, evidence-gated, no GUI. Cross-session memory that the agent proposes and a governance gate decides.
-
engram
Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.
-
engrene-memory-bridge
Bridge AI tool memory with local files for shared context, resume work across IDEs and CLIs, and avoid vendor lock-in
-
F1
F1 [CLI] & [Skills] / Extension (🧩)
-
Giro.Gtdev
AI-powered Engineering Intelligence Platform for deterministic repository understanding, hybrid retrieval, and explainable AI-assisted development.
-
gossipcat-ai
Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch real bugs get picked more often. Agents that hallucinate get deprioritized. MCP server for Claude Code, Cursor, and other IDEs.
-
graph-memory
Manage and compress long conversation histories into structured knowledge graphs to improve context retention across sessions.
-
LangChain
Framework for building applications with large language models — chains, agents, tools, and retrieval.
-
LlamaIndex
Data framework for connecting custom data sources to large language models (RAG).
-
mcp-ai-memory
🧠 Manage semantic memory for AI agents with this production-ready Model Context Protocol server, enabling efficient storage and retrieval of contextual knowledge.
-
mcp-verified-repo-memory
Provide reliable, repository-scoped memory for AI coding agents with code citations, just-in-time verification, and stale-proof data management.
-
memcloud
☁️ Harness nearby devices to create a distributed in-memory data store, pooling RAM for fast and ephemeral storage on macOS and Linux systems.
-
memorize
Shared, persistent memory for AI coding agents — Claude Code & Codex share one local-first, event-sourced project brain that survives sessions and syncs across machines. No server, no API key required.
-
memroos
MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.
-
MindOS
Manage and link knowledge locally with MindOS, a human-AI system that supports collaborative thinking and intelligent data organization.
-
munin-memory
Persistent memory for AI assistants, self-hosted and provider-portable. MCP server with SQLite + FTS5 + sqlite-vec.
-
never-ask-twice
Enterprise Support MemoryAgent on Qwen Cloud that remembers customer context across sessions and proves it with a live re-ask-rate ablation.
-
quickrag
🚀 Index and search documents quickly with QuickRAG, using your preferred embedding provider and LanceDB for efficient similarity retrieval.
-
rorschach
Intelligence without consciousness. Process without self. Scale without limit.
-
wigolo
The go-to web for your agent!
-
vecmem