|
agentmemory: persistent memory for AI coding agents
Persistent memory for AI coding agents. agentmemory captures what your agent did, keeps it on your machine, and hands the right context back in the next sess...
|
84 % |
|
agentmemory — #1 Persistent Memory for AI Coding Agents Based on Real-World Benchmarks
agentmemory is the #1 persistent memory for AI coding agents. 95.2% retrieval R@5, 92% fewer tokens, 53 MCP tools, 12 auto hooks, 0 external DBs. Works with...
|
84 % |
|
Statefulai — Persistent memory for AI coding agents
Statefulai is persistent shared memory infrastructure for AI coding agents. Claude Code, Codex, and Cursor speak the same memory.
|
84 % |
|
Legate Studio | Memory as a service for AI agents
Legate is memory as a service for AI agents. One MCP endpoint gives Claude and any MCP client durable, searchable memory stored as Markdown you own.
|
83 % |
|
Agent-Memo.AI — Persistent AI Agent Memory | Free & Self-Hosted
One-line MCP setup — your AI agent remembers everything across sessions. Works with Claude Code, Cursor, Windsurf, OpenClaw, Hermes & any MCP agent. Auto-sav...
|
83 % |
|
Agent-Memo.AI — Persistent AI Agent Memory | Free & Self-Hosted
One-line MCP setup — your AI agent remembers everything across sessions. Works with Claude Code, Cursor, Windsurf, OpenClaw, Hermes & any MCP agent. Auto-sav...
|
83 % |
|
Engram, the memory layer for AI agents
Local-first, end-to-end encrypted, MCP-native semantic memory for Claude Code, Cursor, and any agent that speaks the Model Context Protocol.
|
83 % |
|
Remnic: one memory store for every AI agent
Open-source, local-first memory for AI agents. Claude Code, Codex CLI, Cursor, ChatGPT, and every MCP client share one memory store: plain markdown files on...
|
83 % |
|
PMB · local-first memory for your AI coding agent
PMB gives Claude Code, Cursor, Codex and Zed a real memory. Decisions, lessons and facts in one SQLite file on your disk. Offline, no API keys, no cloud.
|
83 % |
|
Knownbase: Persistent Project Memory for AI Coding Agents
Stop re-explaining your codebase to AI. Knownbase gives Claude Code, Codex and MCP agents persistent project memory that survives every session.
|
83 % |
|
RecCli — Temporal Memory Engine for AI Coding Agents
Give Claude Code long-horizon memory. Tri-layer memory engine that preserves full reasoning, keeps active context small, and recovers exact prior discussion...
|
82 % |
|
0d3sa — Local-first agent memory
od3sa-memory: local-first SQLite memory for coding agents, with an MCP server, knowledge packets, dreaming, and encrypted multi-device sync through a self-ho...
|
82 % |
|
Memwyre | AI Memory Platform — Persistent Shared Memory for Every AI
Memwyre is the AI Memory Platform that gives every AI tool, agent, and conversation a persistent, shared memory. Connect to Cursor, VS Code, ChatGPT, Claude,...
|
82 % |
|
Agentmemory for AI Coding Agents | Persistent Memory, MCP, and Team Recall
Give Claude Code, Codex, Cursor, OpenAI agents, and MCP workflows governed long-term memory for repos, decisions, procedures, and team handoffs.
|
82 % |
|
Locamem — Local-first AI agent memory (MCP, Claude Code)
Give Claude Code, Cursor and any MCP agent long-term memory in one local SQLite file — private, sub-10ms, $0 per recall, MIT. Memory that never leaves your box.
|
82 % |
|
Something went wrong - Retain7
|
82 % |
|
CodeMem - Memory for AI Code Agents
Universal Memory for AI Code Agents. Give Claude Code, Cursor, and Cline persistent memory across sessions.
|
81 % |
|
hippo-memory: Make your agent's memory work like a brain. Hippo is long-term memory for coding agents.
Make your agent's memory work like a brain. Hippo is long-term memory for coding agents.
|
81 % |
|
Anchor | Cross-Agent Memory MCP Server for Cursor, Claude Code, Cline & Aider
Local-first Model Context Protocol (MCP) server for persistent cross-agent memory. Switch between Cursor, Claude Code, Cline, and other AI coding assistants...
|
81 % |
|
NeuralMind — Codebase Memory for Claude Code & MCP Agents
Codebase memory for Claude Code, Cursor and any MCP agent: the right file at 51–242× fewer tokens than pasting every source file, on a public benchmark with...
|
81 % |
Detected social media networks