its-over-9k
Active·★ 0·MIT·Updated 2026-08-28
Its-Over-9k is a memory framework for AI agents that provides persistent, portable, token-efficient knowledge across sessions and devices. It uses a hierarchical 5-level lazy loading system and hooks to automatically capture session exchanges and generate checkpoints, enabling agents to continue work without re-reading codebases.
#ai-agents#ai-tools#claude#llm#mcp#mcp-server#mcp-servers#memory
01
Features
01Automatic session memory - every conversation is recorded across sessions and devices
02Haiku background checkpoints - extracts lessons and decisions every N exchanges
03Project-based organization - memory is tied to projects, not sessions
04Skills system - structured behavior files loaded on demand
05Embeddable SDK - use HmemStore in your own agents and tools
02
Compatibility
Claude Code
Full integration
Verified via docs
OpenCode
Supported
Verified via docs
Gemini CLI
Supported
Verified via docs
Cursor
MCP-based
Verified via docs
Windsurf
MCP-based
Verified via docs
Cline
MCP-based
Verified via docs
03
Quick start
1
$ npm install -g its-over-9k
04
Use cases
↳Persist project context across AI sessions without re-reading code
↳Sync memory across multiple devices using encrypted sync
↳Share company memory among team agents and tools
05
Alternatives
hmem★ 24
Humanlike persistent memory for AI agents — MCP server with 5-level lazy-loaded SQLite memory. Works with Claude Code, Gemini CLI, Cursor, Windsurf, OpenCode.
YourMemory★ 270
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
multi-agent-memory★ 64
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
tradememory-protocol★ 1.4k
Memory layer for AI trading agents. Outcome-weighted recall, autonomous strategy evolution, 15 MCP tools.
open-ontologies★ 1.2k
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL ontologies. In-memory Oxigraph triple store, native OWL2-DL tableaux reasoner, SHACL validation, SPARQL, versioning. Single binary, no JVM.
AgentRecall-MCP★ 371
Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
Comments
Log in to leave a comment
No comments yet. Be the first!