Agent Memory

Local-first MCP server + CLI that gives terminal AI agents an endless semantic memory via Anchored Compacting, keeping the context window small.

Local-first external brain CLI for coding agents — SQLite-backed context, graph-aware recall, and governed memory for Claude Code, Codex, and MCP clients.

Zettelkasten-based agent memory system with bidirectional links

A cognitive layer for Cursor's AI agent: lossless token savings via a content-addressed evidence store, plus verifiable semantic memory, project world model and skill runbooks. Fully local, zero telemetry. | 给 Cursor agent 的认知层：内容寻址证据库无损省 token；可验证语义记忆、项目

Continual learning MCP server for AI agents — topology-aware knowledge graph with kappa-routing, exposed as 5 loop-phase machines (retrieve/route/act/learn/consolidate), causal metadata, and neural embeddings. One of four MCP servers in the [&] three-prot

Shared team memory for AI coding agents — MCP server and CLI for persistent, queryable knowledge across sessions and teammates

Decision provenance for AI-coded codebases: the why, and what was already tried and rejected.

Portable agent working state MCP server — tasks, plans, notepads, memory, and rules for any AI coding agent

MCP server for pūrmemo - AI conversation memory that works everywhere. Save and recall conversations across Claude Desktop, Cursor, and other MCP-compatible platforms. Intelligent context extraction, smart titles, living documents.

MCP server for persistent, cross-agent working memory. BYO brain directory.

MCP server for Lithium. Give AI agents tools to navigate, store, and retrieve structured data.

Governed local-first memory for coding agents

Continuous learning for Kiro agent sessions on AWS. Passive tool-use capture, LLM extraction, and synchronous context injection — inspired by claude-mem, aligned with Bedrock AgentCore Memory.

Local-first MCP server that gives AI coding agents a living, browser-viewable project wiki and a project-local memory store, so the agent stays oriented and the human stays in control.

Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.

Persistent memory for AI coding agents. Knowledge graph with 4-tier taxonomy, confidence scoring, and MCP protocol support for Claude Code, Cursor, Gemini CLI, Windsurf, Cline, Codex, and OpenCode.

Geometric memory for AI coding agents. Installs the 'attention-matters' package.

Search your Notion, Slack, GitHub, and Google Drive from your AI agent. One command setup. Works with Claude Code, Cursor, and any MCP client.

Vitest harness and matchers for testing MCP (Model Context Protocol) servers — connect over an in-memory transport and assert on tools, resources, prompts, and results.

Spatial AI lab; maker and maintainer of the emem protocol. The architecture is an encoder and a decoder: satellites and detectors encode the world into signed, content-addressed tokens (nine shapes: emem:fact:, emem:cell:, emem:entity:, emem:bundle:, emem:raster:, emem:cube:, emem:rasterset:, emem:…