Home › Knowledge & Memory › kaeru

kaeru

Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a summary of what is open and overdue on every return to a project. Single Rust binary with no embedding model or LLM calls inside; one daemon serves several agents at once, with an optional self-hosted cloud for teams. Works with Claude Code, Codex, Cursor, opencode and any MCP client.

Topics: Knowledge & Memory

Connect

See the repository for installation instructions: https://github.com/LamantinAI/kaeru

Related servers

S

servers

File Systems

Direct local file system access.

★ 91,215 MCP Server

C

Context7

Knowledge & Memory

Official

Up-to-date code docs for any prompt

★ 62,984 MCP Server

H

hindsight

Knowledge & Memory

Hindsight: long-term memory for AI agents modeled on human memory.

★ 49,163 MCP Server

C

cognee

Knowledge & Memory

Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.

★ 32,184 MCP Server

S

Skill_Seekers

Knowledge & Memory

Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector…

★ 15,141 MCP Server

B

basic-memory

Knowledge & Memory

Local-first knowledge management with bi-directional LLM sync via Markdown files.

★ 4,163 MCP Server

Listed in punkpeye/awesome-mcp-servers (MIT)