joshuaswarren/openclaw-engram
Local-first memory plugin for OpenClaw AI agents. LLM-powered extraction, plain markdown storage, hybrid search via QMD. Gives agents persistent long-term memory across conversations.
This tool gives your AI agents a persistent, private memory that lasts across conversations, so they don't forget important details, past decisions, or project context. It takes your agent's interactions and stores them as plain markdown files on your computer. This is ideal for anyone who uses AI agents for tasks like coding, research, or personal assistance and wants them to learn and remember information specific to their ongoing work.
Available on npm.
Use this if you are tired of repeatedly providing the same context to your AI agents or if you want your agents to recall past knowledge and preferences automatically.
Not ideal if you rarely use AI agents or if your agent use cases involve only simple, single-session interactions where no long-term memory is needed.
Stars
13
Forks
6
Language
TypeScript
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/joshuaswarren/openclaw-engram"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
aiming-lab/SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
zilliztech/memsearch
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
microsoft/kernel-memory
Research project. A Memory solution for users, teams, and applications.
zilliztech/GPTCache
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
TeleAI-UAGI/telemem
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication,...