Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.
TypeScript agent-memoryai-agentsanthropicclaude-codecursorgitknowledge-baseknowledge-graphllmmarkdownmcpmcp-servermodel-context-protocolnote-takingobsidianpkmragsecond-brainself-hostedzettelkasten
docs: repo moved to rwnalds/engram — fix Render deploy link
Ronalds Palaciscb45fd79b05d
diff --git a/README.md b/README.mdindex 0f4b9f1..a0cae3c 100644--- a/README.md+++ b/README.md@@ -19,7 +19,7 @@ vault of `.md` files (or the bundled `sample-vault/`) and every agent on your teand write the same knowledge. Humans edit it in a fast dashboard; agents edit it over one MCP endpoint.[](https://railway.com/deploy/engram?referralCode=PEidIe&utm_medium=integration&utm_source=template&utm_campaign=generic)-[](https://render.com/deploy?repo=https://github.com/klyiro/engram)+[](https://render.com/deploy?repo=https://github.com/rwnalds/engram)[](./LICENSE)> **Why it exists:** autonomous AI agents forget everything between sessions. Engram is the