Ombre-Brain
Active·★ 156·MIT·Updated 2026-04-06
Ombre Brain is a long-term emotional memory system for Claude. It tags memories using Russell's valence/arousal coordinates, stores them as Obsidian-compatible Markdown, connects via MCP, and implements a forgetting curve. It features natural decay and active surfacing of unresolved memories.
#ai-agent#chatgpt#claude#emotional-intelligence#gemini#long-term-memory#mcp#mcp-server
01
Features
01Emotional tagging using valence and arousal dimensions
02Natural forgetting with modified Ebbinghaus curve
03Weight pool surfacing of unresolved memories
04Obsidian-native Markdown storage with YAML frontmatter
05API degradation to local keyword analysis when unavailable
02
Compatibility
Claude Desktop
Native via MCP stdio
Verified via docs
Claude.ai
Supported via HTTP tunnel
Verified via docs
Obsidian
Native Markdown storage
Verified via docs
03
Quick start
1
$ git clone https://github.com/P0lar1zzZ/Ombre-Brain.git
2
$ cd Ombre-Brain
3
$ python -m venv .venv
4
$ source .venv/bin/activate
5
$ pip install -r requirements.txt
04
Use cases
↳Persistent cross-conversation memory for Claude
↳Tracking emotional patterns and unresolved topics over time
↳Diary-style archival of daily conversations
05
Alternatives
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.
multi-agent-memory★ 64
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
llm-wiki-kit★ 61
Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube — your agent remembers forever. Based on Karpathy's LLM Wiki pattern.
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.
akemon★ 21
Train your AI agent. Let it work for others. Hire others' agents. Like Pokemon, but for AI agents.
Comments
Log in to leave a comment
No comments yet. Be the first!