This is a local-first memory system that uses orbital mechanics as a metaphor for storing and retrieving AI conversation context. It runs entirely on your machine without external API dependencies, making it a privacy-focused option for giving Claude persistent memory across sessions. The MCP-native design means it hooks directly into the protocol rather than bolting on through a third-party service. Reach for this when you want conversation continuity without sending your data to another cloud service, though the orbital mechanics approach is more conceptual than practical since the source doesn't detail the specific memory operations or retrieval methods exposed through MCP tools and resources.
STELLAR_PROJECTActive project name for memory isolation
STELLAR_DB_PATHPath to SQLite database file (default: ~/.stellar-memory/stellar.db)
STELLAR_API_PORTREST API port (default: 21547)
STELLAR_SUN_TOKEN_BUDGETMax tokens for Sun context (default: 800)
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent