Sage
VerifiedInstitutional memory for AI agents with real BFT consensus. 4 application validators vote on every memory before it's committed — no more storing garbage. 13 MCP tools, runs locally, works with any MCP-compatible model. Backed by 4 published research papers.
Install
No auto-install command available for this server.
Check the GitHub repository for setup instructionsSafety Report
details
Authentication detected: auth_middleware, connection_string, oauth
details
No CORS-relevant transport detected (likely stdio)
details
Rate limiting detected: rate_limit_middleware, requests_per
details
No known CVEs in dependencies
details
No known vulnerable dependencies detected
details
No dangerous code patterns detected
details
License: Apache-2.0
details
Last commit 2 days ago
Frequently Asked Questions
What is Sage?
Institutional memory for AI agents with real BFT consensus. 4 application validators vote on every memory before it's committed — no more storing garbage. 13 MCP tools, runs locally, works with any MCP-compatible model. Backed by 4 published research papers.
Is Sage safe to use?
Yes, Sage has passed our 8-point security audit and is rated Verified. All checks including authentication, dependency audit, and known CVE scan passed.
What are alternatives to Sage?
Similar MCP servers include Context7, Cognee, Hindsight. Each serves a similar purpose but may differ in features, language, and compatibility.
Similar MCP Servers
Context7
VerifiedUp-to-date code documentation for LLMs and AI code editors.
Cognee
CautionMemory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources
Hindsight
UntestedHindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory