mcp server
Nautilus Compass
Drift-aware cross-agent memory · MCP/A2A · LongMemEval-S 56.6% · 1/15 Zep cost
Description as published by the maintainer. Source
- version 1.6.2
- active
- memory and context
- evaluation
active — Most recent push to the repository was 2026-08-05. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 6 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-08-05 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 31 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.6.2 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-05-18 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-05-18 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub |
Where to get it
Related, by what their authors tagged them
-
Lore
— last commit 2026-08-02, shares cross-agent
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
-
WingmanProtocol Agent Gateway
— last commit 2026-07-17, shares a2a, agent-memory, agentic-ai
Durable self for AI agents: one-call resume, memory, real browser, free chat + hire real humans.
-
io.github.Dakera-AI/dakera-mcp
— last commit 2026-07-31, shares agent-memory, agentic-ai
Agent memory engine — 86 MCP tools, self-hosted, single Rust binary
-
SYNAPSE CHANNEL
— last commit 2026-08-06, shares a2a, agentic-ai
Local-first multi-agent coordination for messages, leases, shared plans, status, and resources.
-
io.github.CSOAI-ORG/csrd-compliance-mcp
— last commit 2026-06-16, shares a2a, agentic-ai
Csrd Compliance MCP Server by MEOK AI Labs
-
io.github.CSOAI-ORG/gdpr-compliance-ai-mcp
— last commit 2026-08-04, shares a2a, agentic-ai
Gdpr Compliance Ai MCP Server by MEOK AI Labs
-
io.github.CSOAI-ORG/healthcare-fhir-mcp
— last commit 2026-06-15, shares a2a, agentic-ai
healthcare-fhir-mcp MCP server by MEOK AI Labs
-
io.github.CSOAI-ORG/iso-42001-ai-mcp
— last commit 2026-06-26, shares a2a, agentic-ai
Iso 42001 Ai MCP Server by MEOK AI Labs
-
io.github.CSOAI-ORG/meok-cra-annex-iv-classifier-mcp
— last commit 2026-06-26, shares a2a, agentic-ai
EU Cyber Resilience Act product classifier MCP. Classifies PDEs into CRA hierarchy (default / Class
-
io.github.CSOAI-ORG/meok-dora-tlpt-planner-mcp
— last commit 2026-05-31, shares a2a, agentic-ai
meok-dora-tlpt-planner-mcp MCP server by MEOK AI Labs
These share tags the maintainers applied themselves, such as cross-agent, a2a, agent-memory, agentic-ai. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.
This is not a recommendation and not a test result. It is a map of what the authors said their work is about.
How the author describes it
Topics the maintainer set on GitHub: a2a, agent-memory, agentic-ai, claude-code, cross-agent, mcp, mcp-server, nautilus.
Bring your own setup
We take apart real AI setups every week and show what broke, what cost too much, and what the trace actually said. If you run agents on real work, that is where the useful conversation is.
Join ZBS AI Practice Lab