ZBS Index What actually exists in applied AI, with the source next to it

mcp server

Agent Coherence — Stale Write Guard (FS)

Coherence guard for shared files: denies stale writes so agents don't silently overwrite each other.

Description as published by the maintainer. Source

  • version 0.13.0
  • active

active — Most recent push to the repository was 2026-07-21.

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 10 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 2026-07-21 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 1 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 0.13.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-07-19 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-07-19 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

  • Synap Memory — last commit 2026-08-06, shares agent-memory, autogen, crewai
    Persistent memory for AI agents — log and recall conversation context over MCP.
  • com.knitli/codeweaver — archived, last commit 2026-06-16, shares llm-agent
    Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.
  • KIAgent — last commit 2026-08-05, shares llm-agent
    Your mail, chats and documents indexed into a local SQLite corpus, served to AI clients over MCP.
  • Pickle — last commit 2026-08-05, shares llm-agent
    Free, local MCP server that audits ClickUp, Slack & Teams for work that slipped through.
  • ChatSpatial — last commit 2026-08-03, shares llm-agent
    Natural language-driven spatial transcriptomics analysis with 60+ methods via MCP
  • GrantAi Memory — last commit 2026-03-16, shares crewai, langchain
    Persistent memory for AI agents. Infinite context with sub-millisecond recall.
  • Cathedral — Persistent Memory for AI Agents — last commit 2026-06-13, shares crewai, langchain
    Persistent memory and drift detection for AI agents across session restarts.
  • BrowseAI Dev — last commit 2026-08-02, shares crewai, langchain
    Evidence-backed web research for AI agents with citations and confidence scores.
  • agenthold — last commit 2026-07-07, shares crewai, langchain
    Shared versioned state for multi-agent AI workflows
  • AMZScout Skill + MCP — last commit 2026-08-06, shares crewai
    Amazon research from AMZScout data: analyze products & niches, keywords/PPC, and brand catalogs.

These share tags the maintainers applied themselves, such as agent-memory, autogen, crewai, langchain. 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: agent-memory, ai-agent, autogen, cache-coherence, crewai, langchain, llm-agent, multi-agent-systems, python, state-synchronization, token-efficiency.

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

Sources

  1. Cohexa-ai/agent-coherence on GitHub — GitHub, observed , trust tier 3.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.