Reference MCP vs RunbookHermes

Reference MCP and RunbookHermes are both agent frameworks tracked by AIDiveForge. Below is a side-by-side comparison of pricing, capabilities, platforms, and ownership — sourced from each tool's live website and verified before publishing.

Reference MCP

Reference is a local MCP server that reads session transcripts and memory files — CLAUDE.md, AGENTS.md, and similar — from multiple AI coding tools, then exposes that history to whichever agent is asking. Register it once in each tool's MCP config and any agent can query what any other agent did before. The architecture is passive: Reference does not plan, execute, or chain tasks — it answers lookups. That scope is the point, and also the ceiling. Teams with more than a handful of tools, or who need structured, queryable memory rather than transcript search, will find the file-scanning approach starts to feel fragile as session volume grows.

RunbookHermes

The agent runs multi-signal diagnosis across observability data, builds a root-cause hypothesis, and generates or updates runbooks from what it learns — so the next incident with the same failure pattern starts from a documented baseline instead of a blank slate. The approval-gated remediation workflow means automated action doesn't ship without a reviewer, which matters when the blast radius is a production service. Where it breaks: the repo is five commits deep with zero open issues, which signals early-stage software, not battle-hardened infrastructure. Teams with complex multi-service topologies will hit integration gaps before the agent's reasoning does. Self-hosting is required, so operationalizing this adds a deployment and maintenance surface your platform team owns.

Attribute	Reference MCP	RunbookHermes
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	Yes
Self-hosted option	Yes	Yes
Platforms	Python / local	Linux, macOS, Docker, Kubernetes
Pros	Reads session transcripts from Claude Code, Codex CLI, and Cursor in one place, so you stop re-explaining decisions that were already made in a different tool last week. Fully local and offline, which means code and conversation history never leave your machine — critical for projects where sending context to a third-party sync service is off the table. MIT-licensed with no paid tiers and no account required, so there is no vendor relationship to manage and no access cliff if a pricing tier changes. Single MCP registration pattern works across supported tools, so you configure it once per tool rather than wiring a custom integration for each pair.	Evidence-driven root-cause hypothesis before remediation is proposed, so the on-call engineer reviews a reasoned diagnosis instead of raw signal noise — which means sign-off decisions take seconds rather than requiring independent investigation. Approval-gated execution model, so automated remediation actions cannot ship to production without a reviewer in the loop — which avoids the class of incidents caused by runaway automation acting on a misdiagnosis. Runbook generation and learning from live incidents, so operational knowledge accumulates in structured documentation rather than living exclusively in the memory of whoever was paged — which matters when the person who handled the last incident is on vacation for the next one. MIT license with full self-hosted deployment, so the agent and its incident data stay inside your own infrastructure — which removes the vendor-access and data-residency concerns that block AIOps adoption in regulated environments. Multi-signal ingestion across metrics, logs, and traces, so the agent correlates evidence across observability layers rather than diagnosing from a single data source — which reduces false-positive root-cause conclusions from incomplete signal.
Cons	Search runs over raw transcript files and markdown — not a structured index. Once session volume is high enough that the answer you need is buried in dozens of transcripts, recall becomes a best-effort grep rather than a reliable query, and teams at that point look at purpose-built vector stores like a local Chroma or Weaviate instance instead. Memory is local to one machine. A team of two engineers running the same agents on different laptops gets zero shared context — Reference has no sync layer. Teams who need shared agent memory across contributors abandon this and wire a shared database backend, at which point Reference's architecture no longer fits. There is no API and no programmatic query surface outside the MCP protocol. Any workflow that needs to pull agent history into a dashboard, a CI pipeline, or a custom tool has no supported path — the docs describe no extension point for that use case.	The repository has five commits and no closed issues, which means there is no public evidence of the agent performing correctly under real production incident load — teams that need a vetted tool before adoption will need to run their own failure-mode testing before trusting it on a live on-call rotation. Integration coverage is bounded by what the observability MCP toolserver ships with; teams running Datadog, Honeycomb, or custom telemetry pipelines that fall outside that surface will write and maintain their own integration connectors — at which point they are owning a non-trivial piece of the agent's input layer. There is no community or commercial support path documented in the repo; when the agent produces a wrong root-cause hypothesis or the approval workflow misbehaves at 3 AM, the escalation path is the GitHub repo and whatever institutional knowledge your team has built — teams that require SLA-backed support or vendor escalation will move to a commercial AIOps platform instead.

Bottom line

Only RunbookHermes exposes a public API. Choose based on which difference matters most for your workflow.

Frequently asked questions

What is the difference between Reference MCP and RunbookHermes?

Reference MCP is Free and open source, while RunbookHermes is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Reference MCP better than RunbookHermes?

It depends on your workflow. Use the side-by-side attributes (pricing, open source, API, self-hosted, platforms) to decide. AIDiveForge does not rank a universal winner — we publish verified facts so you can choose.