Kikubot vs Myco Brain

Kikubot and Myco Brain 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.

Kikubot

Each Kikubot container polls one IMAP mailbox, feeds incoming email into an LLM agentic loop with a configured tool set, and replies over SMTP. Multi-agent workflows emerge naturally: a coordinator agent emails specialists, specialists reply, threads become the audit trail. The architecture requires a running mail server, which adds operational surface area before a single agent does anything useful. Teams with no existing mail infrastructure will spend more time on SMTP/IMAP setup than on agent logic. When the email-as-bus metaphor stops fitting — high-frequency tasks, sub-second latency requirements, or webhooks that can't wait for a polling interval — this architecture forces a full redesign.

Myco Brain

The core mechanic is deterministic writes: the application code writes facts to Myco's Postgres store, not the LLM, so every stored fact carries a source document, a confidence score, and a full audit trail queryable via brain_why. One MCP server exposes that memory to Claude Code, Cursor, Codex, Windsurf, and any other MCP-compatible client simultaneously — write from Claude Desktop, retrieve from Cursor, no sync step required. The vendor publishes a 500-question LongMemEval result and a recall@5 figure using a recency reranker, both on the full benchmark set. The hard ceiling appears when your agents need to act on what they remember — Myco stores and retrieves facts; it does not plan, route, or execute tasks, so orchestration logic lives elsewhere.

Attribute	Kikubot	Myco Brain
Pricing	Free	Free
Free trial	No	No
Open source	Yes	Yes
Has API	No	No
Self-hosted option	Yes	Yes
Platforms	Docker containers, IMAP/SMTP email servers	Postgres, Docker, MCP clients
Released	—	2026
Pros	Email threads serve as the native audit log, so every agent action and handoff is inspectable without separate observability tooling — which means compliance reviews don't require digging through custom log pipelines. Per-agent LLM selection, so you assign an expensive reasoning model only to the coordinator and run cheaper models on high-volume specialist agents, rather than paying frontier rates across the entire cluster. Docker-native self-hosted deployment, so the agent network runs inside your existing infrastructure perimeter without data leaving to a managed SaaS layer — critical for teams with data residency requirements. Agents collaborate by emailing each other, so adding a specialist to an existing workflow is one new container and one new mailbox — not a code change to the coordinator or a new API contract. MIT license with no paid tier, so there is no feature gate that forces a pricing conversation when you scale the number of agents or the volume of messages.	Deterministic write path means the LLM never authors the facts stored in memory, so every retrieved fact links to a source document and confidence score — which means regulated teams get an audit trail without building one themselves. One MCP server shared across all connected clients, so a fact written from Claude Desktop is immediately readable by a Cursor agent without a sync job or intermediate API call. Full-stack boot with docker compose and no required API keys, so teams evaluate and prototype without committing credentials or cloud spend before the architecture is validated. Content-hash deduplication on document ingestion, so re-importing the same ChatGPT or Claude export twice does not corrupt or inflate the memory store. Graph queries over entity relationships via the built-in tools, so agents can retrieve not just isolated facts but the web of connections between people, decisions, and documents in the store.
Cons	IMAP polling sets a hard floor on response latency: tasks that need an answer in under a few seconds cannot be served by this architecture regardless of how fast the LLM responds. Teams with real-time requirements switch to an event-driven framework with a webhook-native message queue. A running mail server is a prerequisite, not an optional add-on — teams without existing SMTP/IMAP infrastructure absorb that operational cost before any agent logic runs. At small team size this is a weekend of setup; at scale it becomes a dedicated reliability concern. Complex branching workflows — where the next step depends on structured output from the previous one, across more than two or three agents — have no visual model or built-in router; all routing logic lives in prompt engineering or tool code. Teams with deep conditional logic report maintaining a parallel scripting layer, which means two systems instead of one. GitHub star count and issue tracker show early-stage adoption, which means community answers to non-obvious configuration problems are scarce. Teams encountering edge cases in IMAP handling or tool integration are reading source code, not Stack Overflow.	Myco stores and retrieves facts — it has no planner, no task router, and no execution loop. Teams building agents that need to act on retrieved memory must implement that logic themselves, which means maintaining a separate orchestration layer alongside the memory layer. The self-hosted path requires running Postgres 16 with pgvector and managing that infrastructure. Teams without existing Postgres ops experience hit configuration and maintenance overhead that the single docker compose up does not eliminate long-term. Semantic search requires a local Ollama instance or an external embedding provider; teams without GPU-capable self-host infrastructure who want semantic recall beyond full-text search are blocked until the cloud offering exits beta — at which point they are evaluating a hosted product with a waitlist rather than a drop-in replacement. No API surface is exposed outside the MCP protocol, so teams whose agents run outside MCP-compatible clients cannot integrate without building a custom MCP wrapper — teams with that constraint typically move to a vector database with a standard REST or gRPC API instead.

Bottom line

Kikubot and Myco Brain are closely matched on pricing model, openness, and API availability — pick by feature set and platform support in the table above.

Frequently asked questions

What is the difference between Kikubot and Myco Brain?

Kikubot is Free and open source, while Myco Brain is Free and open source. Compare pricing, free trial, API, platforms, and pros/cons in the table above on AIDiveForge.

Is Kikubot better than Myco Brain?

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.