01 · Encode
Where knowledge lives
Expertise that only lives in prompts or fine-tuned weights is hard to audit and easy to drift. SMEme encodes it as decision-trees you can inspect, version, and deploy.
Sovereign expert reasoning — decision-trees your agents call through MCP
Not every task should run inside a language model — especially expert reasoning. SMEme helps you encode judgment as decision-trees, then compiles them into a logical analysis engine. Your agent gathers evidence; SMEme evaluates against your rules and returns a deterministic, attributable result. Language models handle language. SMEme handles logical analysis.
The short version
Decision-trees, not model weights
02 · Engine
Not a flowchart
A diagram for humans isn’t enough. SMEme decision-trees compile, validate, and evaluate deterministically — same facts in, same conclusion out.
03 · Sovereignty
How hosted trees are handled
You own what you encode. Evaluation runs on SMEme infrastructure, not inside the LLM provider. Self-host when policy requires your own environment.
Read our principles →neuro-symbolic AI at scale
SMEme encodes knowledge — not prompts
You see a decision tree; SMEme sees a micro-theory it can reason over. Run full logical analysis on real evidence your agent gathers, or one-off hypotheticals — verifiable, transparent, and under your control.
LLM-assisted expert system
Agent gathers facts → SMEme tests reachability of conclusions
Your agent is connected to your data. Ask it to gather the relevant facts and call SMEme to evaluate what conclusions can be reached — auditable decision trees, not a flow-chart pasted into a saved prompt.
Logical analysis assistant
Hypotheticals & how-to questions → solver-backed what-if / how-to-reach
Ask “what would have to change to reach a different conclusion?” or “what if this fact were false?” Rich, structured results return directly into chat as context.
Pricing
Hosted or self-host
We operate the platform and you own the decision trees. Need your own environment? Deploy the same Core engine there instead.
Free
Try SMEme end-to-end
$0 / month
No credit card required
- 3 decision trees
- 150 MCP tool calls* / month
- 3 AI-assisted decision-tree builds / month
- MCP server access
Most popular
Pro
For individual experts
$49 / month
Billed monthly · cancel anytime
- 20 decision trees
- 1,500 MCP tool calls* / month
- 20 AI-assisted decision-tree builds / month
- MCP server access
- Email support
Self-hosting
Bring your own infrastructure
Same Core engine, deployed in your environment when residency or policy requires it.
* How usage is counted
* MCP tool calls are weighted by operation type. Evidence validation and a standard decision tree evaluation each count as 1 (a typical agent session uses both); “what if” follow-ups count as 2; “how to” follow-ups (reaching a different outcome) count as more. Listing decision trees and downloading worksheets do not count toward your allowance.
Turn your expertise into a tool agents can run
Build your first decision tree free. No credit card — connect your agent when you're ready.