# MIST Stack

> Eval-driven infrastructure for AI systems. MatchSpec, InferMux, SchemaFlux, TokenTrace.

## About

The MIST stack is eval-driven infrastructure for AI systems. Four Go tools, zero external dependencies, one universal message protocol.

MIST stands for MatchSpec, InferMux, SchemaFlux, TokenTrace.

## Tools

- matchspec: Eval framework for AI systems. Define datasets, write graders, run suites, gate deployments on passing thresholds.
  - Landing: https://miststack.dev/matchspec/
  - Docs: https://miststack.dev/matchspec/docs/
- infermux: Inference router for AI systems. Load balance across providers, fail over automatically, cost-optimize model calls.
  - Landing: https://miststack.dev/infermux/
  - Docs: https://miststack.dev/infermux/docs/
- schemaflux: Structured data compiler. Parse markdown and frontmatter, run 12-pass IR pipeline, emit typed output.
  - Landing: https://miststack.dev/schemaflux/
  - Docs: https://miststack.dev/schemaflux/docs/
- tokentrace: Observability for AI inference. Track cost, latency, and quality across your stack. Alert on regressions.
  - Landing: https://miststack.dev/tokentrace/
  - Docs: https://miststack.dev/tokentrace/docs/
- mist-go: Shared Go library implementing the MIST protocol. Protocol, transport, metrics, circuit breaking, checkpointing. Zero external dependencies.
  - Landing: https://miststack.dev/mist-go/
  - Docs: https://miststack.dev/mist-go/docs/

## Use Cases


- AI Agents: Cascading errors, context rot, and agents that ignore instructions. What the benchmarks don't show about production agents.
  - https://miststack.dev/pillars/ai-agents/
- Model Harnesses: Bad data, silent failures, and catastrophic forgetting. The real problems behind fine-tuning that tutorials skip.
  - https://miststack.dev/pillars/model-harnesses/
- RL Environments: Reward hacking, reproducibility crises, and the debugging abyss. Why RL training fails and what's missing from the toolchain.
  - https://miststack.dev/pillars/rl-environments/

## Links

- Site: https://miststack.dev
- Repo: https://github.com/greynewell/mist-go
- Author: https://greynewell.com