> ## Documentation Index
> Fetch the complete documentation index at: https://adhd.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Roadmap

> What's next for ADHD — tracked openly on the issue tracker.

The live backlog is the [issue tracker](https://github.com/UditAkhourii/adhd/issues). Headline items:

* **Recursive deepen** — multi-level Tree-of-Thought expansion, not just one level
* **Pluggable scorers** — user-defined weights and custom trap detectors
* **Frame packs** — security, ML, frontend, distsys, product
* **Memory across runs** — learn which frames win for which problem shapes ([issue #10](https://github.com/UditAkhourii/adhd/issues/10))
* **Streaming output** during divergence
* **Cross-LLM support** — frames don't depend on Claude
* **Cross-model judging** for the eval suite ([issue #6](https://github.com/UditAkhourii/adhd/issues/6))
* **Hyperfocus / flow-state companion skill** ([issue #11](https://github.com/UditAkhourii/adhd/issues/11))

## Open research threads

Findings from the independent [Han research review](https://github.com/testdouble/han/blob/adhd-swarm-research/docs/research/adhd-application-to-han.md) are tracked openly:

* [Issue #16](https://github.com/UditAkhourii/adhd/issues/16) — human-in-the-loop applicability (CHI 2025 counter-evidence)
* [Issue #17](https://github.com/UditAkhourii/adhd/issues/17) — frames vs personas: how persona-prompting findings do or don't map
* [Issue #18](https://github.com/UditAkhourii/adhd/issues/18) — bridging the K=5 vs K=100 scale gap in the diversity literature
* [Issue #13](https://github.com/UditAkhourii/adhd/issues/13) — a controlled `parallel-N` vs `single-prompt-list-N` comparison

Want to push on any of these? [Join the Discord](https://discord.gg/NbWwkwwGw) — frame design, eval problems, trap-hunting, and neurodivergence-inspired research on reasoning architectures happen there in real time.