Preview. These maps are our reading of public sources and haven't been checked with the projects' maintainers yet.
STROT
Compiles a decision task once with an LLM into a frozen Python artifact; a small local model (Julia-1 by default) then makes each decision on CPU with conformal calibration and abstention. Never mentions Jev or the System One wire format.
github.com/strot-ai/STROT-CompilerChanged direction
PyPI strot-ai first released 2026-03-09 (before Jev), latest 0.11.1 on 2026-10-18. The Show HN link (2026-10-19) points to Project-STROT, which now resolves to a new repo, STROT-Compiler (created 2026-10-11, pushed 2026-10-25), reframed as 'compile System 2 reasoning into System 1 decisions'. (checked 2026-10-25)
In The Jev ecosystem
Where it stands apart
- Is it actively maintained? active, but changed direction (pivot, fork, or rename) (0% of 21 others)
- Can it run entirely on your own device or infrastructure, without the maker's servers? partly (some features need the maker's servers) (19% of 21 others)
- Which shared standard or format does it mainly build on? none of these (its own format or interface) (14% of 21 others)
- Which question types does it handle? a subset or a different set (10% of 21 others)
- Does it check whether its probabilities can be trusted? Pick the first that applies. it calibrates or sets thresholds against your own labelled examples (19% of 21 others)
- Are its answers typed values rather than generated text? (identity question) typed answers, but generated text is part of the pipeline (14% of 21 others)
- Does it publish head-to-head numbers against Jev? benchmarks, but not against Jev (19% of 21 others)
What it shares with most of the community
- How is the main thing licensed? permissive open source (MIT/Apache/BSD) (86% of 21 others)
- How is it mainly sustained? individual side project, no revenue (55% of 20 others)
- Do you need an account to use it? no account (86% of 21 others)
- Who is it for? developers (95% of 21 others)
- Which models answer its questions? Pick the first that applies. other models, not Jev (open, local, or LLMs) (52% of 21 others)
- Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.) it doesn't train models (68% of 19 others)
- Can you use it without a TypeSafe account? yes, no TypeSafe account involved (62% of 21 others)
Nearest neighbors
- OpenDecision 63% of 16 shared answers match
- snap 56% of 16 shared answers match
- CUA-S1 (Cua) 50% of 16 shared answers match
Every answer
| Question | Answer | Source |
|---|---|---|
| Is it actively maintained? | stands apart active, but changed direction (pivot, fork, or rename) Renamed repo and System 1 reframing after Jev's launch. | source 2026-10-25 |
| How is the main thing licensed? | permissive open source (MIT/Apache/BSD) MIT | source 2026-10-25 |
| How is it mainly sustained? | individual side project, no revenue Single author (Amit Rath), MIT, free; no paid tier. | source 2026-10-26 |
| Can it run entirely on your own device or infrastructure, without the maker's servers? | stands apart partly (some features need the maker's servers) Runtime is local CPU; compile step usually calls OpenAI or Anthropic. | source 2026-10-25 |
| Do you need an account to use it? | no account Local runtime and key-free demo; compile step uses your own LLM key or login, not a maker account. | source 2026-10-26 |
| Who is it for? | developers | source 2026-10-25 |
| Which shared standard or format does it mainly build on? | stands apart none of these (its own format or interface) Never mentions Jev or the System One format. | source 2026-10-26 |
| Which models answer its questions? Pick the first that applies. | other models, not Jev (open, local, or LLMs) Decision model is a pluggable slot; Jev is never named. | source 2026-10-25 |
| What is the main thing it ships? | a library, CLI, or SDK for calling models A compiler plus runtime library. | source 2026-10-25 |
| Which question types does it handle? | stands apart a subset or a different set Selection over a registry of actions, typed JSON. | source 2026-10-25 |
| Does it check whether its probabilities can be trusted? Pick the first that applies. | stands apart it calibrates or sets thresholds against your own labelled examples Temperature scaling plus split conformal prediction on a teacher-labelled sample and golden records. | source 2026-10-25 |
| Where do the decisions run by default? | on your own hardware (CPU, Mac, or GPU) | source 2026-10-25 |
| Does it train on Jev's outputs? (TypeSafe's customer agreement forbids using output to distill or build competing models.) | it doesn't train models Fits labels and calibration at compile time; does not use Jev. | source 2026-10-25 |
| Can you use it without a TypeSafe account? | yes, no TypeSafe account involved | source 2026-10-25 |
| Are its answers typed values rather than generated text? (identity question) | stands apart typed answers, but generated text is part of the pipeline An LLM generates the compiled code once. | source 2026-10-25 |
| Does it publish head-to-head numbers against Jev? | stands apart benchmarks, but not against Jev | source 2026-10-25 |
Sources
This page was derived from:
- GitHub · github.com/strot-ai/STROT-Compiler · read 2026-10-25
- Package registry · pypi.org/project/strot-ai/ · read 2026-10-25
RSS for this project · Its own release feed
Are you a maintainer? Claiming and correcting projects is coming soon.