index / lucasmartins-ai/lcc
lcc
Local Context Compiler (lcc): clean, dedupe and compact prompt context before it reaches the model, then report every block dropped, the cache tokens a pass invalidates and when pruning pays off. Runs offline with a local 1K decision model. MIT, no API key, zero telemetry.
Agent and Dev Tooling?UnclearReviewPython
Repository
Stars9
LanguagePython
LicenseMIT
Created2026-06-19
Last pushed2026-10-03
Officialno
Judgment
Genuine Jev project0.48
gate 0.5
Uses Jev at runtime0.18
Is a meta list0.05
Is a reimplementation0.14
Quality scales
Substance2.81 / 3
gate 0.5
Docs2.76 / 3
Novelty1.75 / 3
Composite score0.86
Category distribution
Jev's confidence in this category is below 0.5, so the category is shown with a question mark. It is not a listing condition: this entry's status was decided by genuine and substance alone.
Agent and Dev Tooling0.41
Other0.37
Applications0.12
SDKs and Clients0.07
Research and Evals0.03
Learning0.00
Integrations0.00
Games and Simulation0.00
Assigned categoryAgent and Dev Tooling (uncertain)
Category probability0.41
Category confidence0.32
PatternUnclear
Pattern confidence0.39
Curation
StatusReview
Reasongenuine 0.48 below 0.5
README pickno
Overridenone
Sources
- search:topic:jev
- search:topic:typesafe-ai
- search:topic:jev-ai
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-10-04 11:47 UTC