35 projects
abhyasa
A tutor that asks you questions: active recall, a learner model and a concept graph in your vault
rupaka
Interactive SVG demos from JSON specs, made of small reusable blocks, that make the learner predict first
dhrona
train agents to choose and use the right tools
ramabana
rama's arrow. a harness that does not miss
rishi
fast local llm driver with tools
koshas
kosha (कोश) — a treasury of your repo and environment context for coding agents. FTS5 + vector search + call graph, no LLMs required.
kunda
the vessel that holds live kernels: which interpreter each burns in, and how many stay alight
shalya
the tools an agent is given, and the host that answers them
fossick
Web search, fetch, crawl, and browser automation for humans and agents
gheasy
github made easy
pobblebonk
the clock and the notebook for an agent: schedules, lists and notes on honker, in one file
adhara
Native FTS5 tokenizer and hybrid FTS + vector search for SQLite, as a loadable extension
ganapati
Sanskrit philology for a search index: metre, verse chunking, citations, lemmas and glosses
vishalakshi
one vault for everything you read: web, papers, video, files and code, searchable together and answerable by a local or hosted model
vruksha
a typed entity graph over a litesearch store: LLM extraction, priming, a guarded merge, and a search leg
litesearch
search through files with fts5, vectors and get reranked results. Fast
dockeasy
docker made easy
cfeasy
cloudflare made easy
vpseasy
create resources, deploy code in prod and dev. supports Hetzner, Lightsail and Multipass
dhrishti
a JSON API for live variable inspection & manipulation inside python runtimes
uraiyadal
the chat conventions every backend shares
varga
what kind of thing a document is, and the fields it holds: cue-scored doctypes and schema-constrained extraction
rahasya
thirty-four kinds of personal identifier, found by arithmetic: checksummed patterns read in context, no model and no network
laghu
model2vec static models in a fraction of the memory, with the same vectors
laghu-rs
The optional Rust core of laghu: normalization, pre-tokenization, Unigram Viterbi, WordPiece and mean pooling over mapped files
kavacha
run and package web apps as native desktop applications
pullup
build, release, and deploy projects
pdflite
PDF to markdown: layout repair, OCR fallback, and images on disk
lekhaka
Books of verses read into chapters: verse numbers mended, chapters assembled, akṣaras repaired. On vishalakshi.
vachaka
High-level Sanskrit recitation from text: Vāgdhenu chant and prose voices with line and word timings
paar
live lazy variable inspector for python
onneta
stateful helpers to onnxruntime-genai
sankalpa
intention to reality
fastops
End-to-end developer operations toolkit: Docker, VPS, DNS, Caddy, and CI/CD from Python
shipitpy
python project setup made easy
