Search: github.com/datasets | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

571.

GraphRAG is now on GitHub

2 years ago

282 points

572.

Show HN: Want something better than k-means? Try BanditPAM

github.com/motiwari

3 years ago

281 points

573.

Show HN: uFuzzy.js – A tiny, efficient fuzzy search that doesn't suck

github.com/leeoniya

4 years ago

251 points

574.

Show HN: Cedille, the largest French language model, released in open source

5 years ago

240 points

575.

Show HN: SQLite Plugin for Jekyll

github.com/captn3m0

2 years ago

227 points

576.

Show HN: Quadratic – Open-Source Spreadsheet with Python, AI (WASM and WebGL)

quadratichq.com

3 years ago

224 points

577.

Show HN: Data Formulator – AI-powered data visualization from Microsoft Research

github.com/microsoft

2 years ago

212 points

578.

Show HN: OSS AI agent that indexes and searches the Epstein files

epstein.trynia.ai

5 months ago

211 points

579.

Show HN: Qwen-2.5-32B is now the best open source OCR model

github.com/getomni-ai

a year ago

211 points

580.

Show HN: A modern way to type in African languages

github.com/pythonbrad

2 years ago

189 points

581.

Show HN: Data Painter – A Different Way to Interact with Your Data

docs.kanaries.net

3 years ago

179 points

582.

Show HN: Spice.ai – materialize, accelerate, and query SQL data from any source

github.com/spiceai

2 years ago

177 points

583.

Show HN: Invertornot.com – API to enhance your images in dark-mode

invertornot.com

2 years ago

175 points

584.

Show HN: OCR pipeline for ML training (tables, diagrams, math, multilingual)

github.com/ses4255

a year ago

170 points

585.

Show HN: Axilla – Open-source TypeScript framework for LLM apps

github.com/axilla-io

3 years ago

161 points

586.

Show HN: HelixDB – A graph database built on object storage

github.com/HelixDB

14 days ago

159 points

587.

Show HN: TabPFN v2 – A SOTA foundation model for small tabular data

a year ago

153 points

588.

Show HN: Autolabel, a Python library to label and enrich text data with LLMs

github.com/refuel-ai

3 years ago

153 points

589.

Show HN: Benchmarking VLMs vs. Traditional OCR

a year ago

146 points

590.

Show HN: Rudel – Claude Code Session Analytics

github.com/obsessiondb

3 months ago

144 points

591.

Show HN: Graphiti – LLM-Powered Temporal Knowledge Graphs

github.com/getzep

2 years ago

142 points

592.

Launch HN: UpTrain (YC W23) – Open-source performance monitoring for ML models

3 years ago

138 points

593.

Show HN: A benchmark for analytical databases (Snowflake, Druid, Redshift)

benchmark.clickhouse.com

4 years ago

137 points

594.

Show HN: Investorsexchange.jl – parse trade-level stock market data in Julia

github.com/lukemerrick

4 years ago

136 points

595.

Show HN: Plexe – ML Models from a Prompt

github.com/plexe-ai

a year ago

130 points

596.

Show HN: A tool to seed your dev database with real data

4 years ago

129 points

597.

Show HN: Data Diff – compare tables of any size across databases

4 years ago

127 points

598.

Show HN: Terminal-Bench-RL: Training long-horizon terminal agents with RL

github.com/Danau5tin

a year ago

125 points

599.

Show HN: Hydra - Open-Source Columnar Postgres

3 years ago

122 points

600.

Show HN: Ragas – Open-source library for evaluating RAG pipelines

github.com/explodinggradients

2 years ago

121 points