Alternatives
Products that do what 98% Accuracy | KnoDL does
Turn fractured data into clean knowledge — in real time
- 1
- 2KO
We've open-sourced Klarity - a tool for analyzing uncertainty and decision-making in LLM token generation. It provides structured insights into how models choose tokens and where they show uncertainty. What Klarity does: - Real-time analysis of model uncertainty during generation - Dual analysis combining log probabilities and semantic understanding - Structured JSON output with actionable insights - Fully self-hostable with customizable analysis models The tool works by analyzing each step of text generation and returns a structured JSON: - uncertainty_points: array of {step, entropy,…
2025 · github.com
- 3
- 4AK
I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet. It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you. The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard. I…
Apr 2026 · github.com
- 5
- 6AB
I created a web page to compare different analytical databases (both self-managed and services, open-source and proprietary) on a realistic dataset. It contains 20+ databases, each with installation and data loading scripts. And they can be compared to each other on a set of 43 queries, by data load time or by storage size. There are switches to select different types of databases for comparison - for example, only MySQL compatible or PostgreSQL compatible. If you play with the switches, many interesting details will be uncovered. Full description:…
2022 · benchmark.clickhouse.com
- 7AS
This little project came about because I kept running into the same problem: cleanly differentiating sensor data before doing analysis. There are a ton of ways to solve this problem, I've always personally been a fan of using kalman filters for the job as its easy to get the double whammy of resampling/upsampling to a fixed consistent rate and also smoothing/outlier rejection. I wrote a little numpy only bayesian filtering/smoothing library recently (https://github.com/hugohadfield/bayesfilter/) so this felt like a fun and very useful first thing to…
2024 · github.com
- 8
- 9OS
Hi HN! I’m Farah, co-founder of Dioptra.ai. We just open sourced katiML (https://github.com/dioptra-ai/katiml) this week and wanted to get your take. katiML is a vector+data lake to debug, curate and version AI data. With katiML, teams avoid the “garbage in, garbage out” effect by taking control over the quality of their data. They quickly and effectively curate high quality data for training, fine-tuning, and fixing hallucinations and edge cases. Features include: - Data Curation: interactive embedding visualization and similarity search, mislabeling and hallucination…
2023 · loom.com
- 10
- 11OO
Hi! One of the creators here. Very proud to finally be able to show you what we've been working on for over a year now. Curious to hear your thoughts! Objectiv is open-source (APLv2) product analytics infrastructure. It's built around a generic but strict event taxonomy, open/common data- and infra tools (currently PG, snowplow, working on bigquery with more to come), and the analyses are done using our pandas-like, SQL speaking modeling library called Bach. As a result, we’re moving towards a vision wherein models can be shared openly, independent of product, platform[1] or data…
2022 · objectiv.io
- 12
- 13KE
2015 · github.com
- 14AN
Kimi K3 has 2.78 trillion parameters and ships as 1.42 TB of weights. It clearly does not fit in the memory of a laptop. But K3 is a Mixture-of-Experts model. For each token, only a small fraction of its 896 experts per layer is activated. That changes the problem: the entire model does not need to be resident in RAM, as long as the weights required by each token can be reached quickly enough. We built WASTE — the Weight-Aware Streaming Tensor Engine — to explore that idea. WASTE keeps the dense, repeatedly used part of the model resident in memory, stores the routed experts in an…
Jul 2026
- 15GR
2015 · github.com
- 16RD
Jun 2026 · rep-detect.lambda-combine.net
- 17
High performance storage engine for efficient LLM inference and GPU Training.
1d ago · theopenlake.com
- 18
Free synthetic bank statements for testing parser accuracy
Mar 2026 · bankstatemently.com
- 19
Not just nodes and edges, it reasons about the connections.
Jul 2026 · github.com
- 20
- 21IT
2023 · github.com
- 22PA
Feb 2026 · archilyse.standfest.science
- 23AB
2015 · j-vdh.blogspot.com
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →