-
UC Berkeley
- in/kunalbaldava
Stars
A library for efficient similarity search and clustering of dense vectors.
The Steerability toolkit is an extensible library for general purpose steering of language models.
RL environments + evals for AI agents. Define once, train anything.
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
Visual analysis and diagnostic tools to facilitate machine learning model selection.
🎥 Make videos programmatically with React
Open-source ThreeUI Community catalog with live interactive components and complete Community source.
Mockingbird is a mock streaming data generator
Turn a goal into a supervised run.
Harness for running and evaluating AI agents against RL environments
Paperweight scans your inbox to map your digital footprint, then helps you take back control and delete your data. Local-first and open source.
A skill file for removing AI tells from prose
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Privacy-first AI meeting note taker for Windows, macOS and Linux. Free, open source (MIT). On-device Whisper/Parakeet transcription and speaker diarization, no meeting bot. Open-source alternative …
Free, open-source data broker removal tool. Send GDPR/CCPA removal requests to 750+ data brokers automatically.
HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382
[NeurIPS 2026] An ultra long-horizon SWE benchmark
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori…
A fully-searchable and accessible archive of court data including growing repositories of opinions, oral arguments, judges, judicial financial records, and federal filings.
Download market data from Yahoo! Finance's API
A collection of resources that investigate social agents.
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
This 10-week training program is designed to prepare incoming pre-doctoral research fellows at the Princeton Empirical Studies of Conflict (ESOC) lab with the skills needed to support faculty resea…
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
A list of awesome resources for Computational Social Science