The Builder

A 13B LLM trained exclusively on texts from before 1931

“The ability to test code-learning from scratch on a model that's never seen a modern codebase is genuinely useful for ML research. The methodology here is cleaner than anything I've seen for studying data contamination.”

A 13B LLM trained only on pre-1931 text — by design

“This is one of the most scientifically interesting model releases I've seen. A clean pre-1931 cutoff gives researchers a genuinely controlled environment for studying generalization, data contamination, and in-context learning — problems that plague every other benchmark we have.”

Human pose estimation and vital signs via WiFi — zero cameras needed

“The $9 hardware cost is the headline — prior WiFi sensing research required expensive SDR hardware or proprietary routers. ESP32-S3 + online STDP learning that adapts to new rooms in 30 seconds is a practically deployable combination. For smart home, eldercare, or building automation use cases this opens a category that was previously research-only.”

Real-time global intelligence dashboard with 45 data layers and local AI analysis

“The feed aggregation architecture is solid — 500+ sources with deduplication and geolocation, all queryable via a local API. I've already written a Python script to pull conflict alerts into my own alerting system. The Ollama integration is clean, and the AGPL license doesn't matter for personal use. This took one developer a few months to build what enterprise tools charge $50K/year for.”

Single-GPU PyTorch reproductions of two KV-cache compaction research papers

“KV-cache memory is the wall that stops long-context models from running locally. A clean single-GPU reproduction of two compaction approaches in one repo is exactly what the community needs to evaluate tradeoffs without re-implementing from scratch. The self-study condensation approach in Cartridges could be a game-changer for local inference.”

Answer geospatial questions in minutes — satellite data, flooding, sites at scale

“GIS has always been a specialist skill tax on otherwise capable teams. If PangeAI delivers on the 'flooding at 400 sites in minutes' promise, it's genuinely unlocking analysis that would have taken weeks and a specialized hire. The API integration question is the next thing I'd want to know about.”

Open-source PyTorch reconstruction of Claude Mythos — 770M matches 1.3B performance

“A 770M model that matches 1.3B performance is meaningfully useful for edge deployment and local inference. Even if the efficiency claims hold up at only 80%, this is worth benchmarking against your specific tasks before committing to cloud API spend.”

153 real-world browser tasks, live websites — best AI agent scores only 33%

“The five-layer recording (replays, HTTP traffic, reasoning traces) is the right approach for actual debugging — finally a benchmark where failure analysis is tractable. The 33% score also sets honest expectations for teams planning to ship production browser agents right now.”

AI research agent that remembers every trade thesis you've built

“LangAlpha solves the two worst parts of AI financial research: context rot between sessions and raw data flooding your LLM context window. The persistent workspaces with agent.md memory files and programmatic tool calling (writing Python to process data locally before injecting it) are genuinely novel approaches. 23 pre-built skills for DCF modeling, comp analysis, and earnings analysis means you're not starting from scratch. If you work in finance and write code, this is immediately useful.”

MedChem copilot that blocks toxic molecular modifications before you make them

“The regulatory audit trail feature alone makes this worth evaluating for any pharma team using AI. The FDA is going to want documentation on AI-assisted design decisions, and ORAC-NT is the only open-source tool I've seen that generates that output by design rather than as an afterthought.”

Standardized framework for building world models with perception and memory

“Standardized world model infrastructure is desperately needed. Right now every robotics and simulation project reinvents its own state representation layer. A well-designed shared library here could shave months off development cycles and make research actually reproducible.”