First Person Labs emerged from stealth on Tuesday after raising around $10 million in a round led by Andreessen Horowitz’s infrastructure team. The startup is developing personal “user models.” Andreessen Horowitz says its product Second builds a continuously updated model of the user that can provide context to selected agents. It also says Second runs in the background on the user’s device by default and keeps the personal model inspectable and portable.
What problem it solves
Home networks built on OpenWrt/GL.iNet routers are spread across many devices, and there is no single place to see fleet status, per-router health, connected devices, WireGuard peers, AdGuard Home statistics or alerts as they happen. Operators also need topology and health scoring without handing their network state to a third-party cloud service. NetPulse addresses this by …
What problem it solves
Personal and team knowledge is distributed across notes, conversations, trackers, and research, making it difficult to capture, organize, verify, and synthesize useful information. COG provides a markdown-based workflow in which agents can maintain a shared knowledge base, support recurring research and operational tasks, and verify selected work through independent checks.
…
What problem it solves
AI and machine learning workflows require vector search, fast random access, multimodal data storage, data evolution, and hybrid search combining vectors, full-text, and SQL predicates. Lance brings these capabilities directly into the lakehouse format.
Key features
Expressive hybrid search — Combine vector similarity search, full-text search with BM25, and SQL analytics on …
What problem it solves
Many AI applications send messages to remote servers, where they may be logged and analyzed outside the user's view. This project addresses that concern by running language models, conversations, voices, and tools on the device without requiring an account or internet connection.
Key features
On-device language model chat — Run GGUF language models fully offline, including G…
What problem it solves
Home Assistant users need a way to integrate compatible Samsung appliances without relying on a cloud account for routine control and monitoring. Local communication can also support fast state updates and continued operation without internet access after setup.
Key features
Broad appliance support — LocalThings connects Home Assistant with Samsung washers, dryers, refrigera…
What problem it solves
Coding agents commonly pause for human approval before risky steps, which makes unattended repository work difficult to run in CI, daemons, and scheduled jobs. Teams also need consistent policies, tools, and supervision across different execution environments without maintaining separate framework integrations.
Key features
Repository tooling through MCP — Give an LLM tools …
What problem it solves
Applications need a general-purpose way to compress data losslessly while supporting standard command-line, package-manager, and source-build installation paths. The compressed format must also have a precisely defined specification, while stream consumers need to understand that the format carries no checksums or uncompressed length.
Key features
Lossless compression — Brot…
What problem it solves
Running the Kimi K3 model normally presents a storage and memory barrier because its checkpoint is very large. This project provides a portable C99 inference engine that streams model data so the complete model can run on a CPU without requiring GPU infrastructure or a deep-learning framework.
Key features
Portable C99 inference — The engine is implemented in portable C99 an…
What problem it solves
Turning a video idea into a finished production normally requires coordinating research, scripting, asset generation, editing, composition, and review. AI coding assistants need a structured, agent-driven workflow that supports both generated visuals and real footage while keeping creative decisions reviewable.
Key features
Structured production pipelines — Pipeline workflow…