Agent Native·1d agoLocal Inference Engine That Makes Agents Faster on MacLocal models have improved enough to handle useful development work.
Agent Native·2d agoYour Agent Knows SQL But Doesn’t Understand Your DataLLMs keep getting better at writing SQL, but enterprise databases are still full of ambiguous business language.
Agent Native·4d agoOpen-Source Jev on Apple Silicon and CUDAThe hardest part of production is making thousands of simple decisions reliably.
Agent Native·5d agoUnlock 2x Tensor Throughput on NVIDIA RTX GPUsRTX 3090 delivers about 75 TFLOPS on a BF16 matrix multiplication benchmark.A response icon1A response icon1
Agent Native·6d agoUnderstand Any Codebase Instantly (with up to 99.7% fewer tokens)In this article, we will turn a repository into a queryable graph, which will provide you 30 to 99.7% fewer tokens on the development…A response icon1A response icon1
Agent Native·Nov 66 Open-Source Projects for Serious AI InfrastructureIf you are building agents that need to run somewhere other than a notebook, these six open-source projects are worth knowing.A response icon1A response icon1
Agent Native·Nov 5Context Engineering Is Dead. Long Live Cache Engineering.What happens when we give the agent direct control over its active KV cache?A response icon1A response icon1
Agent Native·Nov 4Claude Bug HunterTo guard against cyber attacks, you have to package security methodologies, patterns from disclosed reports, tool integrations, and…A response icon1A response icon1
Agent Native·Nov 3Pure C inference engine to run MoE models (2.8T) on consumer hardware744-billion-parameter model on a laptop with 25 GB of RAM sounds absurd. The quantized checkpoint alone takes up hundreds of gigabytes.
Agent Native·Nov 2Unified Interface for Agent HarnessesEverybody can connect an LLM to their backend in an afternoon but running a coding agent as a reliable product feature takes a lot longer.
