A focused feed of models, agents, research and open-source releases for people building with AI.
Exa launched Monitors v2 , a scheduled search product that pushes webhooks only when something new appears. Price cut over 7x to $2 per 1,000 runs, down from $15, with no code changes required for existing users.
Next-gen Meta Andromeda hits 1B+ ads/sec per server, a 100x jump over 2024. Retrieval MoE architecture reaches ranking-level quality at ~300x fewer inference FLOPs. Fused GPU kernel keeps tensors in registers and shared memory, hitting ~85% of peak HBM bandwidth.
BKAI's vietnamese-bi-encoder hits 824K+ downloads as a go-to Vietnamese embedding model Built on PhoBERT-base-v2, outputs 768-dim embeddings, ~0.1B parameters, Apache-2.0 licensed Trained on translated MS MARCO, SQuAD v2, and 80% of Zalo 2021 Legal Retrieval challenge Scores 73.28 Acc@1 and 80.73
RustXNG is a Rust rewrite of SearXNG targeted at local AI agent grounding and RAG. Ships as a single binary with no Python or database dependencies, launched via Cargo or Docker. Benchmarks show 0.03s startup vs 0.72s, 13 MiB vs 118 MiB RAM, and 0.27s for 169-engine queries.
Penn and Microsoft Research propose attribution gradients , replacing citation numbers with unfoldable evidence trails. Five layers: claim decomposition, evidence overview bars, color-coded excerpts, in-source PDF viewer, and second-degree citation unraveling.
Parallel launched Parallel for Finance , a universal index upgrade applied across all its APIs with no new subscription. On FinSearchComp T3, Parallel Advanced hits 57.4% accuracy at up to 2x lower cost than Exa and Perplexity.
Exa added 3.2 million podcast episodes with full transcripts to its search API, letting agents query 2.2 million hours of audio for free.
Qdrant's ONNX port of multilingual-e5-large hits 926K downloads, giving teams a lightweight way to run a top multilingual embedder in production.
NVIDIA released Auto Ontology, an open-source Python framework that builds semantic graph layers over enterprise data so agents generate SQL deterministically with provenance.
DeepVK's new Russian sentence encoder packs 8,192-token context and Matryoshka embeddings into a 149M-parameter model that rivals systems 4x its size.
Mem0 leads on GPT-4o-mini. Pi with Claude Opus 5.5 scores 99% for $6.95, against 95% at $17.84 for full context
Sarvam's knowledge fabric restructures enterprise documents into a navigable tree and typed ontology, lifting agent accuracy to 84.2% while slashing costs.
DecisionRAG replaces vector search with an LLM that judges candidates in parallel, beating dense retrieval plus an 8B reranker on multiple benchmarks.
LlamaIndex's new 4B vision-language model tops ParseBench by 12 points and parses a typical page in 0.2 seconds, available now on OpenDocRouter.
Replit is acquiring the vector database maker to build what both companies call the context layer for autonomous enterprise agents.
Ai2 released OlmoEarth v1.3 with precomputed global satellite embeddings at 10m resolution and a browser tool that trains classifiers without a GPU.
A new multilingual benchmark exposes how embedding models and LLMs fail at fact-checking across 10 African languages, and shows what fixes work.
Keenable's search API paired with GPT-5.6 Sol takes the top spot on the Vals Web Search Index at 49.1%, leading finance research.
Cohere's new reranker tops public benchmarks and introduces passage-level Context Focus, cutting LLM token spend by up to 41% with minimal quality loss.
Google's new 740M multimodal embedding model runs locally across text, images, and audio, powering a Mac meeting companion and mobile search demos.
Sakana AI's QD-Rec applies Quality-Diversity evolutionary search to LLM-powered recommendations, growing archives of varied, well-justified picks instead of ranked lists.
A new framework retrieves full scientific papers by decomposing them into aspect-specific queries and iteratively expanding the search as a tree.
Exa 3.0 claims the top spot on eight search benchmarks and introduces a cheaper Lite tier at $4 per 1,000 requests.
A new training recipe called Active Indexing teaches LLMs to cite the documents they learned from, no retriever required at inference time.
No stories match these filters.
