---
title: "Open Source"
description: "568 posts about Open Source, summarised, each linking to the original."
---

# Open Source
> 568 posts about Open Source, summarised, each linking to the original.

## Articles

### [Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers](https://yomu.fyi/post/multi-vector-late-interaction-embedding-models-with-sentence-transform.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Tom Aarsen, Antoine Chaffin, Raphael Sourty
- Published: Aug 18, 2026
- Type: Tutorial

Sentence Transformers v6.0 adds MultiVectorEncoder, bringing ColBERT-style late-interaction retrieval into the library’s existing API for dense, sparse, and reranker models. The encoder retains one projected, typically 128-dimensional vector per token instead of pooling a document into one vector, allowing documents to be encoded independently and indexed offline. At scoring time, MaxSim finds each query token’s highest dot-product match among document tokens and sums those maxima; contextual embeddings support both paraphrase matching and exact-token evidence. The guide covers checkpoint loading, encoding, scoring, semantic search, retrieval and reranking, indexing, token pooling, inference speed, evaluation, and retrieval from page images, audio, and video. It also quantifies the storage trade-off: 4,874 passages produced 608,414 token vectors and a 311.5 MB float32 index, while fast-plaid compression reduced that example to 92 MB.


### [Developing Nemotron 3.5 Lightning NVFP4 with QAD Using NVIDIA Model Optimizer](https://yomu.fyi/post/developing-nemotron-3-5-lightning-nvfp4-with-qad-using-nvidia-model-op.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Tanya Lenz
- Published: Aug 17, 2026
- Type: Tutorial

NVIDIA’s post presents a workflow for developing an NVFP4 checkpoint of the Nemotron 3.5 Lightning 30B-A3B model, targeting lower memory use and higher inference throughput without sacrificing accuracy. The method starts with post-training quantization (PTQ), producing a W4A16 student from the BF16 teacher, then applies quantization-aware distillation (QAD), where simulated quantization and KL-divergence loss align student logits with the frozen teacher. For the selected four\_over\_six recipe, 32K calibration performed best, and the recipe using W4A16 Mamba linears offered the best reported trade-off between accuracy degradation and inference performance; the checkpoint is 22 GB versus 66 GB and delivers up to 4x faster throughput. The workflow includes Model Optimizer examples and launchers for Megatron-LM and Megatron-Bridge, covering calibration, distillation, evaluation, and export.


### [Announcing support for ClickStack in the ClickHouse Terraform provider](https://yomu.fyi/post/announcing-support-for-clickstack-in-the-clickhouse-terraform-provider.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Aug 14, 2026
- Type: Announcement

The ClickHouse Terraform provider now supports managing ClickStack resources for both self-hosted deployments and ClickHouse Cloud. Dashboards, alerts, sources, saved searches, connections, and webhooks can be kept in version control, reviewed, and applied with the standard terraform plan and terraform apply workflow, helping keep configurations aligned across environments. ClickStack is implemented as a dedicated service module in the existing ClickHouse/clickhouse provider, using Cloud organization credentials plus a service ID for Managed ClickStack, or an endpoint and personal API access key for self-hosted deployments. The work also extends the API contract with named schemas, consistent integer fields, structured validation errors, and dashboard JSON validation during planning when the validation endpoint is available. Support is beta from provider version 3.25, with import and generated-configuration workflows for existing resources; if validation is unavailable, planning warns and validation is deferred to apply.


### [State of Open Models: Summer 2026 Observations](https://yomu.fyi/post/state-of-open-models-summer-2026-observations.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Adina Yakefu, Apolinário from multimodal AI art, Irene Solaiman
- Published: Aug 14, 2026
- Type: Benchmark

The report analyzes Hugging Face Hub activity from January through August 2026 to assess how open-model releases, usage, licensing, and agent traffic are changing. Public repositories expanded from 2.43 to 2.96 million models, while 85.6% of models had fewer than 200 lifetime downloads and 1.5% of repositories captured 99.2% of downloads. Chinese labs reached monthly ceilings of 754B to 2.78T parameters, while broader portfolios such as Qwen’s generated far more downloads than frontier-only strategies; likes and downloads measured attention and infrastructure dependence differently. Large Chinese releases were often Apache 2.0 or MIT licensed, though newer trillion-parameter models introduced restrictions, while agents became the Hub’s leading user and autonomous-agent activity exposed the practical value of running quantized open models locally.


### [Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets](https://yomu.fyi/post/record-train-and-deploy-from-one-place-with-strands-agents-lerobot-and.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Sundar Raghavan, Steven Palma, Cagatay Cali, Arron Bailiss, Yin Song
- Published: Aug 13, 2026
- Type: Tutorial

This walkthrough presents a streaming data loop for Strands Robots that records robot demonstrations, stores them in Hugging Face Storage Buckets, trains from the growing dataset, and deploys a resulting policy back to hardware. It uses the LeRobot on-disk format throughout: Robot("so100") records through DatasetRecorder, sync\_dataset\_to\_bucket writes changed bytes to a mutable bucket, and stream\_dataset reads the dataset from the Hub without a full local download while decoding camera video on the fly. The agent can decide which episodes to keep and when to retrain, while the same Robot object records and streams data; deployment changes the robot mode keyword from simulation to real. The default simulation path runs with a mock policy that produces a valid dataset but not a useful one, while hardware, bucket, and training paths require additional dependencies.


### [What’s new in the ClickHouse Grafana plugin](https://yomu.fyi/post/what-s-new-in-the-clickhouse-grafana-plugin.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Aug 13, 2026
- Type: Announcement

ClickHouse’s Grafana plugin has shipped a set of changes aimed at making common observability tasks—finding log lines, narrowing to services, and detecting deployments—faster without requiring SQL. Version 4.20 adds single-table configuration and compact query mode, where users search logs, apply type-aware filters, review query history, and see or edit generated ClickHouse SQL. Investigation can proceed by clicking through collapsible OpenTelemetry Resource, Scope, and Log attributes, filtering values or selected message text, while dashboards can discover Map keys and values across tables. The release also includes interactive Logs Explorer, Traces Explorer, and per-service OpenTelemetry dashboards, plus guided variable and annotation editors that generate editable SQL for distinct values and change markers such as deployments and rollbacks. Additional changes cover schema-introspection caching, trace-ID lookup, Grafana 13 compatibility, SQL validation, backend OpenTelemetry instrumentation, and forwarding Grafana identity to ClickHouse; compact mode initially remains limited to single-table data sources.


### [Introducing Credentio: Open Source C++ Library for C2PA Content Credentials from Google](https://yomu.fyi/post/introducing-credentio-open-source-c-library-for-c2pa-content-credentia.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Sherif Hanna
- Published: Aug 13, 2026
- Type: Announcement

Google introduces Credentio, an open-source C++ library for local validation of C2PA Content Credentials, initially supporting specification versions 2.2 and 2.4. The library is the code used by nearly 40 conformant C2PA-enabled Google products to process tens of billions of generated images, videos, audio files, and documents across many formats. Its API keeps validation inside the developer’s application, avoiding media transmission while providing immediate verdicts, privacy, and zero bandwidth overhead; it is also designed to maintain a small memory footprint for assets ranging from images to multi-gigabyte videos. Credentio parses manifests, assertions, digital signatures, and claims, accepts official or custom trust lists, and reports verification statuses and integrity errors, while planned work includes generating and embedding Content Credentials.


### [What We Learned by Reproducing 2,200 papers from ICML](https://yomu.fyi/post/what-we-learned-by-reproducing-2-200-papers-from-icml.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Abubakar Abid
- Published: Aug 13, 2026
- Type: Benchmark

An ICML 2026 reproduction hackathon examined whether coding agents could audit research at conference scale, amid 23,918 submissions and 6,352 accepted papers. From July 15 to August 2, 1,221 participants published 6,816 Trackio logbooks covering 2,226 papers and 35,908 claims; an open-weights GLM-5.2 judge assigned per-claim verdicts, while participants used cloud jobs and toy reproductions when full experiments were impossible. At least one claim was independently verified in 51% of examined papers, including 266 fully reproduced papers, while 23% had a falsified or contested claim and 242 papers produced opposing verdicts across teams. Adversarial re-checks confirmed issues including a paging-theorem error, a reverse-versus-forward-KL mismatch, and padded evaluation tokens, but also caught false falsifications, leading to the conclusion that agents expand auditing capacity while humans remain necessary to steer experiments and assess cases such as image quality.


### [Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis](https://yomu.fyi/post/introducing-olmoearth-embeddings-custom-embedding-exports-from-olmoear.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Kyle Wiggers
- Published: Aug 12, 2026
- Type: Announcement

OlmoEarth Studio now supports custom computation and export of embedding vectors, compact representations of Earth-observation data generated by open-source OlmoEarth foundation models. Users can select an area, a one-to-twelve-month time span, an encoder variant, spatial resolution, and Sentinel-2 L2A or Sentinel-1 RTC imagery, then receive a Cloud-Optimized GeoTIFF with one int8 band per embedding dimension. The post demonstrates similarity search, few-shot segmentation, change detection, and PCA-based exploration; a logistic regression trained on 60 labeled pixels produced a weighted F1 of 0.84 for three land-cover classes in Ca Mau, Vietnam. Embeddings provide a fast, shareable starting point, while supervised fine-tuning can improve performance for applications needing task-specific results; cloud cover, atmospheric artifacts, and missing observations can affect quality.


### [Taking AUTO CDC to the next level: Solving the hardest real-world use cases](https://yomu.fyi/post/taking-auto-cdc-to-the-next-level-solving-the-hardest-real-world-use-c.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Josh Seidel, Shanelle Roman, Sudhanva Huruli
- Published: Aug 11, 2026
- Type: Announcement

The post describes new AUTO CDC capabilities for challenges that standard CDC patterns do not fully address, including out-of-order bitemporal timelines, partial updates, and durable audit history. Bitemporal AUTO CDC tracks business and system time independently through four managed interval columns, rewriting affected history when corrections arrive out of order so either point-in-time view can be reconstructed. Partial Updates are generally available and treat selected incoming NULL values as "do not update," preventing unchanged fields from overwriting stored values. The post also describes logging business and system timestamps in MLflow for reproducibility after VACUUM, and notes that the Python API for AUTO CDC Type 1 is being contributed to Apache Spark 4.2, with a SQL interface already merged for a next release.


### [Scaling patterns for self-organizing multi-agent clusters with Kiro](https://yomu.fyi/post/scaling-patterns-for-self-organizing-multi-agent-clusters-with-kiro.md)
- Company: [AWS](https://yomu.fyi/company/aws.md)
- Author: Ivo Kammerath
- Published: Aug 11, 2026
- Type: Explainer

Traditional multi-agent architectures rely on a central supervisor agent to decompose tasks and aggregate results, creating single points of failure and context-window throughput bottlenecks. To address these scaling limits on decomposable workloads, kiro-flock implements self-organizing clusters of headless Kiro CLI agents on Amazon EC2 coordinated entirely through shared Amazon S3 state. Agents operate in bounded peer topologies such as logical rings, reading neighbor append-only logs and generating artifacts without direct inter-agent messaging or central brokers. Each agent starts fresh per iteration without conversational memory, reading current direction and peer logs to prevent drift and preserve steering control. This shared-state pattern enables resilient parallelism for tasks requiring diverse independent contributions, such as code reviews or codebase migrations.


### [NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents](https://yomu.fyi/post/nvidia-nemotron-3-5-lightning-delivers-fast-accurate-specialized-task.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Tanya Lenz
- Published: Aug 11, 2026
- Type: Announcement

NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts model with 3B active parameters, designed for the high-volume execution layer of long-running autonomous agents. The post positions it alongside frontier reasoning models: larger systems handle planning and orchestration, while Lightning handles tool calls, result validation, subagent delegation, and other routine work. Its design combines harness-optimized training, multi-token prediction for speculative decoding, DFlash and DSpark draft models, and NVFP4 quantization alongside BF16. The model is customizable through LoRA or full SFT, reinforcement learning, and environment-based evaluations, with weights, training data, and recipes released under OpenMDW-1.1. The post reports up to 4x the output speed of similar-sized models, 86% accuracy on PinchBench, and completion of 10,000 tasks 30% faster than Qwen3.6 35B at similar accuracy, while NeMo Switchyard routes work among models.


### [Route AI Agent Workloads Across Models with NVIDIA NeMo Switchyard](https://yomu.fyi/post/route-ai-agent-workloads-across-models-with-nvidia-nemo-switchyard.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Aug 11, 2026
- Type: Explainer

NVIDIA NeMo Switchyard addresses the problem of routing AI-agent work across models with different capabilities, costs, latency, and verbosity profiles rather than sending every request to one model. At runtime, its router evaluates a request, context, policies, and system signals, then directs work to a configured model pool, potentially routing individual agent steps and carrying session state when needed. The provider-agnostic switchyard-libsy SDK separates semantic model targets from provider endpoints, while a reference server accepts OpenAI, Anthropic, and Responses API requests and records routing decisions and outcomes. Available approaches include tuning-free LLM classifier, stage, and escalation routers, alongside tunable and custom algorithms. In a LangChain evaluation, escalation routing cut cost 74% versus a frontier-only baseline with a measured six-point accuracy trade-off, while Cognition’s staged routing reported near-frontier coding performance at approximately 28% lower mean cost.


### [bitdrift brings ClickHouse-powered mobile observability to ClickStack](https://yomu.fyi/post/bitdrift-brings-clickhouse-powered-mobile-observability-to-clickstack.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Aug 11, 2026
- Type: Announcement

bitdrift has joined ClickHouse’s House Mates program as a mobile observability partner, bringing mobile-native telemetry, tracing, and debugging to ClickStack. ClickStack provides an open-source or managed observability stack built on ClickHouse, with HyperDX and an OpenTelemetry Collector for logs, metrics, traces, and OTLP ingestion. bitdrift’s Capture SDK supports iOS, Android, and React Native, stores unsampled telemetry in a fixed-size on-device ring buffer, and uses control-plane configuration to decide what is collected or uploaded. Shared OpenTelemetry trace context lets engineers follow a mobile request’s trace ID from a session timeline into ClickStack, where backend traces, dependencies, logs, metrics, database operations, and infrastructure behavior are available, creating a continuous debugging path across the device and distributed systems.


### [Whats new in ClickStack - June + July](https://yomu.fyi/post/whats-new-in-clickstack-june-july.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Aug 10, 2026
- Type: Announcement

ClickStack’s June–July releases add a broader set of observability features, with work centered on trace navigation, metrics sources, dashboards, and filter performance. The trace waterfall now assigns stable colors by service, keeps span durations outside bars, preserves clickable proportions for very short spans, and adds a minimap plus OpenTelemetry span-link navigation. Metrics support includes quantiles for exponential histograms, a leaner default schema, and an experimental UI connection to external Prometheus-compatible endpoints, while PromQL is proxied to the configured endpoint. Dashboard filters can narrow one another, event patterns can appear as tiles, kiosk mode provides a read-only display, and filter-value discovery prefers ClickHouse text indexes when available. Additional changes cover alert annotations, browser RUM dashboard views, external links from table tiles, grid snapping, and service-map coloring by latency, error rate, or throughput.


### [Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS](https://yomu.fyi/post/build-low-latency-multilingual-voice-agents-open-weights-full-deployme.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Maryam Motamedi, Mikyas Desta, Jason Li, Jason Roche
- Published: Aug 10, 2026
- Type: Announcement

NVIDIA Magpie Multilingual TTS is a 364M-parameter open-weights model for multilingual voice applications, supporting 12 languages, including newly added Modern Standard Arabic, Korean, and Brazilian Portuguese. It is positioned for cascaded voice-agent architectures in which ASR, TTS, and LLM components are independently deployed, tuned, and scaled on controlled infrastructure. Frame stacking predicts two audio frames per decoding step, while a local transformer models dependencies between simultaneously generated codebook tokens; NVIDIA reports 32–79 ms single-stream TTFA across its listed GPUs. Compared with the previous release, French and Spanish CER improved to 1.54% and 0.60%, while SSIM reached 0.747 and 0.793; German SSIM also increased to 0.742. The Hugging Face checkpoint supports research and fine-tuning, while NVIDIA NIM provides optimized production serving and NeMo supports customization.


### [Introducing FILE type: a native column type for multimodal data](https://yomu.fyi/post/introducing-file-type-a-native-column-type-for-multimodal-data.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Michael Armbrust, Burak Yavuz, Dejan Krakovic, John Spencer
- Published: Aug 10, 2026
- Type: Announcement

The beta of FILE introduces a native column type for storing unstructured data such as documents, images, audio, and video alongside structured table data. FILE applies fine-grained governance, row- and column-level controls, ABAC, and lifecycle synchronization, so deleting a row also deletes the corresponding binary in object storage. Its lightweight pointers fetch file content only when a query requires it, while SQL, Python UDFs, built-in AI functions, and materialized views support multimodal processing. The example uses sampled dashcam frames and object detection to identify stops with no hazard, then joins extracted results with trip metadata; the announcement also describes connectors, incremental pipelines, and an open effort around Parquet, Delta Lake, Apache Iceberg, and Apache Spark.


### [Run Local Agentic AI Workflows with Meta’s Muse Glimmer on NVIDIA](https://yomu.fyi/post/run-local-agentic-ai-workflows-with-meta-s-muse-glimmer-on-nvidia.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Aug 10, 2026
- Type: Announcement

Meta has released Muse Glimmer, a 30B open-weight dense model with a 120K+ context window aimed at local agentic AI workflows. The model uses a dense architecture that activates every parameter per token, avoiding routing overhead and targeting reliable instruction following, long-context coherence, and predictable latency for multi-step agent tasks. On NVIDIA Blackwell Ultra hardware, Muse Glimmer reports over 20K tokens/sec/GPU at BF16/NVF4 precision, with the full model fitting in a single GPU's VRAM. Deployment options span NVIDIA GeForce RTX 5090, DGX Spark, DGX Station, and Jetson edge devices, supported by vLLM, SGLang, and NVIDIA NIM containers. Fine-tuning is available through NVIDIA NeMo AutoModel for SFT and LoRA, with NeMo RL for reinforcement learning, and the NemoClaw harness enables long-running assistants in a sandboxed environment.


### [Making Knowledge Distillation Cheap Enough to Run at Scale](https://yomu.fyi/post/making-knowledge-distillation-cheap-enough-to-run-at-scale.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Antonio Tiene, Iker García-Ferrero, Ali Hashemi, Bakbergen Ryskulov
- Published: Aug 10, 2026
- Type: Problem & solution

Knowledge distillation trains a smaller student to match a larger teacher's capabilities, but conventional online training keeps both models loaded and materializes full vocabulary distributions at every step, making long-context recovery expensive. The proposed system caches the teacher's top-100 logits once and introduces a fused, chunked KL-divergence loss that avoids storing the full vocabulary-by-sequence grid or the student's full logits. In benchmarks with an 8K-token context on one H200, offline fused chunked KL used 58.3GB peak memory versus 102.8GB for online training, while all four methods reached near-identical training loss. At 32K tokens, the fully chunked loss reduced isolated kernel memory from 85.2 GiB to 5.45 GiB; distilling GPT-OSS 20B at that context cut step time from 57.0 to 12.23 seconds and reduced the setup from four GPU nodes to one.


### [Announcing Cloudflare Ambassadors, Community Engineers, and another $1M in open-source funding](https://yomu.fyi/post/announcing-cloudflare-ambassadors-community-engineers-and-another-1m-i.md)
- Company: [Cloudflare](https://yomu.fyi/company/cloudflare.md)
- Author: Kristian Freeman
- Published: Aug 7, 2026
- Type: Announcement

Cloudflare introduced an updated community initiative featuring two tracks: Cloudflare Ambassadors and Cloudflare Community Engineers. The Ambassador program selects community leaders for terms lasting up to two years to organize events, lead student groups, and create learning spaces with company-provided credits, resources, and marketing assets. The Community Engineer track offers grants from a new one million dollar open-source fund spanning the next two years to support maintainers of projects such as Astro, Agents SDK, EmDash, Hono, and Vinext. To maintain its Discord server of nearly 100,000 members, a new Discord committee composed of staff and Ambassadors will guide community discussions while automated spam protections handle routine moderation.


[Newer posts](https://yomu.fyi/topic/open-source/page/4.md) · [Older posts](https://yomu.fyi/topic/open-source/page/6.md)