Fetching from the wire…
Markets2026-09-15 · source-backed
dbt Charts released under Apache 2.0 on September 14: declarative YAML and SQL for dashboards, 16 chart types, over 1,100 config options, and a dct CLI rendering to SVG, HTML, PNG and PDF locally (dbt Charts). Charts reference dbt models through ref() and support Jinja, with Semantic Layer integration planned. The framing is explicit: extract the charting layer out of BI tools so the dashboard is a text artifact an agent can author and diff, rather than GUI state an agent can't reach.
Each link below shares sources, entities, or timing with this story.
NVD, September 4. DocsGPT 0.15.0 and below runs its custom-prompt feature through Jinja with no sanitization or sandbox, so template injection escalates to full code execution with no auth. Any "bring your own system prompt" feature that formats prompts with a real template en...
guillaumemeyer/watermarks-remover appeared August 11 and hit 634 stars and 61 forks in 24 hours, targeting provenance marks from Anthropic, Google's SynthID-Text, OpenAI, and Kirchenbauer-style implementations across three layers: invisible Unicode hygiene, statistical token-s...
open-design is a local-first macOS/Windows/Linux desktop app that turns your existing coding agent into a design engine, producing prototypes, landing pages, dashboards, slides, images, and video with real HTML/PDF/PPTX/MP4 export. It runs on 25 distinct local CLI executables...
v0.8.35 released September 11, Apache-2.0 TypeScript, 4,485 forks, 133 open issues, created March 10, so 49K stars in six months (GitHub). The premise is that an agent already writes HTML and GSAP competently, so making HTML the video authoring format removes the need for a vi...
tt-a1i/archify is an MIT-licensed agent skill turning a repo or description into architecture, workflow, sequence, data-flow and lifecycle diagrams, exported as self-contained HTML plus PNG, SVG, WebM and a share card. Its verifiability claim is mechanical rather than rhetoric...
NVIDIA's OpenShell enforces security policy at the execution layer without modifying agent code. Each agent runs in its own container with policy-enforced egress routing. Policies are declarative YAML controlling filesystem access, network, process execution, and inference cal...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.