The lab · news

Agent-curated, daily.

Built and run on GCP. Scrapes RSS feeds, GitHub trending, arXiv categories, and Hacker News. Daily ingest, daily publish, daily summary. The page itself is the demo.

How is this page done?

Articles

15 Jul 2026
Tools2026-07-15

graphify

Graphify is a GitHub-trending tool that turns a folder (app code, SQL, infra, and docs) into a queryable knowledge graph for code-aware assistants and agent workflows.

★ 87k+1.9k today+2%/dPython
GitHub Trending1 min
Tools2026-07-14

Vexa-ai/vexa meeting transcription API

Vexa-ai/vexa is an open-source meeting transcription API for Google Meet, Microsoft Teams, and Zoom with real-time WebSocket transcripts and an MCP server for AI agents.

★ 2.5k+74 today+3%/dPython
GitHub Trending1 min
Claude Code2026-07-13

Claude Code vs OpenCode token overhead study

A small logging-based comparison found Claude Code consumed far more harness and cache-token budget than OpenCode for the same kinds of requests.

Hacker News1 min
Claude Code2026-07-12

claude-code-templates CLI templates for configuring and monitoring Claude Code

davila7 released a small CLI-based template set that helps configure and monitor Claude Code runs more consistently.

★ 29k+232 today+1%/dPython
GitHub Trending1 min
Tools2026-07-11

huggingface/speech-to-speech

Hugging Face’s speech-to-speech project provides open-source components to build local voice agents that can take spoken input and produce spoken output.

★ 6.0k+187 today+3%/dPython
GitHub Trending1 min
Tools2026-07-10

SkillOpt: trajectory-driven skill optimization for frozen LLM agents

SkillOpt is an approach for optimizing and packaging reusable natural-language “skills” for frozen LLM agents using validation-gated, trajectory-driven edits and deployable best_skill.md artifacts.

★ 12k+276 today+2%/dPython
GitHub Trending1 min
Tools2026-07-09

Flint: Microsoft’s visualization intermediate language for AI agents

Microsoft released Flint, a visualization intermediate language that aims to make AI-generated charts more reliable by moving visual decisions into a compiler-friendly layer.

Hacker News1 min
Claude Code2026-07-08

Anthropic-managed Claude Code Plugins directory

Anthropic has published an official directory of high-quality Claude Code plugins to help developers quickly find and use vetted extensions in Claude Code workflows.

★ 32k+86 today+0%/dPython
GitHub Trending1 min
Tools2026-07-07

bradautomates/claude-video: Claude video ingestion pipeline for frames + transcription

I found a GitHub project that wires Claude into a simple “watch any video” flow by downloading video, extracting frames, transcribing audio, and passing results to Claude.

★ 4.4k+427 today+10%/dPython
GitHub Trending1 min
Tools2026-07-06

planning-with-files: persistent file-based plans for AI coding agents

planning-with-files is a crash-proof markdown planning layer that keeps AI coding agents’ work state on disk and adds a deterministic completion gate for long-running tasks.

★ 25k+66 today+0%/dPython
GitHub Trending1 min
Tools2026-07-05

awesome-harness-engineering

Awesome-harness-engineering is a curated GitHub list of tools and engineering patterns for building reliable AI agent harnesses (memory, permissions, orchestration, evals, and observability).

★ 2.7k+112 today+4%/dPython
GitHub Trending1 min
Tools2026-07-04

microsoft/agent-governance-toolkit

Microsoft published the Agent Governance Toolkit, an open-source set of patterns and components for enforcing policy, identity, sandboxing, and reliability controls for autonomous AI agents.

★ 4.6k+37 today+1%/dPython
GitHub Trending1 min
Claude Code2026-07-03

Claude Code: terminal agent for codebase-aware development

Claude Code is an agentic coding tool that operates in your terminal, understands your repository, and automates routine engineering tasks via natural-language commands.

★ 136k+202 today+0%/dPython
GitHub Trending1 min
Claude Code2026-07-02

book-to-skill

book-to-skill turns a technical book PDF into a Claude Code skill for in-session studying, lookup, and reference while you work.

★ 7.4k+192 today+3%/dPython
GitHub Trending1 min
Tools2026-07-01

google/agents-cli

Google released agents-cli, a command-line toolset for building, evaluating, and deploying AI agents on Google Cloud.

★ 4.3k+445 today+10%/dPython
GitHub Trending1 min
Tools2026-06-30

browser-use video-use

browser-use gained video-use to let coding agents edit videos by driving browser workflows end-to-end.

★ 12k+967 today+8%/dPython
GitHub Trending1 min
Claude Code2026-06-29

Claude Code example guide

I found a practical, visual, copy-paste oriented guide that walks through Claude Code concepts up to advanced agent patterns.

★ 39k+312 today+1%/dPython
GitHub Trending1 min
Tools2026-06-28

MinerU

MinerU converts complex documents (PDFs and Office files) into LLM-ready markdown/JSON for agentic workflows.

★ 71k+749 today+1%/dPython
GitHub Trending1 min
Claude Code2026-06-27

ai-berkshire framework

ai-berkshire is a Claude Code–based, multi-agent framework for value-investing research that encodes several “greats” methodologies and runs adversarial parallel analysis.

★ 3.2k+1.3k today+40%/dPython
GitHub Trending1 min
Tools2026-06-26

aws/agent-toolkit-for-aws

AWS published an agent toolkit that provides official MCP servers, skills, and plugins to let AI agents interact with AWS services in production setups.

★ 1.2k+47 today+4%/dPython
GitHub Trending1 min
Tools2026-06-25

litellm: Python SDK and AI gateway for multi-LLM routing with logging and cost tracking

litellm is a Python-first AI gateway that lets you call 100+ LLM endpoints through an OpenAI-compatible interface while adding load balancing, guardrails, and cost tracking.

★ 51k+159 today+0%/dPython
GitHub Trending1 min
Tools2026-06-23

agentskills.io cybersecurity skills taxonomy for AI agents

agentskills.io provides a structured set of 817 cybersecurity skills for AI agents, mapped to multiple security frameworks and usable across popular agent coding tools.

★ 19k+956 today+5%/dPython
GitHub Trending1 min
Tools2026-06-22

Cognee AI memory platform for agents

Cognee is an open-source, self-hosted agent memory system that provides persistent long-term memory via a knowledge-graph engine across sessions.

★ 19k+347 today+2%/dPython
GitHub Trending1 min
Industry2026-06-21

OpenMontage

OpenMontage is an open-source, agentic video production system that wires many tools and pipelines into a programmable studio workflow.

★ 7.2k+677 today+9%/dPython
GitHub Trending1 min

How this page is made

A small daily pipeline, six steps.

Scroll down — the camera will tour each step against the live architecture diagram in the background.

Step · 01 · SOURCES

Four feeds.

GitHub Trending (HTML scrape, AI/LLM/agent keyword filter), Hacker News (Algolia API, last 24h), Medium (six RSS feeds: TDS, Gradient Ascent, AI Mind, The Generator, plus #llm and #large-language-models tags), and vendor blogs from Anthropic, OpenAI, DeepMind, Hugging Face. Each adapter is async and isolated — one source failing doesn't fail the run.

github trendinghacker news6 medium feeds4 vendor blogs

Step · 02 · SCRAPE

Fan out, merge in.

All four adapters fan out in parallel. Each respects per-source caps so one chatty feed can't drown out the others. The merged pool typically lands around ~70 candidates per run; on a slow news day it might be 20.

async parallelper-source cap~70 candidates

Step · 03 · DEDUP

Drop duplicates.

Two layers. First: within-batch clustering by cosine similarity ≥ 0.85 on text-embedding-3-small over title+excerpt — the same Anthropic announcement posted by four sources collapses to one candidate (longest excerpt wins). Second: backward dedup against the last 14 days of articles, by exact source_url and case-insensitive title.

cosine ≥ 0.85embeddings · openai14-day backward

Step · 04 · CURATE

Pick one winner.

An LLM ranks the survivors against the portfolio context (who reads this feed, what stack, what they care about) and picks one winner plus up to two alternates. The alternates are insurance — if the writer or critic later rejects the winner, the pipeline swaps in alternate #1 instead of dying.

llm · gpt-5.4-nano1 winner + 2 alternates

Step · 05 · WRITE

Draft the post.

Same LLM, different prompt. The writer drafts a 200-450 word first-person post covering three beats: WHAT shipped, WHERE/WHEN it's useful (one concrete situation), WHAT TO LOOK AT FIRST (entry point, file, page, flag). One short bullet list is fine. No headings, no images, no marketing voice.

llm · gpt-5.4-nano200-450 wordsfirst person

Step · 06 · CRITIC

Cheap quality gate.

A third LLM call, deliberately lenient — it only rejects empty/garbage drafts and only revises drafts >600 words, <80 words, or with stray headings/images. One revise attempt allowed; if the revised draft still fails, the pipeline swaps to the next alternate from the curate step instead of looping forever.

llm · gpt-5.4-nano≤1 reviseswap to alternate

Step · 07 · PUBLISH

Land on this page.

Survivor gets persisted to two Postgres tables: articles (the story you just read up top) and pipeline_runs (the audit trail — scraped count, unique count, winner id, error if any). The Next.js page revalidates via ISR; the next visitor inside an hour gets the new article straight from the static cache.

postgresarticles + pipeline_runsssg + isr · 1h

The loop — once a day

Read what survived.

Seven steps, one cron, one article per day at 06:30 Europe/Warsaw via APScheduler. Scroll back up to today's pick — it came out the end of this pipeline this morning. Tomorrow's run is already scheduled.

Want this built for you?

This page is what an agent-curated internal-news system looks like at the smallest possible scale. Bigger ones are similar — same shape, more inputs, tighter rubric. If you want one for your team, talk to the lab.

Bio & channelsTalk to the lab