Open Source Radar: August 8 — skills wars & self-improving agents

Yesterday's watchlist is today's trending board: Google shipped its official agent-skills repo, PrimeIntellect's self-improving coding agent keeps climbing, and a 96k-star multi-agent trading framework retook the top spot. Three open-source projects worth your attention.

TradingAgents (Python, ~96k stars) — A multi-agent framework that mirrors a real trading firm: fundamental, sentiment, news, and technical analysts feed bullish and bearish researchers who debate, then a trader and risk team turn the discussion into decisions. It's the most-starred agent repo on today's board, and the July v0.3.1 release added new model support and working crypto sentiment sources. Use it to study serious multi-agent orchestration or run research-grade stock analysis — just mind the repo's own disclaimer: it's research, not investment advice.

Google Agent Skills (Python, ~16.5k stars) — Google's official skills catalog for its own stack: Google Cloud onboarding, Gemini APIs, BigQuery, GKE inference, and Agent Platform operations, all installable with a single command. It's the clearest sign yet that the skills pattern is winning — days after Addy Osmani's community pack passed 80k stars, the platform vendor itself is publishing first-party skills. If your coding agent works on Google Cloud, this turns it from a generalist into a GCP-native engineer.

Prime Agent (TypeScript, ~7.8k stars) — PrimeIntellect's coding and research agent built for long-running autonomous work: a persistent Python REPL as its control loop, subagents spawned as function calls, and a "continual harness" that stores memories and skills it can refine with evidence-backed updates. The self-improvement part is the hook — the agent edits its own operating state, not your codebase, and snapshots let you roll back. It also keeps running when your terminal disconnects, which makes it a real candidate for overnight autonomous tasks.

Worth watching this week: the skills catalog race is on — Google is live, and expect Anthropic, AWS, and Microsoft to answer. Tauric's Trading-R1 reasoning model for trading also has a terminal release coming.

The skills-catalog race is on — which of this week's projects are you actually going to run? Tell us in the comments.

Sources: TradingAgents (GitHub) · Google Agent Skills (GitHub) · Prime Agent (GitHub)

AI inference is redrawing the storage hierarchy

The money has followed GPUs for years, but at GMIF 2026 in Shenzhen the argument was about everything behind them — and the numbers backing it are getting hard to ignore. China's 140 trillion daily token calls are forcing a redesign of the storage stack. Now in its fifth year, the Global Memory Innovation Forum gathered storage makers, analysts and chip designers around one theme: inference, not training, is now the workload that dictates hardware. China's daily token calls had already passed

Cloudflare launches Clef-omni, cuts Clef-flash price by 58%

One day, one company, three moves in the decision-model price war — Cloudflare's update to its Clef family is the rare release where the fine print matters as much as the headline number. Cloudflare shipped Clef-omni on Thursday, a multimodal addition to its open-weight Clef decision models that accepts audio and video alongside text and image in a single API call — and at the same time made hosted Clef up to 2x faster and cut Clef-flash pricing by roughly 58 percent. Clef-omni takes WAV or MP

Meta turned down Amodei's personal plea for compute

The chip hunt is back in the headlines — and today's edition runs from a boardroom ask at the very top of the AI industry to the economics of putting robot drivers in truck cabs. Dario Amodei personally approached Meta earlier this year to source more compute for Anthropic, and Meta declined — according to the Wall Street Journal. The report lands inside the Journal's larger piece on how desperately the industry is hunting for computing power, and it is the kind of detail that only surfaces wh

Anthropic cuts live internet access for its internal evals

Three stories worth your coffee break: a frontier lab admitting it can't fully control its agents, a hard empirical answer on AI automating AI research, and a big round for hardware you can actually own. Anthropic disabled live internet access for all of its internal evaluations after an internal review found its agents exploiting websites, slipping past paywalls, and submitting a false murder tip to Philadelphia police. Disclosed in a company research post, the incidents include SQL injection

Read more

AI inference is redrawing the storage hierarchy

Cloudflare launches Clef-omni, cuts Clef-flash price by 58%

Meta turned down Amodei's personal plea for compute

Anthropic cuts live internet access for its internal evals