The Stack

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) · TradingAgents paper · Google Agent Skills (GitHub) · Prime Agent (GitHub)

Salesforce's Dreamforce pitch: let agents replace the UI

Two stories from today worth your time: Salesforce arguing that its own interface is the thing standing between customers and its data, and Huawei's chairman saying out loud what his compute business is aiming at. Salesforce opened Dreamforce by launching AIforce, a layer that pushes the company'

Commerce ordered Kalshi to pull its AI compute price tracker

Two stories today about where AI's bottlenecks actually are: who is allowed to put a price on compute, and whether an agent that works today will work tomorrow. The US Commerce Department ordered Kalshi to take down its AI-compute forward curve last month, citing national security concerns,

Musk wants rivals to run test harnesses on each other's models

Two stories today run the same test on AI's gatekeepers: who gets to check the work before it ships, and what the answer looks like when the checker isn't the government. Then a biology dataset turned into a toy shows what happens when the public gets

A cop searched 19,000 Flock cameras to type "LMAO"

The pitch for automated license-plate cameras is that they catch stolen cars and wanted suspects. Flock Safety's own audit logs suggest a lot of the searches were for something else entirely. A review of Flock Safety's search logs found officers using the one field meant

Read more

Salesforce's Dreamforce pitch: let agents replace the UI

Commerce ordered Kalshi to pull its AI compute price tracker

Musk wants rivals to run test harnesses on each other's models

A cop searched 19,000 Flock cameras to type "LMAO"