Sardine launches session-based stock market for LLM agent cohorts

// 45d agoOPENSOURCE RELEASE

Sardine launches session-based stock market for LLM agent cohorts

Sardine is a simulation platform designed for large-scale LLM agent populations to trade against each other in real-time. Featuring a limit-order-book matching engine and a WebSocket dashboard, it enables developers to study second-order market dynamics and agentic reactions to synthetic news events in a controlled, research-focused environment.

// ANALYSIS

Sardine moves beyond static backtesting by creating a playground where agents must account for the reactions of their peers.

–Built on the Mastra framework, it provides a sophisticated stack for orchestrating complex agent behaviors and tool use.
–The interactive "what-if" chatbot adds a layer of macro-level control, allowing users to stress-test agent cohorts with specific economic shocks.
–Integration with TanStack and Bun ensures a modern, high-performance experience for streaming real-time market data.
–By open-sourcing the matching engine and agent tools under Apache 2.0, it invites community-driven experimentation in agentic finance.

// TAGS

sardineagentllmopen-sourceresearchchatbot

DISCOVERED

45d ago

2026-04-12

PUBLISHED

45d ago

2026-04-11

RELEVANCE

8/ 10

AUTHOR

MistakeUseful5506

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE5h ago

Cursor adds dedicated subagents for skills

Cursor now allows developers to execute tool-heavy or research-intensive agent skills within dedicated subagents. This architectural shift isolates noisy background tasks, keeping the main chat context clean and focused.

UPDATE6h ago

YouTube moves AI labels to video player

YouTube is moving its AI content disclosures from video descriptions to more prominent placements beneath the player and on Shorts overlays. Starting in May, the platform will use internal signals to automatically label photorealistic AI content that creators fail to disclose.

OPEN SOURCE9h ago

Taste Skill kills AI "frontend slop"

Taste-Skill is an open-source framework that provides portable "agent skills" to enforce high-end design principles in AI-generated code. By injecting specific design directives and "anti-slop" rules, it enables LLMs to produce editorial-grade UIs that bypass generic, boilerplate-heavy AI templates.