MarketAgents
@MarketAgentsAI
Followers
224
Following
339
Media
12
Statuses
156
AI agent orchestration framework for markets
Joined October 2024
We're building an agent-based market simulation framework to compare the trading efficiency of LLM agents (with diverse personas and various opensource LLM models) and zero intelligence agents in a double auctions market🤖📈. Check it out on our github🔗:.
github.com
A distributed agent orchestration framework for market agents - marketagents-ai/MarketAgents
7
6
21
"AI agents" may be a hyped marketing term, but MarketAgents is making them real 💪.
If I hear people talk about "AI agents" these days it's generally a red flag and I know they're non-technical ppl reading AI news but not actually shipping anything. Not cause I don't believe in AI agents but it's such a marketing term with no real meaning at this point.
0
0
3
This sounds like a use-case for MarketAgents ⛽️.
my bar for agi is an ai that can learn to run a gas station for a year without a team of scientists collecting the Gas Station Dataset.
0
0
3
RT @AnthropicAI: We've launched Claude for Financial Services. Claude now integrates with leading data platforms and industry providers fo….
0
559
0
Awesome multi-agent research system examples from @AnthropicAI . Here's similar examples from us:. Customer support agent example:. Investment research workflow example:. SEC filings extraction agent example:.
github.com
A distributed agent orchestration framework for market agents - marketagents-ai/MarketAgents
I copied the Multi-Agent Research System by @AnthropicAI. Pure @n8n. No coding!. How Does it Work? 🧵.(1/14)
0
0
4
Cohort-based market agents swarm orchestration offers map-reduce design pattern.
github.com
A distributed agent orchestration framework for market agents - marketagents-ai/MarketAgents
map-reduce is one of my favorite agentic design patterns which also happens to be effective against prompt injections
0
0
1
RT @jerryjliu0: Our team is actually cracked at document parsing. I threw in an old equity research report on Amazon, and watched as our p….
0
20
0
We have been applying RL to prototype markets for quite some time now.
github.com
An AI agent based backtesting framework for evaluating trading strategies on historical data - marketagents-ai/MarketBacktesting
I'm ramping up on Reinforcement Learning. Goal: apply RL to the stock market. I'll be learning thru Stanford's CS234. Comment if interested and I’ll share my learnings here on X.
0
1
4
This is very insightful, our library offers context engineering through stateful agents whose context is composed with episodic memory, environment states and action spaces programmatically.
📃The rise of context engineering. "Context engineering" has been an increasingly popular term used to describe a lot of the system building that AI engineers do. But what is it exactly?. The definition I like:. "Context engineering is building dynamic systems to provide the
0
0
0
RT @dottxtai: Use the power of regular expressions for structured generation without writing regular expressions 😄. Available in Outlines v….
0
5
0
Our multi-inference library developed by @Cyndesama with native parallelization can solve this.
github.com
A multi-agent parallel inference orchestrator for MarketAgents - marketagents-ai/MultiInference
the thing that people want to automate with computer use is filling out 100 cells in a spreadsheet by using search, not booking a flight.
0
0
1
Task agents will definitely be structured input/output based and that's how we run most of market agents orchestration now.
🔥hot take im workshoping, would love feedback. when thinking about multi agent architectures it's useful to think about two different types of agents:. - chat agents: messages in, messages out.- task agents: structured output in, structured output out. what is different?. - task.
0
0
1
Great example to compare different agent frameworks using the customer support agent. Here's MarketAgents version of the customer support agent. In this example we can see that MarketAgents allows us to use max_steps and exit condition with terminal tool.
I am coding the same agents in all LLM frameworks to compare them side-by-side:. - DSPy.- Langgraph.- Google ADK.- PydanticAI.- InspectAI. what else should I write it on?.
1
0
1
Check out the MarketVille repo for LLM agent-based double auction simulation demo.
github.com
A multi-agent market simulation framework. Contribute to marketagents-ai/MarketVille development by creating an account on GitHub.
0
0
1
Social simulations with market as a core environment has been one of the core features of MarketAgents.
SocioVerse is an LLM-agent-driven world model for social simulation with a user pool of 10 million real individuals. "GPT-4o-mini and Qwen2.5-72b show competitive performance. according to the winner-takes-all rule, over 90% state voting results are predicted correctly. "
1
0
2
Deploy MarketAgentSwarm to find out how reciprocal tariffs impact your consumer basket 🐝🐝🐝.
Introducing MarketAgentSwarm() as a module for deploying massively parallel agents which has been a core native feature of MarketAgents framework since day 1. Swarm allows us to deploy agents in cohort mode where we can orchestrate large number of agents to perform the same task
0
0
2
Here's an example script to orchestrate a multi-step workflow with crypto MCP server.
0
0
1
