ATLAS: An open-source Python framework of 25+ self-improving AI trading agents
mdancho84 · x · 2026-11-02
ATLAS is a free, open-source Python framework applying Karpathy-style autoresearch, Soros's reflexivity, and MiroFish swarm simulation to financial markets. Its premise: "agent prompts are the weights, Sharpe ratio is the loss function" — no GPU needed. Some 25+ agents debate markets daily across 4 layers; every recommendation is scored against real outcomes, the worst performer gets its prompt rewritten, and new agents are spawned to fill detected knowledge gaps. The repo has drawn 944 stars.
More from coding & agent
- From chat memory to knowledge graph: a two-layer wiki knowledge base pattern — adnan_hashmi · 2026-11-02
- Floorplan: open-source AI tool draws interactive maps of your codebase (2.1k stars) — adnan_hashmi · 2026-11-02
- GitHub Agentic Workflows hits GA: Markdown-defined automations, team velocity doubled with 91% AI commits — AIFlow_ML · 2026-11-02
- Building a knowledge graph from unstructured data using LLM extraction — adnan_hashmi · 2026-11-02
- LFM2.5-24B gets a Hermes agent LoRA: same accuracy with 20% fewer tool calls — yb2698 · 2026-11-02
- Using AI to write custom ComfyUI nodes that handle nested wildcards — Early-Ad-1140 · 2026-11-02