zou-group/sirius
SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
This project helps researchers and developers create AI systems that can learn and improve their reasoning over time, similar to how humans learn from experience. It takes initial problem descriptions or game scenarios, along with agent interactions, and produces improved, more accurate AI agents. This is ideal for those building sophisticated AI agents for tasks like complex problem-solving, iterative refinement of answers, or strategic competitive interactions.
Use this if you need AI agents that can continuously get better at tasks by learning from their past successes and failures.
Not ideal if you are looking for a pre-built, ready-to-deploy AI solution without custom agent development or model fine-tuning.
Stars
98
Forks
11
Language
Python
License
MIT
Category
Last pushed
Dec 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/zou-group/sirius"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mitdbg/palimpzest
A System for Optimized Semantic Computation
SamurAIGPT/GPT-Agent
🚀 Introducing 🐪 CAMEL: a game-changing role-playing approach for LLMs and auto-agents like...
bubbuild/republic
Build LLM workflows like normal Python while keeping a full audit trail by default.
lwcsrf/netflux
Minimalist framework for authoring custom agentic applications in python; emphasizes task...
dlMARiA/Syzygy-of-thoughts
Syzygy-of-thoughts