arcstep/illufly
✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体
Built on memory distillation and vector retrieval, the agent framework integrates knowledge from conversations and documents through a unified RAG pipeline that automatically learns and recalls information—supporting both naive fact injection and semantic document embedding via FAISS. Core single-agent implementations include ReAct, ReWOO, and Plan-and-Solve patterns from recent agent research papers, with OpenAI-compatible function calling and automatic tool callback capabilities for stateful reasoning and planning.
Available on PyPI.
Stars
77
Forks
10
Language
Python
License
MIT
Category
Last pushed
Dec 07, 2025
Monthly downloads
81
Commits (30d)
0
Dependencies
14
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/arcstep/illufly"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
theaiautomators/claude-code-agentic-rag-masterclass
Build an agentic RAG app from scratch by collaborating with Claude Code. 8-module course...
OmidZamani/dspy-skills
Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and...
bug-ops/zeph
Rust AI agent where skills evolve from real usage and every context token earns its place....
aws-samples/conversational-ai-assistant-multi-route-chain
This GitHub repository guides you through building an advanced Conversational AI assistant using...
TechDocsStudio/biel-mcp
Connect AI tools like Cursor, VS Code, and Claude to your product docs.