Zeyad-Azima/AgentsBear
Autonomous multi-agent pipelines from YAML. Any LLM. Zero boilerplate.
This project helps developers and MLOps engineers define, run, and monitor complex AI agent workflows without writing extensive Python code. It takes a declarative YAML file describing agents, tools, prompts, and execution logic, then executes it to produce structured outputs like JSON or markdown reports. It's designed for anyone building multi-step AI solutions that require reproducibility and structured parallelism.
Use this if you need to build structured, parallel, and reproducible multi-agent AI pipelines for tasks like data analysis, content generation, or automated auditing, especially when you want to avoid boilerplate code and ensure consistent execution across environments.
Not ideal if you're looking for an interactive AI assistant for one-off tasks or if your workflow doesn't require complex multi-agent orchestration, parallelism, or strict output schemas.
Stars
8
Forks
1
Language
JavaScript
License
MIT
Category
Last pushed
Apr 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Zeyad-Azima/AgentsBear"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JackChen-me/open-multi-agent
TypeScript multi-agent framework — one runTeam() call from goal to result. Auto task...
rohitg00/pro-workflow
Claude Code learns from your corrections — self-correcting memory that compounds over 50+...
Armur-Ai/Pentest-Swarm-AI
Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification,...
aiperceivable/apflow
**AI-Perceivable Distributed Orchestration** apflow is a distributed task orchestration engine...
ProxySoul/soulforge
Graph-powered code intelligence, multi-agent coding with codebase-aware AI. Good bye grep & pray