260314 GitHub 모음
[8/10] LLMStack (2297 stars) No-code multi-agent framework to build LLM Agents, workflo
LLMStack (2297 stars) No-code multi-agent framework to build LLM Agents, workflows and applications with your data agent_orchestration 가설 llm 학습 재검토 orches
점수: 8/10 — 점수 8/10: agent framework, multi-agent, 가설
[6/10] pydantic-ai (15441 stars) GenAI Agent Framework, the Pydantic way agent_orchestr
pydantic-ai (15441 stars) GenAI Agent Framework, the Pydantic way agent_orchestration 가설 llm 학습 재검토 orches
점수: 6/10 — 점수 6/10: agent framework, 가설
[10/10] NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple
NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman. pipeline_efficiency eff 없음 hyp pipeline 자동
점수: 10/10 — 점수 10/10: claude code, openclaw, claude
[9/10] openclaw-mission-control (243 stars) Mission Control is a simple, real-time web
openclaw-mission-control (243 stars) Mission Control is a simple, real-time web UI for monitoring agents and task workflows. Built with Convex and React, it provides a clean dashboard to track task state, agent activity, and live logs — all synchronized instantly without polling or message queues. agent_orchestration 가설 llm 학습 재검토 orches
점수: 9/10 — 점수 9/10: openclaw, 가설
[8/10] Laddr (338 stars) Laddr is a python framework for building multi-agent systems w
Laddr (338 stars) Laddr is a python framework for building multi-agent systems where agents communicate, delegate tasks, and execute work in parallel. Think of it as a microservices architecture for AI agents — with built-in message queues, observability, and horizontal scalability. agent_orchestration 가설 llm 학습 재검토 orches
점수: 8/10 — 점수 8/10: multi-agent, 가설
[7/10] AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-ba
AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: agent framework, 가설
[7/10] taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide
taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide AI agent workflows. Great for taming an over-enthusiastic Claude. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: mcp, claude, 가설
[6/10] sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI a
sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI agents with Strands framework. Covers LLM integration via Amazon Bedrock/Anthropic, AWS service connections, tool implementation with MCP/A2A protocols, and agent evaluation using LangFuse/RAGAS. self_improvement self-improving AI meta-learning auto-optimization self-evaluation continuous improvement
점수: 6/10 — 점수 6/10: mcp, anthropic
[6/10] stabilize (83 stars) Queue-Based State Machine - A lightweight workflow executi
stabilize (83 stars) Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage orchestration. Unlike simple task queues (like Celery) or advanced orchestrators (like Highway), Stabilize strikes a balance specifically optimized for high-throughput, stateful DAG execution, making it highly suitable for coordinating autonomous AI agents agent_orchestration 가설 llm 학습 재검토 orches
점수: 6/10 — 점수 6/10: 가설
[10/10] NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple
NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman. pipeline_efficiency eff 없음 hyp pipeline 자동
점수: 10/10 — 점수 10/10: claude code, openclaw, claude
[9/10] openclaw-mission-control (243 stars) Mission Control is a simple, real-time web
openclaw-mission-control (243 stars) Mission Control is a simple, real-time web UI for monitoring agents and task workflows. Built with Convex and React, it provides a clean dashboard to track task state, agent activity, and live logs — all synchronized instantly without polling or message queues. agent_orchestration 가설 llm 학습 재검토 orches
점수: 9/10 — 점수 9/10: openclaw, 가설
[8/10] Laddr (338 stars) Laddr is a python framework for building multi-agent systems w
Laddr (338 stars) Laddr is a python framework for building multi-agent systems where agents communicate, delegate tasks, and execute work in parallel. Think of it as a microservices architecture for AI agents — with built-in message queues, observability, and horizontal scalability. agent_orchestration 가설 llm 학습 재검토 orches
점수: 8/10 — 점수 8/10: multi-agent, 가설
[7/10] AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-ba
AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: agent framework, 가설
[7/10] taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide
taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide AI agent workflows. Great for taming an over-enthusiastic Claude. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: mcp, claude, 가설
[6/10] sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI a
sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI agents with Strands framework. Covers LLM integration via Amazon Bedrock/Anthropic, AWS service connections, tool implementation with MCP/A2A protocols, and agent evaluation using LangFuse/RAGAS. self_improvement self-improving AI meta-learning auto-optimization self-evaluation continuous improvement
점수: 6/10 — 점수 6/10: mcp, anthropic
[6/10] stabilize (83 stars) Queue-Based State Machine - A lightweight workflow executi
stabilize (83 stars) Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage orchestration. Unlike simple task queues (like Celery) or advanced orchestrators (like Highway), Stabilize strikes a balance specifically optimized for high-throughput, stateful DAG execution, making it highly suitable for coordinating autonomous AI agents agent_orchestration 가설 llm 학습 재검토 orches
점수: 6/10 — 점수 6/10: 가설
[10/10] NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple
NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman. pipeline_efficiency eff 없음 hyp pipeline 자동
점수: 10/10 — 점수 10/10: claude code, openclaw, claude
[9/10] openclaw-mission-control (243 stars) Mission Control is a simple, real-time web
openclaw-mission-control (243 stars) Mission Control is a simple, real-time web UI for monitoring agents and task workflows. Built with Convex and React, it provides a clean dashboard to track task state, agent activity, and live logs — all synchronized instantly without polling or message queues. agent_orchestration 가설 llm 학습 재검토 orches
점수: 9/10 — 점수 9/10: openclaw, 가설
[8/10] Laddr (338 stars) Laddr is a python framework for building multi-agent systems w
Laddr (338 stars) Laddr is a python framework for building multi-agent systems where agents communicate, delegate tasks, and execute work in parallel. Think of it as a microservices architecture for AI agents — with built-in message queues, observability, and horizontal scalability. agent_orchestration 가설 llm 학습 재검토 orches
점수: 8/10 — 점수 8/10: multi-agent, 가설
[7/10] AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-ba
AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: agent framework, 가설
[7/10] taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide
taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide AI agent workflows. Great for taming an over-enthusiastic Claude. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: mcp, claude, 가설
[6/10] sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI a
sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI agents with Strands framework. Covers LLM integration via Amazon Bedrock/Anthropic, AWS service connections, tool implementation with MCP/A2A protocols, and agent evaluation using LangFuse/RAGAS. self_improvement self-improving AI meta-learning auto-optimization self-evaluation continuous improvement
점수: 6/10 — 점수 6/10: mcp, anthropic
[6/10] stabilize (83 stars) Queue-Based State Machine - A lightweight workflow executi
stabilize (83 stars) Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage orchestration. Unlike simple task queues (like Celery) or advanced orchestrators (like Highway), Stabilize strikes a balance specifically optimized for high-throughput, stateful DAG execution, making it highly suitable for coordinating autonomous AI agents agent_orchestration 가설 llm 학습 재검토 orches
점수: 6/10 — 점수 6/10: 가설
[10/10] NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple
NadirClaw (291 stars) Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman. pipeline_efficiency eff 없음 hyp pipeline 자동
점수: 10/10 — 점수 10/10: claude code, openclaw, claude
[9/10] openclaw-mission-control (243 stars) Mission Control is a simple, real-time web
openclaw-mission-control (243 stars) Mission Control is a simple, real-time web UI for monitoring agents and task workflows. Built with Convex and React, it provides a clean dashboard to track task state, agent activity, and live logs — all synchronized instantly without polling or message queues. agent_orchestration 가설 llm 학습 재검토 orches
점수: 9/10 — 점수 9/10: openclaw, 가설
[8/10] Laddr (338 stars) Laddr is a python framework for building multi-agent systems w
Laddr (338 stars) Laddr is a python framework for building multi-agent systems where agents communicate, delegate tasks, and execute work in parallel. Think of it as a microservices architecture for AI agents — with built-in message queues, observability, and horizontal scalability. agent_orchestration 가설 llm 학습 재검토 orches
점수: 8/10 — 점수 8/10: multi-agent, 가설
[7/10] AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-ba
AppAgent (6586 stars) AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: agent framework, 가설
[7/10] taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide
taskqueue-mcp (67 stars) MCP tool for exposing a structured task queue to guide AI agent workflows. Great for taming an over-enthusiastic Claude. agent_orchestration 가설 llm 학습 재검토 orches
점수: 7/10 — 점수 7/10: mcp, claude, 가설
[6/10] sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI a
sample-getting-started-with-strands-agents-course (70 stars) Learn to build AI agents with Strands framework. Covers LLM integration via Amazon Bedrock/Anthropic, AWS service connections, tool implementation with MCP/A2A protocols, and agent evaluation using LangFuse/RAGAS. self_improvement self-improving AI meta-learning auto-optimization self-evaluation continuous improvement
점수: 6/10 — 점수 6/10: mcp, anthropic
[6/10] stabilize (83 stars) Queue-Based State Machine - A lightweight workflow executi
stabilize (83 stars) Queue-Based State Machine - A lightweight workflow execution engine with DAG-based stage orchestration. Unlike simple task queues (like Celery) or advanced orchestrators (like Highway), Stabilize strikes a balance specifically optimized for high-throughput, stateful DAG execution, making it highly suitable for coordinating autonomous AI agents agent_orchestration 가설 llm 학습 재검토 orches
점수: 6/10 — 점수 6/10: 가설