An enterprise agent-building framework and SDK on LangGraph with tool integration, policy guardrails, multi-agent supervision, and knowledge support.cuga-project
A research routing framework for multi-agent LLM systems that selects executors per subtask with capability screening and contextual-bandit learning, then aggregates outputs by voting.gradienthq
AuC (Agents-ufy-Core) is an asyncio-based Python framework for building single-agent systems, with a ReAct loop, multi-model adapters, tiered tool permissions, checkpoints, and terminal or web interfaces.ufy2024
A Python framework for building production agentic systems, bundling agents, MCP tool interfaces, a runtime harness, agent identity, multi-tenancy, approval gates and audit logging.promptise-com
A research framework that wraps static benchmark environments with composable Setup, Rule and Link layers so agents can learn, induce skills and train with RL across ALFWorld, WebArena, SWE-bench and more.google-research
python-utcp is the official Python implementation of the Universal Tool Calling Protocol, a modular SDK that lets AI agents call any API directly. It ships a core client plus HTTP, CLI, MCP, text, and WebSocket protocol plugins, with OpenAPI ingestion and per-manual protocol restrictions.universal-tool-calling-protocol
A developer framework for interacting with large language models through llama.cpp. It provides function calling, structured output, and agent chains for building LLM-powered agents locally.Maximilian-Winter
Swarm is a Swift-native runtime for building AI agents, with type-safe tools, on-device Foundation Models inference, composable workflows, memory and guardrails.christopherkarani