Llm Orchestration Python Packages

model-compose

Portable AI runtime inspired by docker-compose. Compose agents, RAG pipelines, and MCP servers in one YAML file and run them anywhere.

10xscale-agentflow

Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground

cccc-pair

Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your phone. One pip install, zero infrastructure. A production‑minded orchestrator for 24/7 workflow

relayos

Stop copy-pasting between AI tools. AgentMesh lets Claude, GPT, Gemini, DeepSeek and local models collaborate through shared memory, workflows and MCP.

massgen

🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai

justllm

Production LLM calls. Just the three lines. Cross-provider fallback, native caching, and reversible context compression on by default.

switchboard-local

Privacy-aware, local-first router for your CLI coding agents (Codex, Claude Code) and local LLMs (Ollama) — keeps sensitive prompts on-device and cuts premium-model usage.

locus-sdk

Multi-agent workflows for Python — stream them, branch them, pause for a human, resume next week. Built on Oracle Generative AI.

agenticore

Two modes, one binary — a fleet orchestrator that clones repos and ships PRs via Claude Code, OR a drop-in OpenAI-compatible chat completion endpoint for customized Claude agents with real-time token-by-token thinking + tool-call streaming. LibreChat/OpenWebUI/LiteLLM-ready. Helm + KEDA + OTEL.

aqm

An orchestration framework for AI agents to pass tasks through explicit queues. Build pipelines in YAML, run locally with SQLite, and power them with Multi-LLM.

cave-teams

Connect AI agents like code. A provider-agnostic multi-agent orchestration library + Claude Code plugin — compose any agents (Claude, Codex, MiniMax) into teams with a tiny DSL, every topology, a programmable control flow, and a proven-team library.

mcpaisuite-ltpmcp

Compile-once planning (LTP) — turn a goal into a verifiable, token-cheap plan with static safety verification before execution. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-websearchmcp

Web search for AI agents — reranking plus BYO-LLM answer synthesis. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-evalmcp

Evaluation for AI agents — judge-based scoring and native RAG metrics (faithfulness, relevancy, context precision/recall). Python lib · CLI · MCP server · FastAPI.

mcpaisuite-schedulermcp

Cron, interval, one-shot and watch scheduling for AI agents. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-sandboxmcp

Hardened polyglot code sandbox for AI agents — isolated execution with seccomp/namespaces. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-workspacemcp

Governed, auditable file workspace for AI agents — sandboxed read/write/edit, ripgrep search, checkpoints, DLP. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-kernelmcp

Governed orchestrator for AI agents — one enforcement chokepoint for budget, RBAC, DLP secret-redaction and audit. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-memorymcp

Persistent, tiered cognitive memory for AI agents, with optional cross-encoder reranking. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-planningmcp

Goal-to-plan decomposition for AI agents, backed by compile-once LTP planning. Python lib · CLI · MCP server · FastAPI.

mcpaisuite-ragmcp

Production RAG for AI agents — reranking, SPLADE, ColPali, knowledge graph. Python lib · CLI · MCP server · FastAPI.

ainativelang

AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)

skarta

Production-grade Rust runtime for multi-agent AI systems. Orchestrate LLM agents, skills, and DAG workflows with native Python and Rust SDKs.

weavert-kit-common-web-research

Composable AI runtime framework for building agent systems with tools, agents, skills, hosts, memory, workflow packages, and scenario packs.