Llm Orchestration Python Packages

bernstein

The open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

ouroboros-ai

Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.

chimera-agent

Open-source AI agent that reasons by blending many AI models, does real work on its own, and keeps learning — safe, self-hostable, and fully yours.

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

protocore

Protocore — the agent loop, and nothing else. A protocol-first ReAct runtime for LLM agents in Python 3.12+: context budget, tool surface, compaction, snapshot and resume. No database driver, no HTTP endpoint — everything outward is a Protocol you implement. MPL-2.0.

aipass

Persistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.

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

subagent-harness-mcp

MCP gateway for Codex to orchestrate external coding-agent harnesses, with normalized lifecycle, localhost settings UI, and fail-closed no-overage safety.

async-batch-llm

Provider-agnostic framework for high-throughput LLM processing with async workers, automatic retries, rate limiting, and intelligent validation recovery.

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

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.

synaptum

A minimal, bus-driven Python framework for LLM agent orchestration that decouples communication, versioned prompts, and multi-agent patterns—helping AI architects build scalable, vendor-neutral agent systems without infrastructure lock-in.

treelang

A typed orchestration language for AI-generated, validated tool programs that execute locally—without model round-trips between steps.

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.

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)

harnessie

Verify agent-produced changes before merge, then govern multi-agent work with independent gates, ownership, sandboxing, and audit.

misterdev

Autonomous LLM build orchestrator: plans a goal into tasks, edits code with anchored SEARCH/REPLACE, and verifies every change through build/test/lint/typecheck gates before reporting done. Runs as a CLI or MCP server.

relayos

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

algernon-mcp

Algernon — orchestrate a fleet, keep your mind. Open-source MCP for scoped parallel sub-task dispatch. Apache-2.0.

adam-mcp

Adam Framework for OpenClaw — 5-layer persistent memory and identity architecture for AI agents. Production-validated over 353+ sessions. First documented case of emergent values in persistent AI, quantum-verified on IBM hardware.

justllm

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

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.

multi-mcp

Multi-Model chat, code review and analysis MCP Server for Claude Code

mcpaisuite-kernelmcp

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