Llm Agent Python Packages

strands-agents

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

agentscope

Build and run agents you can see, understand and trust.

monocle-apptrace

Monocle is a framework for tracing GenAI app code. This repo contains implementation of Monocle for GenAI apps written in Python.

gptme

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

strands-agents-mcp-server

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

pocketflow

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

mirascope

The LLM Anti-Framework

veles-ai

Minimal CLI agent framework with compounding project memory — gets smarter with every session. Clean, modular, any LLM provider

strands-harness

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

autogenstudio

A programming framework for agentic AI

hermes-scope-recall

Long-term memory for Hermes and Codex, with local storage, source-backed recall, and tools to inspect, correct, or delete remembered information.

cli-agent-runner

Keep agent CLIs running 7×24 — supervise Claude Code / aider / any prompt-arg agent with 11-layer defenses and structured observability.

chattts

A generative speech model for daily dialogue.

duduclaw

Turn AI coding CLIs (Claude Code, Codex, Antigravity) into AI employees on LINE, Telegram, Discord, Slack and 7 more chat apps. A judge reviews each result, every cost is logged, memory stays on your machine. Also runs as a standalone MCP memory server. Self-hosted, Apache 2.0.

noeta-sdk

Python SDK for durable AI agents: survive crashes, pause for human approval at no cost, scale from a script to a multi-host cluster. Any LLM (Anthropic, OpenAI-compatible), MCP, self-hosted.

synapse-cli-agent

Where intent meets code — a local AI coding agent

autoagent-core

Zero-dependency LLM agent runtime — tool use, MCP, sandboxed self-written tools, checkpoint/resume, approval gates, bi-temporal fact memory, code-level guards (context bounds, loop guard, egress control, shadow mode), declarative tool policy, OpenTelemetry. Not a framework. 885 tests, CI Linux/Windows, 31 runnable demos, online visual builder.

edda-framework

a durable execution framework for Python

noeta-runtime

Python SDK for durable AI agents: survive crashes, pause for human approval at no cost, scale from a script to a multi-host cluster. Any LLM (Anthropic, OpenAI-compatible), MCP, self-hosted.

wcgw

Shell and coding agent on mcp clients

gptme-acp

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

llmling-agent

A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server).

loomcycle

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

agentpool

A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server).