PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Agentic Workflows Python Packages

Python packages with the GitHub topic agentic-workflows. Sorted by relevance, with stars and monthly downloads.
CorvinLabs
corvinos

Self-hosted agentic OS — connects Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

28K 6 0
rahulxj100
pipelinehub

Sentry for data pipelines and agentic workflows. Open source, zero config, 2-line setup.

9K 2 0
vivary-dev
create-vivary

Typed memory, search, and gates for AI-agent workspaces. Scaffold plain-Markdown project memory, state, skills, and review gates in one command.

5K 3 1
imyourboyroy
pyenv-native

Native-first, cross-platform Python version manager inspired by pyenv.

4K 1 0
vivary-dev
vivary-tropo

Typed memory, search, and gates for AI-agent workspaces. Scaffold plain-Markdown project memory, state, skills, and review gates in one command.

4K 3 1
liujuanjuan1984
lifeos-cli

Terminal-native LifeOS with an optional local Web UI for tasks, notes, habits, schedules, timelogs, relationships, and human-agent collaboration.

4K 10 1
DanielDeshmukh
autobot-swarm

Autobots | A decentralized model agentic swarm powered by NVIDIA NIM. Orchestrating high-precision, end-to-end authenticated software development through a specialized 6-file control architecture. Features automated security auditing, non-redundant task routing, and autonomous state management.

3K 6 0
DemonDamon
agenticx

AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).

3K 177 28
aresyn
codex-control-plane-mcp

Durable MCP control plane for long-running Codex Desktop tasks

3K 141 4
adriannoes
asap-protocol

Protocol for agent-to-agent communication with stateful orchestration, MCP-compatible and a public marketplace to discover and register agents.

3K 13 2
jlewitt1
keshro

Plan and run high-stakes engineering projects that need a human in the loop. Works with Claude, Codex, Cursor.

2K 0 0
ForgeWireLabs
repopact

Repository-native operating system for durable work between humans and coding agents: scoped authority, work items, evidence, audits, and project history kept inside the repo.

2K 0 0
rhishi99
agy-headless-bridge

Call the Google Antigravity CLI (agy) headlessly from any non-TTY context — Windows ConPTY + POSIX pty + MCP server. Fixes the empty-output bug (#76).

2K 9 2
thorwhalen
aw

AI Agentic Workflows for data preparation and transformation

2K 0 0
Jessinra
lorekeeper-mcp

Self-improving memory for AI agents

2K 2 0
vivary-dev
vivary-exo

Typed memory, search, and gates for AI-agent workspaces. Scaffold plain-Markdown project memory, state, skills, and review gates in one command.

2K 3 1
angrydat
dbression

Rage-quit your flaky DB regressions — modern, lightweight, multi-DB regression testing

1K 1 0
ENDEVSOLS
longtrainer

Production-ready RAG framework for Python — multi-tenant chatbots with streaming, tool calling, agent mode (LangGraph), vector search (FAISS), and persistent MongoDB memory. Built on LangChain.

1K 30 2
bitflight-devops
mcp-json-yaml-toml

A structured data reader and writer like 'jq' and 'yq' for AI Agents

1K 9 3
amareshhebbar
truenorth-framework

Declare the outcome, skip the logic. The developer-first infrastructure engine for structured, multi-turn AI conversations with built-in safety, async follow-ups, and native compliance

999 25 0
igptai
igptai

The official Python library for the iGPT API

850 13 0
vivary-dev
vivary-ozone

The review layer: graph-aware review and blast-radius impact over a tropo knowledge graph.

812 3 1
shubham10divakar
runxmd

runxmd — add state and execution to your .md files. .xmd is plain Markdown with a run-intent label.

772 0 0
Chris-Rebentisch
dualpass

Reliability-first agent harness with cross-vendor agent-as-judge review. Author with one CLI, review with another. No SDK lock-in.

672 0 0
    • Data from PyPI, GitHub, ClickHouse, and BigQuery