workflowstacks
mcp-server

agentica

One person, a team of agents. Multi-session CLI that collaborates across terminals; /goal keeps long tasks running; WeChat/WeCom/Feishu gateway lets you call them back when you walk away. Async Python SDK, persistent memory, self-evolving skills.
357 stars+2★ this week48 forksPythonUpdated 10/24/2026100% free · open source
What it does

Agentica turns a single developer into a persistent, multi‑agent team you can talk to from the terminal or messaging apps, letting long‑running goals keep running while you’re away.

When to use it
  • •You need a semi‑autonomous assistant that can keep working on a research or data‑gathering task while you switch to other work.
  • •Your team uses CLI‑first workflows and wants to trigger AI agents from Slack‑like tools (WeChat, Feishu, WeCom) without writing code each time.
  • •You want a Python SDK to embed agent calls into scripts and let the agents remember context across sessions.
Ready-to-paste prompt
/goal scrape the Crunchbase API for all Series A rounds in the health‑tech sector between Jan‑2024 and Jun‑2024, rank them by amount raised, and generate a markdown table with links to each company.
Heads up: Agentica requires Python 3.10+ **and** a reachable Redis instance for persistent memory; if `REDIS_URL` isn’t set, the server will fail to start.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/agentica && curl -fsSL https://workflowstacks.com/api/skills/agentica/claude-skill -o ~/.claude/skills/agentica/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How agentica works
Codeflow
Free to inspect

Agentica is a very large Python project (~159k lines across 595 code files, plus 283 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~159k lines · 595 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app — add your API keys. Reading the code is optional.
Runs on
Python · Docker
Needs API keys (.env)
Python 94%TypeScript 4%CSS 1%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    desktop/main.js
    Where the program starts running
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    agentica/__init__.py
    Inside agentica/ — the main logic begins here
What's in each folder
agentica/Core code — the actual logic415 files
web/Frontend / UI62 files
examples/Examples you can copy103 files
docs/Documentation65 files
evaluation/Folder82 files
sdk-ts/Folder12 files
desktop/Folder9 files
scripts/Helper scripts7 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
shibing624
Language
Python
Category
mcp-server
Published
6/3/2024

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/agentica.svg)](https://workflowstacks.com/skills/agentica?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Outcome guide

Turn meeting notes into a summary email automatically

Paste the transcript into a private form and the workflow writes and emails a concise recap — decisions, owners, open questions — that people will actually read.

Outcome guide

Prep for sales objections before every call

List your upcoming deals with a little context, and the workflow builds a prep card per deal: the 3 objections you’re most likely to hear, an honest response to each, and one sharp question to ask.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 376,837
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 288,000
ECC supercharges AI‑agent performance for founders building Claude, Codex, and Cursor
Founders gain optimized skills, memory, security, and research‑first development for Claude Code, Codex, Opencode, Cursor, backed by 280k+ GitHub stars.
mcp-server★ 156,636
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 5,500
wigolo – Local‑First AI Coding Search with No API Keys
wigolo lets founders power their AI coding agents with on‑device search, fetch, and crawling over MCP—zero cloud costs and 5.5k+ GitHub stars, ideal for privacy‑focused dev teams.
mcp-server★ 4,841
Sell Smarter with DeskcommCRM
Self-hosted CRM with AI agents for chat-based sales. Ideal for founders of businesses selling via WhatsApp.
mcp-server★ 417
SHAFT_ENGINE: Streamline Multi‑Platform Test Automation for Faster Releases
SHAFT_ENGINE lets founders run web, mobile, API, CLI, database, and desktop end‑to‑end tests with a concise wizard‑style syntax, cutting setup time and boosting ROI.