AgentForge

Low-code Python framework for YAML-defined agents and multi-agent Cogs, with personas, prompt templates and memory nodes.

Harness by DataBassGit

IndexedGPL-3.0★ 860

Write a review

Install

From the package registry. Read the repository before you give any tool access to your data.

pip install agentforge

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

AgentForge is a low-code framework for building AI agents and cognitive architectures. Agents, Cogs and optional Memory are declared in YAML: Cogs compose agents into multi-agent workflows with branching logic, and prompt templates and personas are YAML files. It works with OpenAI, Google Gemini and Anthropic APIs, and with local models through Ollama and LMStudio, and each agent can use a different model.

Use cases: agent-orchestration, prompt-engineering

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Languages: PythonREADME
Packages: agentforge (pypi)README
Multi-agent: YesREADME
Orchestration: otherREADME
Model providers: openai, google, anthropic, ollamaREADME
Maturity: Betagithub.com

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Alternatives

Frameworks for the same language with a similar way of orchestrating agents.

Signals

Stars: 860
Forks: 162
Open issues: 5
Weekly downloads: 241
Last commit: Aug 10, 2026 (2 months ago)
Last release: Feb 9, 2025 (1 year ago)
Last package publish: Aug 10, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Packages: pypi agentforge
License: GPL-3.0
Repository: github.com/DataBassGit/AgentForge
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql