forge

by antoinezambelli · Agent Tool · ★ 1.6k

About forge

forge A reliability layer for self-hosted LLM tool-calling. Forge lifts an 8B local model to the top of its class on multi-step agentic workflows through guardrails (rescue parsing, retry nudges, step enforcement) and context management (VRAM-aware budgets, tiered compaction). The current top self-hosted config (Ministral-3 8B Instruct Q8 on llama-server) scores 86.5% across forge's 26-scenario eval suite — and 76% on the hardest tier. Three ways to use it: WorkflowRunner — Define tools, pick a backend, run structured agent loops.

agentic-aiagentic-workflowagentsfunction-callingllama-cppllamafilellmollamapythonself-hosted

Quick Facts

Stars1,599
Forks86
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score53.074/100
Open Issues16
Last Updated2026-05-22
Created2026-02-16
Platformspython
Est. Tokens~165k

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is forge?

forge is A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows. It is categorized as a Agent Tool with 1.6k GitHub stars.

What programming language is forge written in?

forge is primarily written in Python. It covers topics such as agentic-ai, agentic-workflow, agents.

How do I install or use forge?

You can find installation instructions and usage details in the forge GitHub repository at github.com/antoinezambelli/forge. The project has 1.6k stars and 86 forks, indicating an active community.

What license does forge use?

forge is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Agent Tool tools