by antoinezambelli · Agent Tool · ★ 2.3k
forge A reliability layer for self-hosted LLM tool-calling. You give forge a set of tools; the model calls whichever it wants in whatever order. Workflow structure is opt-in — , , and let you constrain the loop when you need to, but forge's guardrails (rescue parsing, retry nudges, response validation) apply with zero required steps too. Forge takes an 8B local model from single digits to 84% across forge's 26-scenario v0.7.0 eval suite — and even lifts Sonnet 4.6 from 85% to 98% on the same workload (Anthropic numbers measured in v0.6.0; not re-run in v0.7.0 since the cost is non-trivial).
| Stars | 2,262 |
| Forks | 174 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 38.25/100 |
| Open Issues | 3 |
| Last Updated | 2026-10-24 |
| Created | 2026-02-16 |
| Platforms | python |
| Est. Tokens | ~164k |
These tools work well together with forge for enhanced workflows:
Explore other popular agent tool tools:
forge is A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows. It is categorized as a Agent Tool with 2.3k GitHub stars.
forge is primarily written in Python. It covers topics such as agentic-ai, agentic-workflow, agents.
You can find installation instructions and usage details in the forge GitHub repository at github.com/antoinezambelli/forge. The project has 2.3k stars and 174 forks, indicating an active community.
forge is released under the MIT license, making it free to use and modify according to the license terms.