by antoinezambelli · AI 工具 · ★ 2.3k
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.
| Stars | 2,257 |
| Forks | 173 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 69.0813162037958/100 |
| Open Issues | 3 |
| Last Updated | 2026-10-15 |
| Created | 2026-02-16 |
| Platforms | python |
| Est. Tokens | ~16k |
Explore other popular ai 工具 tools:
forge is A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows. It is categorized as a AI 工具 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 173 forks, indicating an active community.
forge is released under the MIT license, making it free to use and modify according to the license terms.